CSEDU 2022 Abstracts


Area 1 - Artificial Intelligence in Education

Full Papers
Paper Nr: 8
Title:

Bone Segmentation of the Human Body in Computerized Tomographies using Deep Learning

Authors:

Angelo Antonio Manzatto, Edson José Rodrigues Justino and Edson Emílio Scalabrin

Abstract: The segmentation of human body organs in medical imaging is a widely used process to detect and diagnose diseases in medicine and to help students learn human anatomy in education. Despite its significance, segmentation is time consuming and costly because it requires experts in the field, time, and the requisite tools. Following the advances in artificial intelligence, deep learning networks were employed in this study to segment computerized tomography images of the full human body, made available by the Visible Human Project (VHP), which included among 19 classes (18 types of bones and background): cranium, mandible, clavicle, scapula, humerus, radius, ulna, hands, ribs, sternum, vertebrae, sacrum, hips, femur, patella, tibia, fibula, and feet. For the proposed methodology, a VHP male body tomographic base containing 1865 images in addition to the 20 IRCAD tomographic bases containing 2823 samples were used to train deep learning networks of various architectures. Segmentation was tested on the VHP female body base containing 1730 images. Our quantitative evaluation of the results with respect to the overall average Dice coefficient was 0.5673 among the selected network topologies. Subsequent statistical tests demonstrated the superiority of the U-Net network over the other architectures, with an average Dice of 0.6854.
Download

Paper Nr: 10
Title:

Fine-grained Detection of Academic Emotions with Spatial Temporal Graph Attention Networks using Facial Landmarks

Authors:

Hua Leong Fwa

Abstract: With the incidence of the Covid-19 pandemic, institutions have adopted online learning as the main lesson delivery channel. A common criticism of online learning is that sensing of learners’ affective states such as engagement is lacking which degrades the quality of teaching. In this study, we propose automatic sensing of learners’ affective states in an online setting with web cameras capturing their facial landmarks and head poses. We postulate that the sparsely connected facial landmarks can be modelled using a Graph Neural Network. Using the publicly available in the wild DAiSEE dataset, we modelled both the spatial and temporal dimensions of the facial videos with a deep learning architecture consisting of Graph Attention Networks and Gated Recurrent Units. The ablation study confirmed that the differencing of consecutive frames of facial landmarks and the addition of head poses enhance the detection performance. The results further demonstrated that the model performed well in comparison with other models and more importantly, is suited for implementation on mobile devices with its low computational requirements.
Download

Paper Nr: 29
Title:

A New Way to Characterize Learning Datasets

Authors:

Célina Treuillier and Anne Boyer

Abstract: The student’s interaction with Virtual Learning Environments (VLE) produces a large amount of data, known as learning traces, which is commonly used by the Learning Analytics (LA) domain to enhance the learning experience. Digital learning systems are generally based on the processing of these traces and must be able to adapt to different student profiles. However, the information provided in raw traces is diversified and can’t be directly used for the profile identification task: it requires defining learning indicators pedagogically relevant, and measurable directly from learning traces, and then classify learners profiles according to these indicators. The paper’s main contribution remains on the characterization of LA datasets both in terms of groups sizes and observed digital behaviors. It answers the lack of clearly stated information for LA systems developers, who need to ensure that their algorithms do not introduce bias, especially by disfavoring specific categories of students, which would only worsen existing inequalities in the student population. To go further, the embodiment of these identified profiles by translating them into learner personas also participates in the improvement of the explicability of LA outcomes by providing easy-to-interpret descriptions of students. These personas consist of fictitious representative student profiles, expressing different needs and learning objectives to which the LA systems must respond.
Download

Paper Nr: 45
Title:

Introducing a Framework for Code based Fairness Audits of Learning Analytics Systems on the Example of Moodle Learning Analytics

Authors:

Hassan Tagharobi and Katharina Simbeck

Abstract: Machine learning based predictive systems are increasingly used in various areas, including learning analytics (LA) systems. LA systems provide educators with an analysis of students’ progress and offer predictions about their success. Although predictive systems provide new opportunities and convenience, studies show that they harbor risks for biased or even discriminatory outcomes. To detect and solve these discriminatory issues and examine algorithmic fairness, different approaches have been introduced. The majority of purposed approaches study the behavior of predictive systems using sample data. However, if the source code is available, e.g., for open-source projects, auditing it can further improve the examination of algorithmic fairness. In this paper, we introduce a framework for an independent audit of algorithmic fairness using all publicly available resources. We applied our framework on Moodle learning analytics and examined its fairness for a defined set of criteria. Our fairness audit shows that Moodle doesn’t use protected attributes, e.g., gender, ethnicity, in its predictive process. However, we detected some issues in data distribution and processing, which could potentially affect the fairness of the system. Furthermore, we believe that the system should provide users with more detailed evaluation metrics to enable proper assessment of the quality of learning analytics models.
Download

Paper Nr: 76
Title:

Vocabulary Volume: A New Metric for Assessing Vocabulary Knowledge

Authors:

Dolça Tellols, Takenobu Tokunaga and Hikaru Yokono

Abstract: This paper presents Vocabulary Volume, a new metric to assess vocabulary knowledge. The existing metrics for vocabulary knowledge assessment rely on word difficulty, which is often defined in terms of the use frequency of words. In addition to word difficulty, our proposed metrics consider the semantic diversity of words. To formalise semantic diversity, every word is transformed into a vector representation in the semantic space by using the word embedding techniques developed in the natural language processing research. The semantic diversity is defined as the volume of a convex hull that covers all points corresponding to the words. The Vocabulary Volume score (VVS) is calculated from both semantic diversity and word difficulty. To prove the validity of our proposed metric, we conducted experiments using data gathered from Japanese language learners and native Japanese speakers. The experiments explored various options for each component in calculating VVS: word embeddings, dimension reduction methods, and word difficulty scale. The metric was evaluated by distinguishing between the learners’ responses with different levels of language proficiency. The experimental results suggested the best configuration of the components and showed that our proposed metric is better than an existing metric that considers only word difficulty.
Download

Paper Nr: 98
Title:

Implementing Open-Domain Question-Answering in a College Setting: An End-to-End Methodology and a Preliminary Exploration

Authors:

Augusto Gonzalez-Bonorino, Eitel J. M. Lauría and Edward Presutti

Abstract: Advances in Artificial Intelligence and Natural Language Processing (NLP) can be leveraged by higher-ed administrators to augment information-driven support services. But due to the incredibly rapid innovation rate in the field, it is challenging to develop and implement state-of-the-art systems in such institutions. This work describes an end-to-end methodology that educational institutions can utilize as a roadmap to implement open domain question-answering (ODQA) to develop their own intelligent assistants on their online platforms. We show that applying a retriever-reader framework composed of an information retrieval component that encodes sparse document vectors, and a reader component based on BERT -Bidirectional Encoder Representations from Transformers- fine-tuned with domain specific data, provides a robust, easy-to-implement architecture for ODQA. Experiments are carried out using variations of BERT fine-tuned with a corpus of questions and answers derived from our institution’s website.
Download

Paper Nr: 125
Title:

Analyzing Student Programming Paths using Clustering and Process Mining

Authors:

Anis Bey and Ronan Champagnat

Abstract: Learning programming is becoming more and more common across all curricula, as seen by the growing number of tools and platforms built to assist it. This paper describes the results of an empirical study that aimed to better understand students’ programming habits. The analysis is based on unsupervised classification algorithms, including features from previous educational data mining research. The k-means method was used to identify the behaviors of six students profiles. The main and interaction impacts of those behaviors on their final course scores are tested using analysis of covariance.
Download

Paper Nr: 132
Title:

On Deep Learning Approaches to Automated Assessment: Strategies for Short Answer Grading

Authors:

Abbirah Ahmed, Arash Joorabchi and Martin J. Hayes

Abstract: The recent increase in the number of courses that are delivered in a blended fashion, before the effect of the pandemic has even been considered, has led to a concurrent interest in the question of how appropriate or useful automated assessment can be in such a setting. In this paper, we consider the case of automated short answer grading (ASAG), i.e., the evaluation of student answers that are strictly limited in terms of length using machine learning and in particular deep learning methods. Although ASAG has been studied for over 50 years, it is still one of the most active areas of NLP research as it represents a starting point for the possible consideration of more open ended or conversational answering. The availability of good training data, including inter alia, labelled and domain-specific information is a key challenge for ASAG. This paper reviews deep learning approaches to this question. In particular, deep learning models, dataset curation, and evaluation metrics for ASAG tasks are considered in some detail. Finally, this study considers the development of guidelines for educators to improve the applicability of ASAG research.
Download

Paper Nr: 141
Title:

Exploring the Limits of Lexicon-based Natural Language Processing Techniques for Measuring Engagement and Predicting MOOC’s Certification

Authors:

Esther Félix, Nicolas Hernandez and Issam Rebaï

Abstract: We address the problem of assessing the contributions of lexicon-based Natural Language Processing (NLP) techniques to measure learner affective and cognitive engagement and thus predict certification in French- speaking MOOCs. Interest in these approaches comes from the fact they are explainable. Our investigation protocol consists of applying machine learning techniques to determine the relationships between lexicon-based engagement indicators and learning outcomes. The lexicon-based approach is compared with trace log features, and we distinguish between specialised linguistically-based approaches with dedicated lexicon resources and more general but deeper text representations. Language quality and its impact on the task are discussed. We investigate this issue in MOOCs imposing or not the use of the forum in their learning activities.
Download

Paper Nr: 151
Title:

Sequencing and Recommending Pedagogical Activities from Bloom’s Taxonomy using RASI and Multi-objective PSO

Authors:

Denis José Almeida, Márcia Aparecida Fernandes and Newarney Torrezão da Costa

Abstract: According to student needs, learning can be supported and enhanced through structured and personalized instruction. This paper presents an approach to personalized pedagogical recommendations based on the student’s cognitive profile, given by the Revised Approaches to Studying Inventory (RASI). The recommended pedagogical actions follow the hierarchy of Revised Bloom’s Taxonomy. We model the sequencing of pedagogical actions as a multi-objective optimization problem. This problem solution was implemented using a Particle Swarm Optimization (PSO) algorithm. The optimized objectives in this problem are the similarity between the student’s profile and the sequence of actions, and the number of actions appropriate to the student’s profile. Experiments conducted with students in higher education institutions suggest that the proposed approach using PSO presents solutions that are better accepted by students than the randomized pedagogical recommendation.
Download

Paper Nr: 172
Title:

Designing a Learning Analytics Dashboard to Provide Students with Actionable Feedback and Evaluating Its Impacts

Authors:

Xiaojing Duan, Chaoli Wang and Guieswende Rouamba

Abstract: Various educational settings have begun to increasingly leverage the power of data analytics to optimize the learning environment and enhance the learning experience for students. However, despite this effort, significant research gaps still exist around utilizing educational data mining to provide students with actionable feedback and assess the comprehensive impact of data-informed feedback on students. In this study, a learning analytics dashboard was designed to provide students with actionable feedback to advance their self-regulated learning skills and improve their course performance. A rigorous inquiry using mixed methods was also conducted to study the dashboard’s impacts on students. It found that students’ use of the dashboard was positively correlated with their course performance, and those who viewed the dashboard had higher course ranks. In addition, it showed that students’ use of the dashboard was positively correlated with their homework submission time, and those who viewed the dashboard submitted homework earlier as the course progressed. The inquiry also revealed that students had mixed feelings about the dashboard, including motivation and anxiety.
Download

Short Papers
Paper Nr: 18
Title:

Keep It Up: In-session Dropout Prediction to Support Blended Classroom Scenarios

Authors:

Nathalie Rzepka, Katharina Simbeck, Hans-Georg Müller and Niels Pinkwart

Abstract: Dropout prediction models for Massive Open Online Courses (MOOCs) have shown high accuracy rates in the past and make personalized interventions possible. While MOOCs have traditionally high dropout rates, school homework and assignments are supposed to be completed by all learners. In the pandemic, online learning platforms were used to support school teaching. In this setting, dropout predictions have to be designed differently as a simple dropout from the (mandatory) class is not possible. The aim of our work is to transfer traditional temporal dropout prediction models to in-session dropout prediction for school-supporting learning platforms. For this purpose, we used data from more than 164,000 sessions by 52,000 users of the online language learning platform orthografietrainer.net. We calculated time-progressive machine learning models that predict dropout after each step (completed sentence) in the assignment using learning process data. The multilayer perceptron is outperforming the baseline algorithms with up to 87% accuracy. By extending the binary prediction with dropout probabilities, we were able to design a personalized intervention strategy that distinguishes between motivational and subject-specific interventions.
Download

Paper Nr: 32
Title:

An Online Controlled Experiment Design to Support the Transformation of Digital Learning towards Adaptive Learning Platforms

Authors:

Nathalie Rzepka, Katharina Simbeck, Hans-Georg Müller and Niels Pinkwart

Abstract: Digital learning platforms are more and more used in blended classroom scenarios in Germany. However, as learning processes are different among students, adaptive learning platforms can offer personalized learning, e.g. by individual feedback and corrections, task sequencing, or recommendations. As digital learning platforms are already used in classroom settings, we propose the transformation of these platforms into adaptive learning environments. To measure the effectiveness and improvements achieved through the adaptions an online-controlled experiment design is created. Our result is a process that consists of the target definition, development of the prediction model, definition of the adaptions, building the experiment architecture, the experimental period, and the hypothesis testing. As an example, we apply this design exemplarily to an online learning platform for German spelling and grammar. In this way, we contribute to the research field by bridging the gap between adaptive learning technology and the process of transformations and experiment designs.
Download

Paper Nr: 35
Title:

WawaSimi: Classification Techniques for Phonological Processes Identification in Children from 3 to 5 Years Old

Authors:

Braulio Baldeon, Renzo Ravelli and Willy Ugarte

Abstract: In the context of the pandemic we are living in, most of the interactions between kindergarten-aged children has decreased, meaning that their language development might be slowed down. Our work presents a machine learning-based method for the classification of phonological processes and a corpus with a total of 3,324 audios, being 40% of them audios with a correct pronunciation, and the remaining 60% wrong. One of the main problems encountered when trying to perform children speech recognition in Spanish, is, to the best of our knowledge, the lack of a corpus. 329 audios were collected from 20-30 years old adults and a voice conversion technique was applied in order to generate the required audios for the corpus construction. A modified AlexNet was trained to classify if a word was correctly pronounced, if the audio was classified as mispronounced, it goes through a second AlexNet to classify which kind of Phonological Process is found in the word.
Download

Paper Nr: 71
Title:

Digital Device and Mathematics: Multilevel vs Machine Learning Models for Value-added Ranking in Italy

Authors:

Donatella Papa

Abstract: With the COVID-19 pandemic and the development of distance education programs, digital learning is popular and strategic in many learning fields. The deployment of Information and Communications Technology and its impact on both national and international learning programs are becoming increasingly significant. This study seeks to explore in the Italian context both the effectiveness of digital learning in Mathematics Education and which features and how affect value-added at the classroom level. To explore Information and Communications Technology contribution and value-added scoring, the study takes into consideration the analytical power of classical multilevel models concerning the predictive power of different types of machine learning models. The study aims to investigate how Information and Communications Technology, and related concepts, impact the Weighted Likelihood Estimates in Mathematics for students in the lower secondary school, using data from the INVALSI of the school year 2017/2018. The main finding is that Personal Computer ownership at home plays an important role in mathematical learning. Finally, a machine learning model incorporated in the educational domain can be an interesting starting point for developing class-predictive policies.
Download

Paper Nr: 114
Title:

Development, Implementation and Acceptance of an AI-based Tutoring System: A Research-Led Methodology

Authors:

Tobias Schmohl, Kathrin Schelling, Stefanie Go, Katrin Jana Thaler and Alice Watanabe

Abstract: This Design-Based Research (DBR) project aims to develop an intelligent tutoring system (ITS) for higher education. The system will collect teaching and learning materials in audio and video formats (e.g., podcasts, lecture recordings, screencasts, and explainer videos), and store them on a learning experience platform (LXP). Then, the ITS will process them with the help of speech recognition to gain data which, in turn, will be used to power further applications: Using artificial intelligence (AI), the platform will allow users to search the materials, automatically compiling them according to criteria like lesson subject, language, medium, or required prior knowledge. By the end of the last DBR cycle, the ITS will also provide a more active form of support: It will automatically generate exercises based on predefined patterns and teaching materials, thus allowing learners to check up on their learning progress autonomously. In order to closely match the ITS’s features to the needs and learning habits of students in higher education, the development of this AI-based tutoring system is accompanied by an interdisciplinary team which will continuously re-evaluate and adapt the concept over the course of several DBR cycles. Our goal is to derive implications for the system’s technical development by collecting and evaluating educational research data (mixed methods design; primary and secondary research methods).
Download

Paper Nr: 120
Title:

A Machine Learning based Eye Tracking Framework to Detect Zoom Fatigue

Authors:

Anjuli Patel, Paul Stynes, Anu Sahni, David Mothersill and Pramod Pathak

Abstract: Zoom Fatigue is a form of mental fatigue that occurs in online users with increased use of video conferencing. Mental fatigue can be detected using eye movements. However, detecting eye movements in online users is a challenge. This research proposes a Machine Learning based Eye Tracking Framework (MLETF) to detect zoom fatigue in online users by analysing the data collected by an eye tracker device and other influencing variables such as sleepiness and personality. An experiment was conducted with 31 online users wearing an eye tracker device while watching a lecture on Mobile Application Development. The online users were given an exam followed by a questionnaire. The first exam was based on the content of the video. The online users were then given a personality questionnaire. The results of the exam and the personality test were combined and used as an input to five machine learning algorithms namely, SVM, KNN, Decision Tree, Logistic Regression and Ada-Boost. Results of the five models are presented in this paper based on a confusion matrix. Results show promise for Ada-Boost for detecting Zoom fatigue in online users with an accuracy of 86%. This research demonstrates the feasibility of applying an eye-tracker device to identify zoom fatigue with online users of video conferencing.
Download

Paper Nr: 156
Title:

Conversational Analysis to Recommend Collaborative Learning in Distance Education

Authors:

Antônio J. Moraes Neto, Márcia A. Fernandes and Tel Amiel

Abstract: Conversational agents can recommend interactions among students in a Virtual Learning Environment (VLE) for the purpose of supporting collaborative learning, an important approach to improve online education. This paper describes the current position of a research that addresses the implementation of Conversational Analysis (CA) in order to make recommendations through chatbots for promoting collaborative learning among students in a VLE. Based on an experiment, the authors propose a CA strategy to determine the level of collaboration among students, point out possibilities for chatbot’s intervention in favor of collaborative learning, and present the results obtained in the current stage of the research.
Download

Paper Nr: 157
Title:

An Approach to Teaching Applied Machine Learning with Autonomous Systems Integration

Authors:

Chad Mello, Adrian De Freitas and Troy Weingart

Abstract: We propose an applied machine learning course that teaches students with no machine learning background how to train and use deep learning models for deploying aerial drones (multi-copters). Our unique, hands-on curriculum gives students insight into the algorithms that power autonomous systems as well as the hardware technology on which they execute. Students learn how to integrate Python code with serial communications for streaming sensors and imagery to deep learning models. Students use OpenCV, Keras, and TensorFlow to learn about computer vision and deep learning. The final project (see Figure 1) provides the opportunity for students to plan and develop an end-to-end, fully autonomous, self-contained product (i.e. all systems physically residing on the drone itself) that is integrated with heavy-payload drones and computer vision in a scenario centered around an outdoor search and rescue mission. With no human in the loop, students deploy drones in search of a missing person. The drone locates and identifies the individual, delivers a care package to their location, and then reports the individual’s geolocation to ground rescuers before returning home. The novel helper code and solutions are built in-house using Python and open technologies. Results from a pilot offering in the spring of 2021 indicate that our approach is effective and engaging for computer and cyber science students who have previously taken a basic artificial intelligence course and who have 1-2 years of programming experience. This paper details the design, focus, and methodology behind our Autonomous Systems Integration curriculum as well as the challenges we encountered during its debut.
Download

Paper Nr: 170
Title:

LAOps: Learning Analytics with Privacy-aware MLOps

Authors:

Pia Niemelä, Bilhanan Silverajan, Mikko Nurminen, Jenni Hukkanen and Hannu-Matti Järvinen

Abstract: The intake of computer science faculty has rapidly increased with simultaneous reductions to course personnel. Presently, the economy is recovering slightly, and students are entering the working life already during their studies. These reasons have fortified demands for flexibility to keep the target graduation time the same as before, even shorten it. Required flexibility is created by increasing distance learning and MOOCs, which challenges students’ self-regulation skills. Teaching methods and systems need to evolve to support students’ progress. At the curriculum design level, such learning analytics tools have already been taken into use. This position paper outlines a next-generation, course-scope analytics tool that utilises data from both the learning management system and Gitlab, which works here as a channel of student submissions. Gitlab provides GitOps, and GitOps will be enhanced with machine learning, thereby transforming as MLOps. MLOps that performs learning analytics, is called here LAOps. For analysis, data is copied to the cloud, and for that, it must be properly protected, after which models are trained and analyses performed. The results are provided to both teachers and students and utilised for personalisation and differentiation of exercises based on students’ skill level.
Download

Paper Nr: 61
Title:

A Free and Open Dataset from a Prototypical Data-driven Study Assistant in Higher Education

Authors:

Johannes Schrumpf, Felix Weber, Katharina Schurz, Niklas Dettmer and Tobias Thelen

Abstract: Digital study assistants (DSAs) are an as of yet sparsely explored method to build bridges between classical, on-campus higher education and novel digital education opportunities. The DSA we present in this paper (SIDDATA) aims at supporting students to identify, reflect upon and follow their personal educational goals. Over the course of 11 months, students interacted with a prototype version 2.0 of the software, generating data about what features were interacted with, users' study-related data, and which features were deemed as useful. In this data paper, we present a preprocessed version of the DSA database for research in the domain of digital higher education. We present the data model design of the DSA and its relation to its’ features. We further expand on the data extraction method used to generate the present dataset from the DSA’s database. We discuss potential research paths that can be explored based on the dataset as well as its limitations
Download

Paper Nr: 62
Title:

A Dynamic Indicator to Model Students’ Digital Behavior

Authors:

Oriane Dermy, Anne Boyer and Azim Roussanaly

Abstract: During the first French Covid19 lockdown, students had to switch to a fully online learning mode. Therefore, understanding students’ digital behavior becomes crucial for analysts serving public institution policy. In particular, they want to determine and interpret the evolution of students’ digital behavior. This paper aims to offer them indicators. We propose to study generic student logs corresponding to standard digital workspace services. Therefore, this paper contributes to the scientific question: Can we give an easy-to-interpret and visual indicator to model students’ behavior changes from poor and generic data? We first verify that we can extract epidemic-specific temporal patterns on these logs using Contrast Mining. These patterns represent students’ behaviors and pace. Then, we propose a new method called Temporal Pattern Histories (TPH), representing the evolution of the temporal patterns’ over time. It is a dynamic representation of students’ digital behavior. Using this method, we present graphically abrupt changes during the Cov19 lockdown, and we give some hypotheses about these results. This case study proves the relevance of TPH to detect and analyze students’ behavioral changes in an interpretive way. This approach has the advantage of representing the global evolution of students’ behavior without giving students specific information.
Download

Area 2 - Information Technologies Supporting Learning

Full Papers
Paper Nr: 7
Title:

Personalized Curiosity Engine (Pique): A Curiosity Inspiring Cognitive System for Student Directed Learning

Authors:

Safat Siddiqui, Mary Lou Maher, Nadia Najjar, Maryam Mohseni and Kazjon Grace

Abstract: Pique is an AI-based system for student directed learning that is inspired by a cognitive model of curiosity. Pique encourages self-directed learning by presenting a sequence of learning materials that are simultaneously novel and personalized to learners’ interests. Pique is a web-based application that applies computational models of novelty to encourage curiosity and to inspire learners’ intrinsic motivation to explore. We describe the architecture of the Pique system and its implementation in personalizing learning materials. In exploring the use of Pique by students in undergraduate and graduate courses in Computer Science, we have developed and implemented two computational models of novelty using Natural Language Processing techniques and concepts from recommender systems. In this paper, we describe the Pique model, the computational models for measuring novelty in text-based documents, and the computational models for generating sequences of personalized curiosity-eliciting learning materials. We report the response from students in the use of Pique in four courses over two semesters. The contribution of this paper is a unique approach for personalized learning that encourages curiosity.
Download

Paper Nr: 11
Title:

An Intervention with Technology for Parental Involvement in Kindergarten: Use of Design-based Research Methodology

Authors:

Dionisia Laranjeiro, Maria João Antunes and Paula Santos

Abstract: Parental involvement in preschool education has an impact on children's learning, development and adaptation to school, and can be promoted through digital technologies. This research aimed to develop and test a digital platform, with functionalities for communication and content sharing between parents and educators and, at the same time, to assess the impact of using the platform in three participating institutions. The methodology used was Design-Based Research. Parents and educators were involved in all phases: preliminary study, development and evaluation. The results allow us to conclude that the most important functionalities are the sharing of activities carried out with children in kindergarten and a private messaging service. In terms of local impact, the intervention had different results in each kindergarten, associated with previous practices of using technologies for parental involvement and the roles assumed by the users within the platform.
Download

Paper Nr: 23
Title:

Free Online Training and Value Perception in France

Authors:

Gail Tidey, Laurent Dedieu, Annabel Levert and Jean-Christophe Sakdavong

Abstract: Digital training has taken on a major place in our society with the health crisis. Among the many online training offers available, some are free of charge, so that the user does not have to pay for his or her learning, and we can sometimes wonder about the value of these training courses: do they offer the same quality as the paid ones? After collecting data from 245 people, our study shows that the price of an e-learning course does not necessarily influence the value that the user attributes to it, and that a free course can have the same value and interest as a paid course. Moreover, free training is a significant marker in the decision-making process: it gives the training an additional benefit, which goes beyond the mere monetary savings made, compared to the same paid offer. Therefore, free training can give the user the perception of a greater general benefit than paid training.
Download

Paper Nr: 24
Title:

Using Inclusive Design for People with Cognitive Limitations to Develop Online Training in the Workplace

Authors:

Louise Sauvé, Patrick Plante, Gustavo Adolfo Angulo Mendoza, Caroline Brassard and Guillaume Desjardins

Abstract: Whether it's downloading applications, doing research, using communication tools, shopping online, filling out a form or finding directions, having good digital competencies is essential in our contemporary society. But what about people with cognitive limitations (PCLs)? It appears that more than 31% of PCLs do not have the basic competencies to face this new digital reality and thus function harmoniously in society. To enable them to become autonomous in activities requiring the use of the Internet via a tablet, a research and development project is underway to create TAQ-TIC, an online digital literacy learning environment adapted to their needs. Using an inclusive design approach that puts the learner at the heart of the creation process, we validated the design, usability, and pedagogical readability of TAQ-TIC with PCLs. Findings emerged that allowed us to make recommendations for online training intended for PCLs, notably the addition of navigation indicators and contextual aids, the cleaning up of screen pages both graphically and textually, and the predominant use of video-based content.
Download

Paper Nr: 38
Title:

What Indicators Can I Serve You with? An Evaluation of a Research-Driven Learning Analytics Indicator Repository

Authors:

Atezaz Ahmad, Jan Schneider, Joshua Weidlich, Daniele Di Mitri, Jane Yin-Kim Yau, Daniel Schiffner and Hendrik Drachsler

Abstract: In recent years, Learning Analytics (LA) has become a very heterogeneous research field due to the diversity in the data generated by the Learning Management Systems (LMS) as well as the researchers in a variety of disciplines, who analyze this data from a range of perspectives. In this paper, we present the evaluation of a LA tool that helps course designers, teachers, students and educational researchers to make informed decisions about the selection of learning activities and LA indicators for their course design or LA dashboard. The aim of this paper is to present Open Learning Analytics Indicator Repository (OpenLAIR) and provide a first evaluation with key stakeholders (N=41). Moreover, it presents the results of the prevalence of indicators that have been used over the past ten years in LA. Our results show that OpenLAIR can support course designers in designing LA-based learning activities and courses. Furthermore, we found a significant difference between the relevance and usage of LA indicators between educators and learners. The top rated LA indicators by researchers and educators were not perceived as equally important from students' perspectives.
Download

Paper Nr: 44
Title:

Trends and Issues in STEM + C Research: A Bibliometric Perspective

Authors:

Hanxiang Du, Wanli Xing, Bo Pei, Yifang Zeng, Jie Lu and Yuanlin Zhang

Abstract: The integration of computing education or computational thinking with STEM majors has gained substantial research interests. A number of research papers of the topic were published. This work is to provide a comprehensive overview of literature in the STEM + C field through both bibliometric and content analysis. We conducted a systematic search to identify articles and utilized machine-learning-based techniques to analyze these articles. Common bibliometric indicators were used for bibliometric analysis. Machine-learning-based text mining techniques such as LDA topic modelling and flow analysis were used for content analysis. Our analysis spotted STEM + C publication trends, popular topics and their dynamics over time. This work also pinpointed commonly used methodologies for integration study for both PK, K–12 and higher education. Meanwhile, several future research directions were identified. This work contributes to the literature by systematically examining the existing literature and bringing machine-learning-based data mining techniques to the analysis.
Download

Paper Nr: 53
Title:

Features of Micro-credential Platforms in Higher Education

Authors:

Padmasheela Kiiskilä, Ahmed Hanafy and Henri Pirkkalainen

Abstract: Interest in and demand for micro-credentials in higher education institutions is on the rise. Although the concept of micro-credentials is still evolving, they can be seen as short learning opportunities that are accompanied by digital credentials that capture the proofs of the learning. These digital proofs of learning range from skills and competences acquired to information whether such skills were acquired via formal or non-formal learning activities. Micro-credential platforms are used for multiple purposes including issuing, viewing, and storing the digital credentials. Despite the growth in the number of micro-credential platforms in the recent years, literature is limited on the features offered by the platforms and how they are helpful for higher education institutions and learners. To address this gap in research, we employed a qualitative approach by semi-structured interviews and group discussions with platform providers and education experts. Our findings resulted in 38 features that can help higher education institutions, learners, and providers understand what kind of features are emphasized in micro-credential platforms and how they can be helpful for different use purposes. As practical implications, the findings of this study can help higher education institutions in considering adoption and usage of micro-credential platform.
Download

Paper Nr: 107
Title:

Ethical Perception of a Digital Study Assistant: Student Survey of Ethical Values

Authors:

Paul Greiff, Carla Reinken and Uwe Hoppe

Abstract: The digital transformation in higher education progresses constantly. Here, new technical innovations are emerging, such as a digital study assistant (DSA). The DSA is designed to help students to identify and achieve their personal study goals. In this regard, it should be noted that ethical considerations play an increasingly important role in the introduction of digital systems and thus also in the DSA. Therefore, the user-centered perspective is taken into account in the development of a DSA by addressing personal ethical values. For this purpose, two consecutive surveys were conducted with 42 and 156 students from a German university. The aim of the work is to identify ethical values in relation to the DSA that were perceived as particularly important by students as the main user group. From this, practical implications and further research possibilities regarding DSAs and ethical issues can be derived.
Download

Paper Nr: 109
Title:

Word2Course: Creating Interactive Courses from as Little as a Keyword

Authors:

Sébastien Foucher, Damián Pascual, Oliver Richter and Roger Wattenhofer

Abstract: In this work, we introduce a novel pipeline that enables the generation of multiple-choice questions and exercises from as little as a topic keyword. Hence, providing users the possibility to start with a study objective in mind and then automatically generate personalized learning material. The main contributions of this project are a scraper that can extract relevant information from websites, a novel distractor generation method that can make use of context and a technique to automatically combine text and questions into interactive exercises. Our novel distractor generation method was tested in a human survey which showed that the distractor generation quality is comparable to hand crafted distractors. The pipeline is built into a web application that lets users refine the results for each step, openly accessible at https://adaptive-teaching.com.
Download

Paper Nr: 115
Title:

Using Software Reasoning to Determine Domain-law Violations and Provide Explanatory Feedback: Expressions Tutor Example

Authors:

Oleg Sychev, Nikita Penskoy and Grigory Terekhov

Abstract: Introducing students to a new subject domain involves getting them acquainted with many new concepts. Some of these students need a trial-and-error process to learn these concepts, but it is time-consuming for teachers. An intelligent tutor capable of detecting domain-law violations and providing explanatory feedback can allow training until learning without supervision. This is especially important when teaching software engineering because it requires learning a lot of new concepts and has well-defined laws. Our goal was to develop a tutor capable to explain to the student the cause of their errors: the subject-domain laws that they violated. We present an approach to modeling subject-domain concepts and laws that allows finding correct answers and determining law violations in students’ answers. A web-based tool for learning the order of evaluation for programming-language expressions was developed to assess the viability of this approach. The experiments show that Apache Jena and Clingo inference engines work quickly enough to find domain-law violations after each error in middle-sized tasks. The developed tool was evaluated by volunteer undergraduate students and received positive feedback. After the initial evaluation, the tool was used in the learning process; the students’ learning gains after using the system were statistically significant.
Download

Paper Nr: 116
Title:

Towards a Machine Learning Flow-predicting Model in a MOOC Context

Authors:

Sergio Iván Ramírez Luelmo, Nour El Mawas, Rémi Bachelet and Jean Heutte

Abstract: Flow is a human psychological state positively correlated to self-efficacy, motivation, engagement, and academic achievement, all of which positively affect learning. However, automatic, real-time flow prediction is quite difficult, particularly in a Massively Online Open Course context, because of its online, distant, asynchronous, and educational components. In such context, flow prediction would allow for personalization of activities, content, and learning-paths. By pairing the results of the EduFlow2 and Flow-Q questionnaires (n = 1589, two years data collection) from the French MOOC “Gestion de Projet” (Project Management) to Machine Learning techniques (Logistic Regression), we create a Machine Learning model that successfully predicts flow (combined Accuracy & Precision ~ 0.8, AUC = 0.85) in an automatic, asynchronous fashion, in a MOOC context. The resulting Machine Learning model predicts the presence of flow (0.82) with a greater Precision than it predicts its absence (0.74).
Download

Short Papers
Paper Nr: 3
Title:

Clean Code Tutoring: Makings of a Foundation

Authors:

Nikola Luburić, Dragan Vidaković, Jelena Slivka, Simona Prokić, Katarina-Glorija Grujić, Aleksandar Kovačević and Goran Sladić

Abstract: High-quality code enables sustainable software development, which is a prerequisite of a healthy digital society. To train software engineers to write higher-quality code, we developed an intelligent tutoring system (ITS) grounded in recent advances in ITS design. Its hallmark feature is the refactoring challenge subsystem, which enables engineers to develop procedural knowledge for analyzing code quality and improving it through refactoring. We conducted a focus group discussion with five working software engineers to get feedback for our system. We further conducted a controlled experiment with 51 software engineering learners, where we compared learning outcomes from using our ITS with educational pages offered by a learning management system. We examined the correctness of knowledge, level of knowledge retention after one week, and the learners’ perceived engagement. We found no statistically significant difference between the two groups, establishing that our system does not lead to worse learning outcomes. Additionally, instructors can analyze challenge submissions to identify common incorrect coding patterns and unexpected correct solutions to improve the challenges and related hints. We discuss how our instructors benefited from the challenge subsystem, shed light on the need for a specialized ITS design grounded in contemporary theory, and examine the broader educational potential.
Download

Paper Nr: 5
Title:

A Lightweight Method for Modelling Technology-Enhanced Assessment Processes

Authors:

Michael Striewe

Abstract: Conducting assessments is one of the core processes in educational institutions. It needs careful planning that can be supported by appropriate process models. Many existing assessment process models take a technical perspective and are not necessarily suitable for communication among educators or other people concerned with assessment organization. The paper reports on an alternative and more lightweight modelling approach and provides two sample process models for technology-enhanced assessments to illustrate its usage. Positive results from an evaluation of the modelling method in a workshop with eight participants demonstrate its suitability from the educator’s perspective.
Download

Paper Nr: 6
Title:

Where Does All the Data Go? A Review of Research on E-Assessment Data

Authors:

Michael Striewe

Abstract: E-Assessment systems produce and store a large amount of data that can in theory be interesting and beneficial for students, educators and researchers. While there are already several reviews that elicit commonly used methods as well as benefits and challenges, there is less research about the various contexts and forms in which data from e-assessment system is actually used in research and practice. This paper presents a structured review that provides more insights into the contexts and ways data and data handling is actually included in current research. Results indicate an emphasis on some contexts in current research and that there are two dimensions of data usage.
Download

Paper Nr: 27
Title:

The Influence of Cognitive Presence, Social Presence and Teaching Presence on Online Foreign Language Speaking Anxiety, L2 Motivational Self and Intended Effort-A Structural Equation Modeling Approach

Authors:

Qihui Chen, Wenting Sun and Xiaoling Wang

Abstract: Although a large number of online foreign language oral learners has emerged, little is known about the interactive mechanism between online learning environmental factors and learners’ self-relevant factors. Using the quantitative method, 466 questionnaires of Chinese young adult learners were collected to test the hypothesized relationships between cognitive presence (CP), teaching presence (TP), social presence (SP), L2(second language) motivational self (including Ideal L2 self (IL2) and Ought-to L2 self (OL2)), general self-efficacy (GSE), online foreign language speaking anxiety (AN) and intended efforts (IE) in a structural equation model. The findings illustrate: (1) Online foreign language speaking learners are in middle anxiety, high GSE and high IE level; (2) Online learning environment is an overall ecology in which CP, TP, SP, IL2, OL2, and GSE are highly correlated with each other; (3) In terms of causality, TP and OL2 enhance AN, GSE weakens AN, GSE and OL2 strengthen IE while AN reduces IE. To facilitate online oral foreign language learning, designers of online learning platforms should consider providing the choice of learning partners and more meta-cognition support to guide learners to deal with negative evaluations and manage learning recordings.
Download

Paper Nr: 39
Title:

An Authoring Tool based on Semi-automatic Generators for Creating Self-assessment Exercises

Authors:

Nathalie Guin and Marie Lefevre

Abstract: This article presents ASKER, a tool for teachers to create and disseminate self-assessment exercises for their students. Currently used in the first year of a bachelor's degree at the University of Lyon (France), it enables students to carry out exercises in order to evaluate their acquisition of concepts considered important by the teacher. ASKER enables the creation of exercises (matching, grouping, short open-ended questions, multiple choice questions) that can be used to assess learning in many different fields. To create exercises to assess a concept, the teacher defines a model of exercises that will enable the generation of various exercises, using text or image resources. Such an exercise model is based on constraints that the exercises created from this model must comply with. Automatic generators create, from the resources defined by the teacher, many exercises respecting these constraints. The possibility for the learner to request the generation of several exercises from the same model enables her to assess herself several times on the same concept, without the teacher having to repeatedly define many exercises.
Download

Paper Nr: 40
Title:

A-Learning: A Computerized Adaptive Learning Expert System

Authors:

Mariz Awad, Jailan Salah, Nabila Hamdi and Slim Abdennadher

Abstract: Computer Adaptive Testing (CAT) methods have been widely used by test centres to assess examinees quickly. These methods change question difficulty in response to the performance of the examinee. This work presents a modified framework, which we call Computer Adaptive Learning (CAL). CAL uses the CAT principles to improve exam-training efficiency rather than assessment efficiency. We applied the proposed method to a learning platform and conducted a comparative experiment using 50 participants to investigate the effectiveness of CAL. We evaluated the system in terms of knowledge gain, learning efficiency, and engagement by comparing it to another adaptive method in which the game mechanics and UI adapt to the user’s emotional state. Results confirm that the proposed CAL algorithm exposes the learner to questions more efficiently and improves the learning gain when compared to traditional systems in which difficulty increases sequentially. Engagement, however, did not differ across systems.
Download

Paper Nr: 46
Title:

Chatbot-mediated Learning: Conceptual Framework for the Design of Chatbot Use Cases in Education

Authors:

Stefan Sonderegger and Sabine Seufert

Abstract: While chatbots or conversational agents are already common in many business areas, e.g. for customer support, their use in the education sector is still in its infancy. Chatbots might take over the role of a teacher, tutor, conversational partner, learning analyst, team member, support assistant, or recommender system. Within these different roles, chatbots can enhance learning and inherently address many requirements and success factors for learning. The scalability and adaptiveness of conversational AI allow an individualised learning support for all learners combined with collaboration opportunities and thus more equality in education. In this context, the paper at hand discusses this pedagogical potential of chatbots in different roles and social settings resulting in a conceptual framework for the understanding and design of chatbot use cases in education. Based on success factors for learning derived from established learning theories and reports, core attributes and goals of chatbot learning are deducted within three pedagogical domains of individual, social and analytic chatbot learning. By combining this pedagogical dimension with a technological and content dimension, the presented conceptual framework provides an overview of possibilities of how chatbots in education can be used and designed.
Download

Paper Nr: 48
Title:

Need Finding for an Embodied Coding Platform: Educators’ Practices and Perspectives

Authors:

Tommy Sharkey, Robert Twomey, Amy Eguchi, Monica Sweet and Ying Choon Wu

Abstract: Eight middle- and high-school Computer Science (CS) teachers in San Diego County were interviewed about the major challenges their students commonly encounter in learning computer programming. We identified strategic design opportunities that is, challenges and needs that can be addressed in innovative ways through the affordances of Augmented and Virtual Reality (AR/VR). Thematic Analysis of the interviews yielded six thematic clusters: Tools for Learning, Visualization and Representation, Pedagogical Approaches, Classroom Culture, Motivation, and Community Connections. Within the theme of visualization, focal clusters centered on visualizing problem spaces and using metaphors to explain computational concepts, indicating that an AR/VR coding system could help users to represent computational problems by allowing them to build from existing embodied experiences and knowledge. Additionally, codes clustered within the theme of learning tools reflected educators’ preference for web-based IDEs, which involve minimal start-up costs, as well as concern over the degree of transfer in learning between block- and text-based interfaces. Finally, themes related to motivation, community, and pedagogical practices indicated that the design of an AR coding platform should support collaboration, self-expression, and autonomy in learning. It should also foster self-efficacy and learners’ ability to address lived experience and real-world problems through computational means.
Download

Paper Nr: 54
Title:

A Recommendation System Framework for Educational Content Reinforcement in Virtual Learning Environments

Authors:

Adson R. P. Damasceno, Lucas C. Carneiro, João Victor F. T. De Sampaio, Allberson B. O. Dantas, Eudenia Magalhães, Paulo Henrique M. Maia and Francisco C. M. B. Oliveira

Abstract: In Virtual Learning Environments, tutors play a vital role by supporting students and improving their learning through the courses. One important task is to identify content with which the students struggle and give them suggestions for educational resources to reinforce their learning and overcome difficulties. However, providing individualized suggestions for each student may be infeasible, especially for courses with many enrolled students. In this work, we propose and validate a framework for building recommendation systems of educational content for Virtual Learning Environments. Our proposed system identifies the content that a student needs to reinforce based on the results of his assessments and recommends resources that best relate to the questions that he answered incorrectly, using Information Retrieval, Machine Learning, and Natural Language Processing techniques. We validate our proposed solution by taking as a case study data collected from DAL - Dell Accessible Learning, an distance learning platform. We built a dataset with content from 8 courses to compare the performance of different methods and text representations in our framework. Our best result achieved an accuracy of 0.89 using a Nearest Neighbor method with TF-IDF representation.
Download

Paper Nr: 73
Title:

The Effectiveness of Virtual Team Learning and Its Potential Factors in Entrepreneurship Education Courses

Authors:

Li Chen, Dirk Ifenthaler and Jane Yin-Kim Yau

Abstract: Entrepreneurial instructors and learners are pioneers in adopting virtual team learning processes, despite its novelty and the lack of empirical results showing its effectiveness. In this study, we present an online survey method that was designed to collect data from both students and educators from higher education institutes, in order to analyse the perception of virtual team learning from competence, technologies, and possible factors influencing entrepreneurial education. Findings show that virtual team learning and technologies are effective for entrepreneurship education. Gender, family entrepreneurial history, and prior entrepreneurial experience do not significantly affect respondents’ attitudes. The role, education degree, and field have impaction in certain aspects. This research will help educators and entrepreneurial scholars to adopt virtual team learning in practice and theoretical studies.
Download

Paper Nr: 110
Title:

Investigating Remote Teaching: How Google Meet and Zoom Affect Teachers and Students’ Experience

Authors:

Brenda Aguiar, Franciane Alves, Paulo Gustavo, Vinicius Monteiro, Elizamara Almeida, Leonardo Marques, José Carlos Duarte, Bruno Gadelha and Tayana Conte

Abstract: Due to the suspension of in-person classes caused by the COVID-19 pandemic, educational institutions had to adapt to remote teaching. Thus, videoconferencing tools were adopted to make it possible. However, using these tools can impact the remote teaching experience. In this paper, we present an investigation about the Google Meet and Zoom. We considered teacher and students profiles concerning Usability, a quality attribute that allows assessing the ease of use of user interfaces, and the User Experience (UX), which provides a holistic view focusing on subjective aspects such as affect and emotions. The purpose of Usability and UX is to understand the impacts of the tools on the quality of the remote teaching experience. Our results indicate that besides the tools, the interaction between teacher and student, in the context of synchronous classes, impacts the remote teaching experience, being an essential aspect of discussion and enabling further investigations within the technology-supported education community.
Download

Paper Nr: 111
Title:

Let’s Play! or Don’t? The Impact of UX and Usability on the Adoption of a Game-based Student Response System

Authors:

Myrian Rodrigues, Barbara Nery, Miguel Castro, Victor Klisman, José Carlos Duarte, Bruno Gadelha and Tayana Conte

Abstract: Remote teaching emerged as an alternative to face-to-face classes during the COVID-19 pandemic. In this scenario, teachers adopt formative assessments through different approaches. One of these approaches is Game-based Student Response Systems (GSRS). Kahoot! is a prominent GSRS widely adopted in the educational context. Previous studies investigated the effects and use of Kahoot! by students. Still, none of them reports the teachers’ perception of its Usability and User Experience (UX), attributes that influence the tool’s adoption. This paper presents the usability and UX evaluation of Kahoot! from the point of view of teachers and students. To comparatively visualize the difference in the experience of the two profiles of platform users, we included five students and five teachers in the study. The evaluation results showed that teachers were more dissatisfied, although the positive and negative emotions were similar for the two profiles. We then conducted interviews with the teachers to understand the motives behind their dissatisfaction. The interviews helped us determine which aspects related to usability and UX teachers perceived as critical during the use of Kahoot!.
Download

Paper Nr: 113
Title:

To the Next Level! an Exploratory Study on the Influence of User Experience on the Acceptance of a Gamified Learning Platform

Authors:

Laísa Paiva, Moisés Barbosa, Solano Oliveira, Max Barbosa, Victor Klisman, José Carlos Duarte, Genildo Gomes, Bruno Gadelha and Tayana Conte

Abstract: Gamification is associated with using game elements in different contexts, and one of these is the educational environment. The education area’s motivation for this concept assumes that gamification provides an alternative to motivate and engage students during the learning process. For this, it is common to use gamified teaching platforms, wherein the experience of students and teachers using these platforms impacts the success of their adoption. This paper presents an evaluation of the Classcraft gamified learning platform, aiming to investigate the User Experience (UX) and usability of this platform and how these elements influence its acceptance. We performed an empirical study with a group of high school students to investigate how UX- related factors influence platform acceptance. As a result, we identified that the students do not consider the platform’s visual elements attractive, with insufficient stimulus for its use. Furthermore, we also noted the platform’s low attractiveness and usability through the AttrakDiff results. These results show that using gamification in educational platforms does not mean it will reach a good level of acceptance. To achieve that, it is essential to also look forward to the usability and UX of those platforms.
Download

Paper Nr: 118
Title:

Applying GitHub Services to Support Teaching-learning Strategies in Computer Science Courses

Authors:

Manel Mena, Javier Criado, Isabel M. del Águila, Joaquín Cañadas and Luis Iribarne

Abstract: Computer Science students need to acquire both theoretical and practical use of the knowledge that is covered by the subjects or courses of their degrees. However, sometimes they attend lectures about theoretical concepts that they cannot apply with real development tools that are part of the industry. Therefore, we believe that students have to start working as soon as possible in a similar way to the one they will use in their work once they have finished their studies, considering each course or each deliverable activity as a software development project. This paper describes the solutions adopted and applied to five Computer Science courses in two innovation teaching projects of the University of Almería. Furthermore, we present a series of support teaching tools for managing and creating GitHub projects as GitHub is the core technology for developing teaching-learning activities because of its widespread use. Each course manages its own strategy according to its specific characteristics (i.e., learning objectives, number of students, schedule or programming languages).
Download

Paper Nr: 121
Title:

The World Is Our Classroom: Developing a Model for International Virtual Internships - The Global Innovations Project

Authors:

Paul Doyle, Brian Keegan, Damian Gordon, Anna Becevel, Paul J. Gibson, Zhiying Jiang and Dympna O’Sullivan

Abstract: In the aftermath of COVID-19, remote working has become the norm, and graduates now need an even wider range of skills, which traditional classrooms and internships do not always provide. Working in multiple time zones, within global multi-cultural teams, and only ever meeting colleagues through online technology are just some of the challenges, which require a new type of global graduate. Transversal skills including leadership, collaboration, innovation, digital, green, organization and communication skills are critical. The disruption from COVID-19 also presents unprecedented opportunities to develop more inclusive approaches to internships and international experiences, to level the playing field for students with special needs, from underrepresented groups or with caring commitments. In this position paper, we present a new Global Innovation internship model that has the aim of allowing students to complete technology internships and projects by working together virtually on real world challenges, guided by experienced industry and academic mentors. The model is being developed as part of an Erasmus+ funded project, and the partnership includes seven Higher Education Institutions from six different countries around the world. This position paper describes the design and development of a pilot programme of the Global Innovations internship model.
Download

Paper Nr: 127
Title:

Educational Software Requirements Elicitation Techniques: Including Children with Autistic Spectrum Condition

Authors:

Lucas N. Cabral, J. Antão B. Moura, Marcelo A. de Barros, Laurent Borgmann, Uwe Terton and Carla C. M. Medeiros

Abstract: Although specialized literature and software engineering frameworks suggest techniques for elicitation of software requirements, no elicitation technique works for all situations. Challenges arising from end users’ communication disabilities make choosing an adequate technique even more important to identify these users’ usability and accessibility needs and preferences. Children with such disabilities, e.g. Autistic Spectrum Condition (ASC), are particularly challenging. The literature on software requirements elicitation for children with ASC seems particularly scanty. Here, systematic mapping studies of the literature, analyses of some software development frameworks and recommendations from practicing software engineers were considered to create an initial catalogue of elicitation techniques. Specialists on software and autism were then invited to evaluate the applicability of each of the catalogued techniques for children with an ASC. This paper brings results of such evaluation. As such it may assist software requirements engineers in selecting techniques that are more likely to successfully include children with ASCs in the requirements elicitation process. Future work could experiment with such techniques in (educational) software development contexts.
Download

Paper Nr: 134
Title:

Educational Chatbots: A Sustainable Approach for Customizable Conversations for Education

Authors:

Donya Rooein, Paolo Paolini and Barbara Pernici

Abstract: This paper proposes using chatbots as “tutors” in a learning environment; tutors who are not domain experts but helpers in guiding students through bodies of learning material. The most original contributions are the proposal that conversation should be content-independent (although chatbots speak about content); The production process should allow non-technical actors to customize chatbots and keep the costs of development and deployment low. We specifically discuss conversation customization, which is relevant, especially for learning applications, where users might have specific needs or problems. We achieve the features introduced above via extensive “configuration” (regarding direct programming), making the underlying technology novel and original. Experiments with teachers and students have shown that chatbots in education can be effective and that customization of conversations is relevant and valued by users.
Download

Paper Nr: 135
Title:

A Recommendation Module based on Reinforcement Learning to an Intelligent Tutoring System for Software Maintenance

Authors:

Rodrigo Elias Francisco and Flávio de Oliveira Silva

Abstract: The demand for qualified professionals to work with Software Maintenance (SM) brings challenges to computer education. These challenges are related to SM’s inherent complexity and the teacher’s significant work in providing adequate support in practical SM activities. In this context, Artificial Intelligence (AI) based techniques, such as recommendations, can play a central role in developing Intelligent Tutoring Systems (ITS) to focus the teaching-learning process. The literature points out a lack of ITS to SM and that most of them do not use AI-based techniques to recommend content to the students. In this work, we present an Expert Knowledge Module (EKM) for an ITS specially designed for SM. To model the EKM content, we did a deep analysis of the ACM curricula regarding SM topics and the syllabus related to SM from all Brazilian public universities. The content recommendation engine uses the Q-Learning algorithm, a well-known Reinforcement Learning (RL) AI-based technique. Using simulation-based experiments, we could verify the efficiency of the Q-Learning-based recommendation mechanism to propose contents using the ITS’s EKM properly. This work highlights how AI-based techniques can enhance and improve SM’s teaching-learning process using ITS and advance this research area.
Download

Paper Nr: 138
Title:

Intelligent Tutoring System for Computer Science Education and the Use of Artificial Intelligence: A Literature Review

Authors:

Rodrigo Elias Francisco and Flávio de Oliveira Silva

Abstract: Education in computer science brings specific challenges to the teaching-learning process. Students spend a lot of time dealing with the complexity of problems and learning to use existing technologies. Intelligent Tutoring System (ITS) is a technology that can contribute to this scenario, automating and adapting teaching to the student’s profile. This work presents a literature review on ITS’s for Computer Science Education, focusing on Artificial Intelligence (AI) in this scenario. We analyze the development and use of ITS’s in Computer Science Education and assess AI techniques, algorithms, and datasets. The results of this review point to challenges in research on aspects such as the unavailability and difficulty of reproducing datasets, the lack of in-depth explanations about the relationship between AI techniques and these ITS data, the need to deepen these techniques of AI, and the need for more research about software engineering to ITS. This work contributes to providing opportunities to this research area that can help the digital transformation of Computer Science Education.
Download

Paper Nr: 142
Title:

Possible Application Scenarios for a German National Education Platform

Authors:

Daniel Staegemann, René Degenkolbe, Stefan Weidner, Robert Häusler, Vinzent Lange and Klaus Turowski

Abstract: In today’s knowledge-driven world, the competences of its citizens have turned into one of the most valuable resources a country can build its success upon. Hence, it is of extremely high importance to not only provide high-quality education, but to also make life-long learning as convenient as possible. This is the main idea behind the national education platform the German government intends to establish. With that goal in mind, momentarily, a prototypical implementation is being developed in a project called BIRD. The publication at hand outlines four possible scenarios: classical learning environment, simulation games, extracurricular certifications, digitization of administrative processes. The contribution is therefore twofold, to disseminate the project as well as to provide a basis for discussion that might lead to additional or related scenarios.
Download

Paper Nr: 143
Title:

Structural Challenges in the Educational System Meet a Federated IT-Infrastructure for Education: Insights into a Real Lab

Authors:

Alexander Knoth, Franziska Blum, Erwin Soldo and Ulrike Lucke

Abstract: This position paper describes the need and the proposed solution for a federated educational infrastructure currently developed in a national flagship project in Germany. Existing technologies and standards, tools, and services are brought together in a heterogeneous yet consistent infrastructure by a distributed middleware. These technical developments are accompanied by consulting and organizational activities. The article describes the expected outcomes of this pilot project that will be available as an interoperable prototype throughout the year 2022. This also includes the international perspective of such a solution.
Download

Paper Nr: 147
Title:

The Future of Higher Education Is Social and Personalized! Experience Report and Perspectives

Authors:

Sven Strickroth and François Bry

Abstract: This position paper is devoted to learning and teaching technologies aimed at alleviating problems and addressing challenges faced by learners or teachers in mass classes. It reports on practical experiments run over the last terms at the Institute for Informatics of Ludwig-Maximilian University of Munich, Germany. Furthermore, perspectives for higher education opened by technology are discussed: Digital social learning and/or experimentation spaces and technology-based personalization. It is further argued that such approaches provide specific advantages that are not only desirable for teaching mass classes.
Download

Paper Nr: 149
Title:

Gamification of an Exercise Tool of a Virtual Learning Environment

Authors:

Claudia Pimentel, Rafaela Pscheidt, Brayan Eduardo Rosa, Avanilde Kemczinski and Isabela Gasparini

Abstract: Gamification uses game design elements in non-playful contexts, such as educational environments, to achieve motivation, interaction, and performance benefits. This paper presents the gamification of an exercise tool of a Virtual Learning Environment to induce students to increase their participation through creating new questions in the tool and answering the questions of their peers. The development of the gamification process and the experiment with students are detailed, and as result, we can find gamification can be an ally as a motivation tool for students.
Download

Paper Nr: 152
Title:

Factors Influencing Co-creation of Open Education Resources using Learning Object Repositories

Authors:

Mulenga Chanda, Elizabeth Chirwa, Mirriam Kamanga, Mwenya Kayula and Lighton Phiri

Abstract: Open Education Resources (OERs) have been identified as instrumental in facilitating access to quality teaching and learning materials. However, despite the rapid development of technologies capable of making OERs, the uptake and co-creation of OERs by educators is still low. This paper outlines a study conducted in order to investigate the use of Learning Object Repositories (LORs) in co-creation of OERs by educators. Using the Uses and Gratification theory, a survey was conducted with 36 educators in order to identify learning objects commonly used by educators and, additionally, to determine the factors that can positively influence educators to be co-creators of OERs. The results indicate that sharing knowledge, contributing to other people and intellectual challenge are factors that are highly correleted in motivating educators to be co-creators of OERs. The results also indicate that the learning objects commonly used by the educators are the course modules and presentation slides. In conclusion, in order for educators to be co-creators of OERs they need to be intrinsically motivated and be able to collaborate with others for non-selfish reasons. The results of of this study have the potential of influencing how LORs should be design in order to facilitate effective co-creation of OERs.
Download

Paper Nr: 153
Title:

A Systematic Literature Review on Technological Solutions to Fight Bullying and Cyberbullying in Academic Environments

Authors:

Priscila Cedillo, Alexandra Bermeo, Alexa Betancourth, Francisco Espinosa, Lourdes Illescas and Janio Jadán

Abstract: Nowadays, the world is more connected than ever; the use of internet, social networks and platforms allows for people of all ages to have constant communication. During the past year, due to the COVID-19 pandemic, children and teenagers have had to spend most of their time using a technological device, for educational and recreational purposes. This constant connection has carried on several issues, one of them being cyberbullied. This is when a person intentionally and repeatedly harms another one, on a virtual environment. Even with its downside, technology has many advantages; it has allowed for children and teenagers to engage in educational communities and applications. Then, studies on bullying and the ways to fight it exist from many years prior, however, there are little literature about the technological solutions to help in the fight against cyberbullying and bullying. Therefore, the objective of this research is to perform a Systematic Literature Review (SLR) about technological solutions for education and to fight bullying and cyberbullying in children and teenagers. To perform a trustworthy, rigorous and repeatable SLR, the methodology proposed by Kitchenham was used. The presented SLR, uses studies from 2009 to 2021. To start, a group of primary studies was selected, which met the characteristics to answer the research question “What technological tools, methods and models are used to educate about bullying and cyberbullying?” The primary studies were obtained from the most used digital libraries, prominent journals, and most representative conferences in the area. In conclusion, this study provides a global vision of the state of the art in this area, which represents a helpful tool for researchers to detect weaknesses and gaps and open new horizons regarding the use and design of technology to fight bullying and cyberbullying.
Download

Paper Nr: 155
Title:

Improving Accessibility in Virtual Learning Environments and Educational Resources: A Practical Case and Future Challenges

Authors:

Yandson Costa, Rayanne Silveira, Ana F. Oliveira, Luis Rivero, Alana Oliveira, Mário Teixeira and Davi Viana

Abstract: A system is considered accessible if it allows different users to access its features, even if these users have physical, visual, auditory or any other type of disabilities. Accessibility has become crucial in Virtual Learning Environment (VLE) since these deliver the educational contents as online activities and electronic courses. Despite such importance, one of the most consistent problems with modern learning management systems is their failure to comply with standards for accessibility. Also, those that manage to meet accessibility criteria still receive negative reviews from disabled users. As a result, accessibility issues act as a barrier in the growth of VLEs. In this paper, we intend to reduce this barrier by providing a practical example of how educational institutions can improve their VLEs and their educational resources. We proposed and applied a process for identifying accessibility requirements and implemented these requirements, testing the redesigned VLEs and educational resources with end users. Obtained results are discussed to provide insights on how software engineering teams can improve the accessibility of VLEs and educational resources.
Download

Paper Nr: 166
Title:

Online Master in International Logistics: Methodology, Design and Implementation

Authors:

Jerzy Korczak and Marcin Pawęska

Abstract: The article presents conceptual ideas as well as methodological approach to development and implementation of a fully online international Master program. Master in International Logistics is being created by nine universities from eight different countries leveraging the strength of each partner, while assuring uniformity of the expected outcomes. The authors in this paper focus on global features and objectives of the program which not only offers flexibility of deployment by the project partners but guarantees rigorous requirements of didactic process as well. The paper also describes the principles of designing the whole course, individual classes, along with the methods of knowledge assessment. The program has been fully accredited by Chartered Institute of Logistics and Transport. The Master courses are already deployed by the International University of Logistics and Transport in Wrocław, Poland; they will be initially offered in 2022/2023 academic year in a mode of online and blended learning.
Download

Paper Nr: 169
Title:

A Machine Learning-based Course Enrollment Recommender System

Authors:

Xiwei Wang, Longyin Cui, Muhammad Bangash, Mohammad Bilal, Luis Rosales and Wali Chaudhry

Abstract: As an integral component of human society, higher education has been undergoing a transformation in multiple aspects, such as administrative reorganization, pedagogical reform, and technological innovation. To line up with the latest trends, many institutions constantly update their curriculum, which poses challenges to students and their advisors. This paper proposes a machine learning-based course enrollment recommender system that aims to make personalized suggestions to students who expect to take classes in the upcoming semester. Using matrix factorization as the core algorithm, the model exploits several available types of information, including student course enrollment history and other contextual features, such as prerequisite restrictions, course meeting times, instructional methods, and course instructors. The system not only helps students but also facilitates their advisors’ work. Our experimental results show that the recommended courses were highly relevant while providing plenty of options to students.
Download

Paper Nr: 9
Title:

A Self-adaptive Mechanism for Serious Quiz Games

Authors:

Michael Striewe

Abstract: Serious quiz games can provide an entertaining way to assess knowledge and promote learning. Motivation of the players can be increased by presenting quiz questions in the order of increasing difficulty or by presenting many different quiz questions during subsequent quiz sessions. However, maintaining a question set to adjust difficulty ratings for the target audience and to avoid early repetitions of questions can be a challenging task that requires constant effort. The paper presents a self-adaptive mechanism that is able to solve both tasks without collecting any explicit information about the anonymous target audience. The evaluation demonstrates that a quiz with about 600 questions on 15 difficulty levels has been maintained successfully over several years and more than 100’000 quiz sessions with minimal manual intervention.
Download

Paper Nr: 42
Title:

Personalised Learning Environments based on Knowledge Graphs and the Zone of Proximal Development

Authors:

Yoshi Malaise and Beat Signer

Abstract: The learning of new knowledge and skills often requires previous knowledge, which can lead to some frustration if a teacher does not know a learner’s exact knowledge and skills and therefore confronts them with exercises that are too difficult to solve. We present a solution to address this issue when teaching techniques and skills in the domain of table tennis, based on the concrete needs of trainers that we have investigated in a survey. We present a conceptual model for the representation of knowledge graphs as well as the level at which individual players already master parts of this knowledge graph. Our fine-grained model enables the automatic suggestion of optimal exercises in a player’s so-called zone of proximal development, and our domain-specific application allows table tennis trainers to schedule their training sessions and exercises based on this information. In an initial evaluation of the presented solution for personalised learning environments, we received positive and promising feedback from trainers. We are currently investigating how our approach and conceptual model can be generalised to some more traditional educational settings and how the personalised learning environment might be further improved based on the expressive concepts of the presented model.
Download

Paper Nr: 55
Title:

Beyond Viewing Counts, Likes & Co: An Analysis of Instructional Videos on Youtube

Authors:

Miriam Mulders and Johannes Wendt

Abstract: The aim of this study is to open up criteria of instructional videos through a search of the scientific literature. Shoufan (2019) tested the Video Cognitive Value (VCV) of instructional videos as a function of cognitive and other characteristics. Here, the VCV is formed from the likes and viewing counts. Based on Shoufan’s results, the present study aims to answer the following two research questions: 1. Can comparable correlations be reproduced for instructional videos from another subject area? 2. Can the correlations be further explained by criteria regarding the instructional design? For this purpose, 100 videos using the YouTube API were collected. Multiple linear regression analyses were performed. However, only 9% could be explained by cognitive characteristics and 5% by instructional design criteria of the total variance in VCV. The recent study could not reproduce Shoufan’s results and supplementary criteria could not explain further data variance. With regard to the literature, criteria such as likes and viewing counts cannot describe the instructional quality ratings of instructional videos. More promising approaches to evaluate quality perception of instructional videos (e.g., comments) are mentioned.
Download

Paper Nr: 56
Title:

Expressing Adaptations to Take into Account in Generator-based Exercisers: An Exploratory Study about Multiplication Facts

Authors:

Pierre Laforcade, Emeric Mottier, Sébastien Jolivet and Bérénice Lemoine

Abstract: This paper intends to explore how the generation logic and the elements involved are expressed from the teachers’ viewpoint, in the context of learning games. We present an interview-based exploratory study: preparation, realization, analysis, and findings. From the results we also propose a dedicated metamodel to capture these expressed elements and logic. We evaluate this metamodel by developing a high-level generator component about the practice of times tables.
Download

Paper Nr: 89
Title:

Analysis of Social Networks of Students' Learning with a Focus on Their Performance

Authors:

Waldir Siqueira Moura, Mônica Ferreira da Silva, Jonice Oliveira Sampaio Guimarães de de Souza and Tainá Souza

Abstract: The low performance of students in high school is a problem that has had considerable growth due to the constant transformations generated by the current pandemic. The formation of groups to develop collaborative work in the classroom is a rich tool that can effectively develop Collective Knowledge, provided there is planning. Furthermore, through the analysis carried out, we realised that the way the learning occurs affects the students' performance and can be reorganised by the teachers to enable a better group (and even individual) development within the group.
Download

Paper Nr: 137
Title:

Applying Simulation in Teaching Selected Courses in Business Informatics with the FlexSim Platform

Authors:

Aleksander Binsztok, Beata Butryn, Katarzyna Holowinska, Mieczysław L. Owoc and Małgorzata Sobińska

Abstract: Using simulation in various sectors as a tool to predict and design processes is very common. The popularity of such solutions is growing, and even in the education field, this kind of tool can be an interesting form of enriching classes. Today, education requires a constant search of methods and instruments that stimulate students' engagement. Active teaching methods ensure students' activities through their creativeness and reactiveness during educational processes. The research aims to investigate the role and usability of simulation, which in turn can be a crucial component of the active teaching method. Education in the Business Informatics area relates to computer technologies and management skills. Our proposals presented in the paper cover both mentioned areas, the simulation of defined business models and the development of applications useful in certain phases of managerial procedures. The application of simulation techniques in education is considered a vital teaching instrument, which allows preparing adequate education, directs students to the proper attitude, motivates them to learn, inspires them and enables their development. This article attempts to fill the research gap by describing the usability of such tools.
Download

Paper Nr: 139
Title:

A Platform to Interest Young People in STEM using Robotics and AI in a Playful Way

Authors:

Fabian Gibert and Georg J. Schneider

Abstract: This paper describes an educational and affordable robotics design of hardware and software for a technical platform for playful learning in STEM fields, providing a low entrance barrier and a smooth transition from playing to developing, depending on the user’s age. The platform is installed in a toy car and operates the vehicle motors. A smartphone app serves as remote control. In addition to the simple basic electrotechnical structure for driving, which is comprehensible to users, the design can be extended with actuators or sensors via standardized modules and interfaces. On the software side, experimentation possibilities arise to process captured sensor values or to experiment with an AI-supported image recognition, allowing users to get an insight into up-to-date discussions like AI-based image recognition int the context of autonomous driving. In addition, the system offers smartphone app functions, such as an image display on the smartphone or automated vehicle behavior. Manufacturer-independent and without proprietary specifications, this platform opens up a flexible, expandable technical basis for playfully exploring the interaction of components in one's own interest without prior knowledge or programming experience.
Download

Paper Nr: 140
Title:

An Interface Adaptation Model for LMSs According to Learning Styles

Authors:

Alana Oliveira, Emanuelle Lemos, Anderson Galvão, Carlos S. Soares Neto and Mario M. Teixeira

Abstract: An LMS adapted to students’ learning styles has the potential to promote more meaningful learning experiences. This work develops an interface adaptation model for LMSs based on Honey and Mumford’s learning styles. Relevant characteristics of these styles are mapped and serve as basis for an Adaptation Model used for LMS interface prototyping regarding activist, reflector, theorist and pragmatic students. Information organization, navigation and presentation are among the aspects considered. A teacher module is also developed to help instructors create content adapted to different individuals.
Download

Paper Nr: 145
Title:

Building, Controlling and Simulating We-Do Robots

Authors:

Ahmed Wael, Ghada Ahmed and Nada Sharaf

Abstract: Robotics is now integrated in the STEM curricula for teaching mathematical concepts, mechanics, physics and programming skills. However, the presence of the robots and hardware components is always a challenge. It could be costly and in case of online learning, it is hard to use hardware elements. This is why there is an increasing need of simulators that display the robot in different environments. Such simulators could provide feasible solutions. The work presented in the paper introduces “Let’s LEGO”, which is a simulator for building and constructing robots, controlling them programmatically and seeing them in action based on the Lego WeDo 2.0 electronic kit. The work presented in this paper builds on the current need of introducing computational thinking to children from an early age. The goal of this project is to investigate methods for developing a Simulator for creating and constructing robots, controlling them programmatically, and viewing them in operation. Let’s LEGO was evaluated by instructors responsible for teaching programming and robotics to children in grades 2-4 (7+ years old). They reported that they thoroughly enjoyed the experience and would like to include it in their teaching techniques. The aim is to strengthen how technology-mediated learning may be used to provide a better and a more enjoyable learning experience to students with different profiles.
Download

Paper Nr: 146
Title:

IMASHEDU: Intelligent MAshups for EDUcation - Towards a Data Mining Approach

Authors:

Priscila Cedillo, Pablo Martínez León and Marcos Orellana

Abstract: Nowadays, technological tools greatly support the work of teaching-learning tasks. In this sense, there are various sources of information from which teachers and students rely on to complement their academic activities. Content is sought on the web, significantly updated and easy to understand, generally in the form of videos. As people progress in their learning, they face terms, concepts, and topics that they are not familiar with them. However, those topics are included in the video. In this context, a complex process is generated of alternating sections of the video with other sources of information that explain the related topics and contribute to the understanding of the topic discussed. In this regard, and considering the possibility of systematically consuming information from various sources, it is necessary to build a method and an application that orchestrates the contents of these sources in a convenient, fast and automatic way, according to the person's learning. This proposal contemplates the development of a Mashup. This mashup integrates different data sources in a single graphical interface. Also, it is considered the construction of a core software solution based on text mining techniques. This solution allows extracting the textual content from videos and identifying the terms that could support the knowledge of the topic. It would significantly contribute to the fact that related topics are presented unified in the same interface. At the same time, the learning experience is greatly improved, avoiding losing the common thread of the observed video. Therefore, this article presents a process of orchestrating various data sources in a Web Mashup application. It includes videos available on YouTube channels, with other sources (e.g., Wikipedia, Pinterest) that help understand the topic better, generating hypertext references based on the generation of terms through text mining techniques. A Mathematics Learning mashup has been built to show the proposal’s feasibility.
Download

Area 3 - Learning/Teaching Methodologies and Assessment

Full Papers
Paper Nr: 16
Title:

A Syllabus to Support Teaching and Learning of Exploratory Test Design and Execution

Authors:

Igor Ernesto Ferreira Costa and Sandro Ronaldo Bezerra Oliveira

Abstract: Exploratory Testing has become increasingly widespread in the industry, one of the reasons being the need to use agile approaches in the quality assurance process. In this context, it was observed that many professionals in the area are hardly able to apply this approach with systematic procedures because they understand it as an informal strategy. From a literature review carried out, a great potential for research was identified, focusing on the education of Exploratory Test Design and Execution. Therefore, this study presents the process of building a systematic teaching-learning approach to support the Exploratory Tests Design and Execution, training students to obtain skills, theoretical and practical knowledge relevant to the industry. For this, a mapping of assets involving the curricula was carried out: training reference for undergraduate courses in computing from SBC (Brazilian Computer Society), Computer Science Curricula from ACM/IEEE and the practical guide from TMMi (Test Maturity Model integration), analyzing the process area of Test Design and Execution. In addition, interviews were conducted with professionals to identify tools, work products and techniques used to make a teaching-learning approach adherent to industry practices and guidelines for theoretical knowledge in the academic context. Therefore, this work provides a set of skills favorable to teaching Exploratory Test Design and Execution, encouraging academic program managers and professors to use the knowledge generated to help them build disciplines containing a systematic application of exploratory testing.
Download

Paper Nr: 17
Title:

Fairness of In-session Dropout Prediction

Authors:

Nathalie Rzepka, Katharina Simbeck, Hans-Georg Müller and Niels Pinkwart

Abstract: The increasing use of machine learning models in education is accompanied by some concerns about their fairness. While most research on the fairness of machine learning models in education focuses on discrimination by gender or race, other variables such as parental educational background or home literacy environment are known to impact children's literacy skills too. This paper, therefore, evaluates three different implementations of in-session dropout prediction models used in a learning platform to accompany German school classes with respect to their fairness based on four different fairness measures. We evaluate the models for discrimination of gender, migration background, parental education, and home literacy environment. While predictive parity and equal opportunity are rarely above the defined threshold, predictive equality and slicing analysis indicate that model quality is slightly better for boys, users with higher parental education, users with less than ten books, and users with a migrant background. Furthermore, our analysis of the temporal prediction shows that with increasing accuracy of the model, the fairness decreases. In conclusion, we see that the fairness of a model depends on 1) the fairness measure, 2) the evaluated demographic group and 3) the data with which the model is trained.
Download

Paper Nr: 33
Title:

Work-From-Anywhere Skills: Aligning Supply and Demand Starting from High Schools

Authors:

Ilenia Fronza, Luis Corral, Gennaro Iaccarino, Lucia Bartoli and Claus Pahl

Abstract: The world of work-from-home (WFH) and work-from-anywhere (abbreviated WFX or WFA) grew more than ever during the COVID-19 pandemic. Many companies are now planning on permanently allowing WFX, with subsequent demand for specific skills. It is crucial to foster these skills in high schools, as students may enter the job market without attending University. Up-to-date analysis of the current situation is missing to align supply and demand by enabling educators to set goals and strategies to train students so that they will be able to mesh into a WFX setting. To address this issue, we collected complementary data using a case study (23 students), a questionnaire (616 students), and interviews with professionals and practitioners of the software development sector. Results suggest that information management, communication skills, autonomy, and resourcefulness are key competencies that enable professionals to succeed in a WFX environment. However, students feel less prepared in terms of communication skills; moreover, they lack time management and autonomy skills. Based on our results, we highlight recommendations for educational practice that educators can use in curriculum building to fill the gaps that emerged in this study to assure the effective development of the skillset demanded by current and future WFX conditions.
Download

Paper Nr: 41
Title:

Method for Joining Information and Adapting Content from Gamified Systems and Serious Games in Organizations

Authors:

Mathieu Guinebert, Joël Fabiani, Melaine Cherdieu, Pierre Holat and Charlie Grosman

Abstract: In some work fields, the number of various knowledge and skills one must master can be tremendous. Therefore, we decided to make work and training more rewarding and motivating. The skills and knowledge mustered by the employees in both those situations are the same, but the systems responsible for the tracking and the adaptation of the content are not. Therefore, our contribution is twofold. First, a system that centralizes the learner’s game, learning and professional profiles and provides the other systems connected to it with the necessary information to adapt their content thanks to various modules. Secondly, a generic model that should be respected by any system connecting to our first element. We argue that it is necessary to use both our method and model to be able to fully exploit the information provided by our system. We tested our model and method on three different implementations but could not measure the impact of said implementations on our learners.
Download

Paper Nr: 60
Title:

Exploring Geolocation Data: An Inquiry-based Methodology Used in Lower Secondary Education

Authors:

Gabriela Lovászová and Viera Michaličková

Abstract: The presented research study is focused on building conceptual knowledge of pupils in the field of data representation and tools for their processing using the inquiry-based methodology (the 5E model was applied). We have chosen geolocation data as a less traditional type of data, which also provides an opportunity for a non-traditional form of teaching computer science outdoors using mobile technology. Pupils’ task is to determine suitable tools for processing geolocation data. They analyze a GPX file’s contents and formulate questions that can be answered from the available data. During the outdoor phase of the learning scenario, pupils produce an original GPS drawing and share it in a common digital map. Data collected from teachers who implemented the proposed methodology in several primary schools confirmed that our methodology based on the IBL principles was successful in achieving educational goals at higher levels of Bloom’s taxonomy. The teachers were also confirming that combining the inquiry approach with using mobile technology stimulates pupils' interest in the subject of teaching significantly.
Download

Paper Nr: 112
Title:

Analysing Usability and UX in Peer Review Tools

Authors:

Romualdo Azevedo, Gretchen Macedo, Genildo Gomes, Atacilio Cunha, Joethe Carvalho, Fabian Lopes, Tayana Conte, Alberto Castro and Bruno Gadelha

Abstract: Due to the pandemic scenario, teachers and students needed to master several technologies such as collaborative tools to support remote learning. Trying and adopting these tools properly in a context can positively contribute to learning, potentially maximizing student engagement. In this sense, this paper presents perspectives from professors and students about aspects of User Experience (UX), on two collaborative tools that support Peer Review: (i) The Moodle Assessment Laboratory (MoodlePRLab) and (ii) Model2Review. Thus, it was possible to propose improvements to promote a better user experience from professors and students when using these sorts of tools and discuss how UX can affect collaboration during remote teaching.
Download

Paper Nr: 129
Title:

Digital Game-based Learning in Primary School: What Issues Does/Does Not Recent Research Focus on?

Authors:

Maria Koutantou and Maria Rangoussi

Abstract: Recent research on Digital Game-Based Learning (DGBL) applied specifically in Primary Education is reviewed in a systematic way. 87 journal papers published in the last 4 years (2017 - 2020) are selected and analyzed in order to draw conclusions regarding the effectiveness of DGBL (i) in producing cognitive domain learning outcomes, (ii) in developing social skills, (iii) in producing affective / metacognitive outcomes, and (iv) in offering an enjoyable experience to Primary Education students. Apart from the classic questions of literature reviews, aimed at describing the methodology, aims and outcomes of the reviewed works, the current review is also interested (a) in the ways of integrating the digital game in the educational practice, in relation to the adoption of a specific learning theory and educational method and (b) in the measurement tools employed to evaluate the effectiveness of DGBL interventions, in relation to the aims set and the results obtained. The goal of this review is to reveal those aspects of DGBL that recent research focuses on and at the same time those aspects that are not adequately researched and require more attention and effort. The latter result is especially useful in the planning of future studies. The results record a steadily increasing research interest in DGBL and a strongly positive effect of DGBL in all the examined axes. On the other hand, they reveal an almost general lack of a solid foundation of DGBL interventions in learning theories and consequent educational methods – an alerting situation that deserves careful examination.
Download

Paper Nr: 136
Title:

Using Kintsch's Text Comprehension Model to Identify CS Students’ Conceptions and Misconceptions

Authors:

Christina Kyriakou, Agoritsa Gogoulou and Maria Grigoriadou

Abstract: Recent research attempts to figure out the hard points of Computer Science (CS) discipline curricula that seem to trouble students. The presented work focuses on assessing first-year CS students’ knowledge on issues related to fundamental computer architecture concerning main memory organization, operation, and role on program execution. Formulating questions based on Kintsch's text comprehension model theory is a promising diagnostic tool to identify students’ conceptions and misconceptions. The paper discusses the Kintsch model as the basis for formulating meaningful questions, analyzes students’ answers, and attempts to categorize and explain the revealed misconceptions. The emerging misconceptions may be helpful for effective learning design and appropriate educational material.
Download

Paper Nr: 161
Title:

A Research Supervision Framework for Quality and Scalability

Authors:

Paul Stynes and Pramod Pathak

Abstract: Academic staff provide research supervision based on the one on one approach or the apprenticeship model. Current student recruitment policies are enrolling larger numbers of students on taught master’s programmes. The current research supervision approach is not sustainable with growing numbers of students and conducting research supervision that is scalable is a challenge. Increasing the number of supervisors leads to difficulties with the consistency in the quality of the supervision. This research proposes a research supervision framework that scales with increasing numbers of re-search students and ensures consistency in the quality of research supervision among faculty. The framework combines teaching practices, timetabled group supervision, co supervision, coaching and scaffolding. The research supervision framework was applied in timetabled group research supervision sessions in May to August2020 with 15 students, September 2020 to January 2021 with 10students and May to August 2021 with 12 students. Results demonstrate an increase in the quality of research as demonstrated by the publication of 4 book chapters, 3 peer reviewed international conference papers and 3 invention disclosures. These publications occur during a period of growth in student numbers by approximately 1000% from 2012 to 2020. This research is of interest to both Deans and faculty. Deans will gain insight in how to ensure quality of supervision with growing student numbers on taught master’s programmes. Faculty will gain insight in how to effectively supervise students in order to increase their academic publications using alternative supervision approaches.
Download

Paper Nr: 176
Title:

A Systematic Literature Review of Game Design Tools

Authors:

Sebastian Gajewski, Nour El Mawas and Jean Heutte

Abstract: Existing research works show the role of game-based learning to increase lifelong learners’ learning and motivation. Furthermore, many game design tools are increasingly available and easy-to-use even by people without any technical knowledge, making the choice of the tool difficult. The aim of this paper is to identify and compare game design tools in order to help people to choose the most suitable game design tool for their needs. After having identified 9 criteria that characterize a game design tool, we have conducted a systematic literature review following the PRISMA methodology. This methodology allows us to identify references via 2 methods: databases and the interview with a pedagogical engineer. From 302 identified studies via 5 databases (IEEE Xplore, ScienceDirect, Scopus, Springer, and Web of Science), 18 have been used for the discussion. From the 8 game design tools advised by the pedagogical engineer, 3 have been used for the discussion. These 2 methods allow us to identify 12 game design tools. This research work is dedicated to Technology Enhanced Learning community and pedagogical community, and more specifically to game designers, pedagogical engineers, teachers, and researchers who encounter difficulties in choosing the game design tool the more suitable for their needs.
Download

Short Papers
Paper Nr: 12
Title:

Formative Feedback in Mathematics Teacher Education: An Activity and Affordance Theory Perspective

Authors:

Said Hadjerrouit and Celestine Ifeanyi Nnagboa

Abstract: The increasingly high number of students’ enrolment has necessitated the recent attention on the use of computer-based assessment systems for feedback delivery to students for mathematical learning, such as Numbas. However, little is known about the affordances of Numbas in the research literature. The purpose of this study is to investigate the affordances of Numbas, their perception and actualization by students and teachers, and their effects on mathematical learning from an activity and affordance theory perspective. The study follows a qualitative research design using semi-structured interviews of six students and two teachers. The results reveal the perception and actualization of several affordances at the technological, mathematical, and pedagogical level. Conclusions and future work are drawn from the results to promote Numbas formative feedback for teaching and learning mathematics.
Download

Paper Nr: 34
Title:

Programming in Year 4: An Analysis of the Design Research Process

Authors:

Ivan Kalas, Andrej Blaho and Milan Moravcik

Abstract: In this paper, we analyse the educational design research process in which we looked to develop an evidence-based intervention and professional development (PD) content for programming in primary Year 4b. We explain how the latest period of the Computing with Emil project extends our previous intervention for Year 3 by exploiting the same constructivist pedagogy and design principles. We recall these principles and the research strategy which we consider appropriate for the current state of knowledge in transforming computing education in lower primary years. As the concluding phase of the design research, we reflect on the design process in greater depth and formulate the characteristics of the intervention by focusing on its programming language and concepts. To frame this effort, we identify five interwoven contexts that shaped the development cycles of our inquiry, namely: (1) programming environment, (2) programming language, (3) content development, (4) workbook for pupils, and (5) teachers’ PD design. Looking back, we analyse the iterative design process within these contexts through the lens of the five instruments of reflection we were continuously exploiting to inform our design, namely: (a) observing pupils work, (b) interviewing teachers, (c) analysing pupils’ workbooks and onscreen content, (d) evaluating Emil Y4 pilot PD sessions, and (e) analysing Emil Y3 data. Among other findings, which have resulted from the analysis of the design process, we highlight in particular a thoughtfully designed pulsating range of the command set. Although we had gradually created the content ourselves, it was not earlier than the concluding retrospective analysis that exposed it so clearly.
Download

Paper Nr: 36
Title:

Using Cybersecurity Exercises as Essential Learning Tools in Universities

Authors:

Răzvan Deaconescu, Andra Bălțoiu, Tiberiu Georgescu and Alin Puncioiu

Abstract: Capture-the-flag (CTF) contests play a well-established role in the cybersecurity culture, being at once skill-testing grounds and community-building platforms. While these contests provide education benefits, their adaptation to academic objectives is not straightforward, since the competitive nature of CTFs makes them more appropriate for knowledge evaluation than acquisition. In this paper we present the preparing, deploying and evaluating a cybersecurity exercise for university students. Our work aims to stimulate students for a career in cybersecurity, evaluate their experience and collect feedback. We detail our experience in organizing the exercise; we also present student feedback and draw conclusions and lessons learned on using cybersecurity exercises as educational tools.
Download

Paper Nr: 47
Title:

Transferring Learning into the Workplace: Evaluating a Student-centered Learning Approach through Computer Science Students’ Lens

Authors:

Mădălina Eraşcu and Velibor Mladenovici

Abstract: Over time, instructional training activities for academics that promote student-centered learning (SCL) increased. However, few things are known about the extent to which academics’ learning is transferred into the daily teaching practice. In this study, we investigated the impact of transferring learning into the workplace of an Informatics teacher (first author of this paper) seeking to promote SCL within a new discipline in her portfolio (i.e., Software Engineering). For this purpose, a quasi-experimental design with pre- and post-test was employed. Self-reported data were collected as follows: from the experimental group, there were 52 students (28.8% female) at the pre-test, and 29 students (37.9% female) at the pre-test, while from the control group, data were collected from 26 students (34.6% female) at the pre-test and 19 students (47.3% female) at the post-test. Independent t-test analysis showed that the SCL initiative had only a positive impact on student learning approaches and teaching quality as perceived by students. Concerning students’ learning approaches, the SCL initiative had no effect. Several interpretations and perspectives of the current study are discussed.
Download

Paper Nr: 66
Title:

The Adoption of a Framework to Support the Evaluation of Gamification Strategies in Software Engineering Education

Authors:

Rodrigo Henrique Barbosa Monteiro, Maurício Ronny De Almeida Souza, Sandro Ronaldo Bezerra Oliveira and Elziane Monteiro Soares

Abstract: Context: gamification has been largely used to increase the engagement and motivation of students and professionals in their organizations, with a variety of models/frameworks for developing gamified approaches. Problem: the empirical data published so far are not sufficient to elucidate the phenomena resulting from the use of gamification, as there is no standardization in the specification of evaluation strategies, methods of analysis and reporting of results. Objective: therefore, the objective of this study is to present and discuss the use of a framework for the evaluation of gamification in the context of software engineering education and training. Method: for this, we executed a case study, in which the framework was used to support the design of an evaluation study for a gamification case in a software process improvement research group in a public university. Results: We report the main findings from observations and reports from the applicator of the case study, and 11 recommendations for the design of evaluation studies supported by the framework. Our main findings are: providing examples of usage of the framework improves its understanding, the framework helped the applicator in understanding that qualitative and quantitative data could be use in compliment to each other, and it helped streamlining the design of the evaluation study, considering the consistency between data to be collected, evaluation questions, and the goals of the evaluation study.
Download

Paper Nr: 69
Title:

Better the Phish You Know: Evaluating Personalization in Anti-Phishing Learning Games

Authors:

Rene Roepke, Vincent Drury, Ulrike Meyer and Ulrik Schroeder

Abstract: Anti-phishing learning games present a motivating, interactive approach to user education and thus, various games have been developed and studied in the past. A common trend among these games is a limited use of game mechanics and no consideration of learners using methods of personalization. In this paper, we compare an anti-phishing learning game with its personalized version in the scope of a longitudinal user study with 89 participants. For personalization, the player’s familiarity with different services is used to provide personalized content in the form of URLs in the game. To further understand the effects of personalization, we analyze game log data and evaluate how players interact with personalized learning game content. While the comparison of both game versions did not yield significant differences in the participants’ performance in URL tests, the in-game analysis confirmed that players interact differently when confronted with URLs based on services they are not familiar with compared to those they use or know. These differences when handling unknown URLs in the in-game analysis might indicate, that personalization could be leveraged to improve awareness and the knowledge transfer to the real world.
Download

Paper Nr: 86
Title:

Webfolio: Secure Digital Portfolio for Early Childhood Education

Authors:

Willian de Oliveira Silva, Arlete Teresinha Beuren, Cristina Mesquita and Rui Pedro Lopes

Abstract: In early childhood education, there are several techniques to understand children’s development in kindergarten. One of these techniques is based on Portfolios that, in early childhood education, allows the understanding of the progress of the child, allowing a shared reflection with the child, teachers, and the child’s parents towards the understanding on the child’s learning process. The work described in this paper has as its main objective the development of a web application, which allows support for the construction of a platform for the storage and sharing of digital portfolios for early childhood education. In addition, it is intended that an access control of users be made so that it is possible to manage access to certain portfolios or sub-parts of them. The system has features such as: creating portfolios, creating notes, and managing user permissions. After the application was implemented, usability tests were carried out, with the participation of teachers. Through the techniques and methodologies used, it was possible to create a web tool to aid in the creation of portfolios for early childhood education, allowing the registering of audio, video, or image files. In addition, the system allows the sharing of portfolios with different users of the system who, in turn, can perform actions in the portfolio according to their role in the system.
Download

Paper Nr: 102
Title:

Bridging the Theory and Practice Gap in Marketing Education

Authors:

Rui Patrício

Abstract: The paper proposes a new marketing course curriculum for bridging the theory and practice gap in marketing education. This new approach aims to develop students' marketing and soft skills like communication, creativity, and collaboration and facilitate their integration into professional life. By applying a project-based learning approach and integrating innovation methods like design thinking, the course curriculum improves students’ engagement and ability to address and solve real and impactful company challenges. The paper also provides a detailed road map of tasks related to the preparation phase and project modules for instructors who consider implementing this new marketing curriculum. Moreover, it identifies areas for further research related to measuring this new course curriculum's impact on the learning process and faculty development.
Download

Paper Nr: 104
Title:

Adapting Formal Logic for Everyday Mathematics

Authors:

Antti Valmari

Abstract: Although logic is considered central to mathematics and computer science, there is evidence that teaching logic has not been a great success. We identify three issues where what is typically taught conflicts with what is needed by those who are supposed to apply logic. First, what is taught about the notion of implication often disagrees with human intuition. We argue that in some cases human intuition is wrong, and in some others teaching is to blame. Second, the formal concepts of logical consequence, logical equivalence and tautology are not the similar concepts that everyday mathematicians and computer scientists need. The difference is small enough to go unnoticed but big enough to cause confusion. Third, how to deal with undefined operations such as division by zero is left informal and perhaps fuzzy. These problems also harm development of computer tools for education. We present suggestions about how to address them in teaching.
Download

Paper Nr: 108
Title:

The Developer’s Journey: A Storytelling Framework for Cooperative Learning in Software Engineering

Authors:

Patrick Wolfschwenger, Mona Emara, Wolfgang Lumetsberger, Thomas Hatter, Barbara Sabitzer and Zsolt Lavicza

Abstract: An educational storytelling concept is presented, inspired by the archetypal story pattern common in ancient myths as well as modern day adventures. Software development is a complex profession demanding constant learning and improvement in a field changing almost daily. Apart from learning new technologies and writing computer code, much of a developer’s time is spent on problem-solving and debugging – that is, detecting and correcting errors and bugs that cause a system to break or behave unexpectedly. The average developer regularly goes through a series of transformative steps to overcome intricate problems that often appear obscure and enigmatic at the beginning. The return with special knowledge to share with others is the final reward earned on the Developer’s Journey. Under the premise that a good story can change our perception and offset the biases of our interpretation of reality, a didactic method has been designed for sharing and interpreting experiences in a cooperative learning environment. In the context of cloud computing education, its effects on problem-solving, motivation and perception are evaluated. We analyze transformative learning opportunities in connection with narratives and discuss its potentials and limitations in community-based learning.
Download

Paper Nr: 119
Title:

Towards a Work Task Simulation Supporting Training of Work Design Skills during Qualification-based Learning

Authors:

Ramona Srbecky, Michael Winterhagen, Benjamin Wallenborn, Matthias Then, Binh Vu, Wieland Fraas, Jan Dettmers and Matthias Hemmje

Abstract: This paper describes a novel approach towards integrating work task simulation-based training of skills related to configuring relevant features for work design with the Qualifications-Based Learning Model (QBLM) approach. To achieve this, nine psychologically relevant work design characteristics from work content, workflow/organization, and social relations can be manipulated in the simulated work training tasks and their training context. The concretization of these work design characteristics requires extensive psychological testing and fine-tuning of the parameters for simulating the respective working conditions. For this purpose, Kirkpatrick's evaluation model from 1998 will be used. Therefore, the existing approach of QBLM will be used to develop an Applied Game for a simulation of work tasks. The existing tools and systems for QBLM will be extended by a QBLM-oriented gaming and learning analytics framework and the approach of QBLM-based Structural Didactical Templates. Besides the relevant state of the art, the conceptual modelling for the approach as well as a first set of initial visual prototypes of the system image will be presented following a user centered design methodology. Furthermore, a cognitive walkthrough of the visual prototype will be performed to support a first formative evaluation. The paper concludes with a summary and the remaining challenges of the approach.
Download

Paper Nr: 171
Title:

On the Use of Regular Expressions and Exact-text Matching in Computer-based Test Scoring Algorithms

Authors:

Wojciech Malec

Abstract: This paper addresses the issue of implementing two alternative approaches to developing automated scoring algorithms in computer-based language testing. One of the approaches discussed is based on the application of regular expressions and the other is based on exact-text matching. Although scoring algorithms that make use of regular expressions are technologically very attractive, there is evidence to indicate that they are not able to guarantee perfect scoring accuracy. Accordingly, in testing situations where decisions about the test takers need to be made on the basis of test scores, as in school settings, exact-text matching may actually be the preferred option. Moreover, whichever approach is adopted, it seems reasonably clear that automated scoring should ideally be subject to some human verification. The paper includes a brief description of a testing system where automated scoring employing exact-text matching is supplemented by human verification of the results.
Download

Paper Nr: 72
Title:

BubbleMumble: A Serious Game for the Dissemination of Scientific Results in Secondary Schools

Authors:

Alessandro Signa, Manuel Gentile, Sabrina Picciotto, Antonella Cusimano and Salvatore Perna

Abstract: Disseminating the scientific results of a project, especially to young audiences such as secondary school students, is a difficult task. Often the worlds of research and school are so far apart in terms of communication that there is a risk of dissipating dissemination efforts without achieving satisfactory results. Serious Games are a tool that can respond to this problem by providing a fun and effective environment that is very close to the world of young people, and that uses familiar language through which the educational content can be conveyed. In this paper, we will present BubbleMumble, a Serious Game designed and implemented to disseminate the results of the European project VES4US. We will also describe the project together with its dissemination objectives, and finally, we will present the results of an experiment on the use of the serious game involving 131 students of the secondary school.
Download

Paper Nr: 94
Title:

New Categorization of Practical Works Activities with Hybridization of Bloom’s Taxonomy, Grimard’s Pyramid, and Specific MOOC

Authors:

Karima Boussaha, Mouhamed Beggas and Khalil Khoualdi

Abstract: Due to the outbreak of the coronavirus pandemic and the total confinement imposed on all countries to prevent the spread of the virus, Massive open online courses (MOOC) systems have been widely used in recent years, and have attracted more attention in educational institutions, especially. But MOOCs intended for learning practical work have not been adequately addressed. However, everyone knows that the chances of dropping out of MOOCs are very high compared to conventional offline courses. Researchers have implemented extensive and diverse methods to determine the reasons behind learner attrition or lack of interest to apply timely interventions. We decided to address the dropout problem due to the lack of motivation among learners, with special practical works MOOCs. We have hybridized two methodologies: cognitive levels of learners, namely, Bloom’s taxonomy and Grimard’s pyramid for motivation this hybridization allowed us to create a new categorization for practical works, and we propose a new MOOC for learning practical works activities for programming languages in computer science. The main objective of this MOOC platform is to automatically generate practical works of different levels of complexity to be solved according to the level of motivation related to the learner. It composed into three principal components: IMMS survey component, motivation component, and practical works generator component.
Download

Paper Nr: 97
Title:

An Application of a Gamification to Knowledge Management Teaching: A Qualitative Evaluation

Authors:

Antonilson da Silva Alcantara and Sandro Ronaldo Bezerra Oliveira

Abstract: The education area has been encouraging the adoption of innovative practices and methodologies for the teaching and learning process. Teaching in Information Technology (IT) courses brings several challenges. Thus, the objective of this work is to present a qualitative analysis of the application of a gamification, adapted for the remote modality, applied in the context of a software quality laboratory about knowledge management. A brief description of the gamified approach is made, followed by the application plan of this proposal. Then, a brief report about the analyzed case study is presented. Soon after, the qualitative evaluation is detailed as well as its results. Finally, conclusions and future work are presented.
Download

Paper Nr: 103
Title:

Application of a Gamification to Solve Problems of Software Process Improvement in the Educational Context: A Case Study

Authors:

Elziane Monteiro Soares and Sandro Ronaldo Bezerra Oliveira

Abstract: Specialized studies report that organizations face several problems and difficulties in conducting software process improvement initiatives. Among the existing factors are issues related to the attitudes of individuals, for example, resistance to change, lack of motivation, support and commitment of those involved in the initiatives. In this context, it is important that organizations adopt approaches and strategies to facilitate the implementation of Software Process Improvement (SPI) initiatives. Thus, the use of gamification in the context addressed can stimulate people's motivation and commitment to effectively join and participate in SPI initiatives. Gamification has been used to assist in the teaching-learning process, and can be applied in the educational area or in companies, to stimulate a learning and work climate through the motivation of the people involved. Thus, the objective of this work is to analyze the results obtained in a Case Study from the application of a dynamic with gamification elements in an SPI context.
Download

Paper Nr: 154
Title:

Towards Deep Learning in the University through Collaborative Instructional Design based on Learning Outcomes and Threshold Concepts

Authors:

Jack Fernando Bravo-Torres, María Dolores Fernández Pérez, Cinthya María Cevallos-Ludeña, Wilson Daniel Bravo-Torres and Esteban Fernando Ordoñez-Morales

Abstract: This article presents a proposal for the development of a collaborative curriculum and instructional design at the university. It starts from the premise that teaching-learning processes at any level of training must be designed, managed and implemented in a collaborative way, supported by teacher structures grouped around their domains of knowledge. Moreover, we consider as central axes of all curricular and instructional design a correct selection and structuring of the contents to be studied, based on the identification of the conceptual structures of the topics under study (threshold concepts and their interlinkages) together with an appropriate definition of the desired learning outcomes and evaluation tools.
Download

Paper Nr: 162
Title:

Assessment for Computer Programming Courses: A Short Guide for the Undecided Teacher

Authors:

João-Paulo Barros

Abstract: As the large number of articles on teaching introductory programming seem to attest, teaching and learning computer programming is difficult. However, perhaps surprisingly, the assessment design for those courses does not seem to be the most studied aspect. This short position paper provides a structured set of options and alternatives to consider when choosing the assessment elements for a programming course. The objective is to promote additional reflection on several alternatives for each assignment, exam, or other assessment elements. Along with this presentation, we point to eventually valuable references. We believe the resulting information should be helpful and applicable to many other disciplines, but the focus is on computer programming courses.
Download

Paper Nr: 173
Title:

Formative e-Assessment in Engineering Education

Authors:

Odysseus Tsakiridis and Panos Photopoulos

Abstract: This paper presents a pedagogical practice introduced to second-year undergraduate Electrical and Electronic Engineering students to enhance learning and understanding during the classes. The practice consisted of four formative, objective-type e-assessments taken in two months. Each assessment followed a two-week teaching period. During the e-tests, the students used their notes and worked in groups or independently. Each test included a small number of problems in Electronics uploaded at the course's web page. The assessments were not competitive, and the students were allowed to discuss the solutions with the tutor during the problem-solving session. After the fourth test, the students evaluated the practice by answering a survey. The responses showed high satisfaction with the e-assessment, student retention during classes and active participation. The e-assessment increased students' engagement through interactive learning in a non-competitive environment, followed by a moderate improvement in the final examinations' grades. This paper highlights the opportunity to mobilise students' active participation in the lectures and bring closer teaching, learning and assessment with the help of the Learning Management System (LMS).
Download

Area 4 - Social Context and Learning Environments

Full Papers
Paper Nr: 37
Title:

Individualizing Learning Pathways with Adaptive Learning Strategies: Design, Implementation and Scale

Authors:

Ana Donevska-Todorova, Katrin Dziergwa and Katharina Simbeck

Abstract: Individual undergraduate learners have heterogeneous knowledge backgrounds and undergo diverse learning experiences during their university studies. Consequently, designs of virtual learning environments should adjust to learners’ needs and competencies, especially in the current pandemic crisis. This paper discusses pedagogical aspects of personalized and self-regulated learning and situates its focus on design, implementation, and scale of e-content and e-activities for individualized learning pathways (ILP). Characteristics of ILP such as shape, length, and turning points enabled through adaptive features of existing Learning Management Systems (LMS) have seldom been discussed in the literature. We tackle this issue from a didactical perspective of microlearning with regards to three adaptive learning strategies: 1) Feedback Adaptations, 2) Task Design, and 3) Task Sequence Design. Within a first phase of a complete initial Design Research (DR) cycle, we have collected and analysed data which enable us to generate, cluster and label queries and differentiated items for each of the three strategies. Further on, we offer a visualization of possible ILP illustrated with contextual examples of productive, technology-based task and feedback designs applicable and scalable in higher education settings.
Download

Paper Nr: 175
Title:

A Delphi Method Approach to Develop Anchor Examples for the Self-evaluation of Corporate Community Managers

Authors:

Verena Jautelat and Alexander Clauss

Abstract: Corporate Community Managers (CCM) significantly support the creation and distribution of knowledge to achieve common business goals. The job profile of CCM requires multifaceted competences. It lacks company independent as well as scientifically rigorous descriptions of competences and related qualification opportunities. The activity of CCMs is characterized by the organic growth of communities in companies, which make it necessary to evolve with the communities. These characteristics encourage lateral entrants to the profession and often call for on-the-job qualifications. A conceivable solution to meet these requirements are competence-oriented micro qualification modules, as they allow individualized, need-oriented qualification based on a persons’ current competence level. For a realization it is necessary to offer precise tools for the self-evaluation of current competences. This can be achieved with detailed anchor examples. Such examples reflect highly specific, observable actions by describing individual work performances on different levels of skill proficiency. In combination with a comprehensive competence profile this allows to identify individual qualification gaps systematically. Prior research results regarding the competence profile and associated anchor examples for CCMs lack an empirical, multi perspective expert evaluation. This Delphi Method approach aims to close this gap. Therefore, this article provides an evaluation and modification of the CCM competence profile and its detailed description with anchor examples. Further, this research provides general recommendations and good practices for the design of competence profiles and associated anchor examples for job profiles in the field of digital communication.
Download

Short Papers
Paper Nr: 77
Title:

Impact of Viewpoint on Social Presence and Collaborative Processes in a Collaborative Serious Game

Authors:

Anthony Basille, Élise Lavoué and Audrey Serna

Abstract: Collaborative serious games have proven to be effective learning environments to enhance the development of learners’ soft skills, such as collaboration, negotiation and cooperation. To be effective, such role paying games should provide genuine interactions. However, little is known on how design choices, such as the viewpoint (either first or third person perspective), impact collaborative processes and learners’ perception of their partners. This paper reports an exploratory study on the impact of the viewpoint on the sense of social presence, and on collaborative processes that emerge from learners’ interactions in a collaborative serious game dedicated to soft skills training. To address this issue, learners played in either first-person or third-person perspective during a session of two games. Our results show that the first-person view allowed for a higher sense of social presence and increased information sharing. This seems to be mainly due to the knowledge asymmetry caused by the affordances of the environment, in other words design choices. These results can be applied in the design of collaborative serious games that support social interactions and collaborative skills training.
Download

Paper Nr: 79
Title:

New Professional Competencies and Skills Leaning towards Industry 4.0

Authors:

Roque Antônio Moura, Marco Rogério Silva Richetto, Daniela Ercole Dale Luche, Luiz Antonio Tozi and Messias Borges Silva

Abstract: Industry 4.0, the so-called fourth industrial revolution, has been popularized by a German government project to promote digitization and automation, and has become a global strategy disseminated throughout several countries. It is widely used by researchers and mentors in different contexts and studies on opportunities, risks and challenges concerning employability. Therefore, this study aims to address the challenges of recruiters in the face of trends in new skills, profiles, and professional competencies for safeguarding jobs. Its method involves a systematic literature review using the keywords “Human and Machine Learning” and “Industry 4.0 and Education”. Bibliometrics was performed on works published on the theme during the latest decade. Results demonstrate the importance of updating Human Resources and Educational policies within the development of new skills and competencies to meet the new professional profile requirements and ensure human employability.
Download

Paper Nr: 130
Title:

Game-based Events for School Community Mobilization

Authors:

Victor Prado, Carla Delgado, Mônica Ferreira da Silva, Waldir Siqueira Moura and Leandro Mendonça do Nascimento

Abstract: Community involvement in school activities has long been the topic of studies, and while much has been discussed in terms of its consequences and types of involvement, there is little research regarding events, as a way to mobilize school communities in Brazil, especially game-based events. In light of Brazil’s poorly perceived school environments as shown in 2018 PISA and the massive popularity of electronic games as a hobby for Brazilian youth, this research will attempt to demonstrate how game-based school events can be an effective way of involving school communities. This research followed a game-based city-wide project, which occurred simultaneously in all schools of Maricá in Rio de Janeiro state, in Brazil, over the course of 2019. While the project had many goals and activities, this article will aim on demonstrating the effects of its game-based events in relation to school communities, as perceived by teachers and their students who participated in the project.
Download

Paper Nr: 163
Title:

Open Education: Towards Epistemic Sustainability

Authors:

Barbara Class

Abstract: Conducted in a scholarship of teaching and learning approach (Boyer, 1990), this position paper shares a scholar’s reflection on epistemic sustainability. Conceived as a philosophy for Humans living harmoniously with the many ecosystems they are involved in, it is nurtured by values encountered in Open Education – freedom, transparency, sharing, universal ownership. It aims at reconsidering knowledge so that each individual can identify with it, resulting in a process of engaged learning and caring for knowledge environment. It rests on the diversity of knowledge systems (UNESCO, 2021) and contributes to the growth of the knowledge society. Discussed with the backdrop of a framework composed of social learning theories (Wenger, 2018) and the sociology of absences and emersions (Santos, 2016), it offers two examples of concrete changes in the praxis of scholars in computer-supported education. The first resides in programming algorithms for AI considering the diversity of knowledge systems and Open Education values. The second invites to reconsider the lifecycle of a course beyond academic borders.
Download

Paper Nr: 167
Title:

Active Learning Activities in a Pandemic Context for a Software Engineering Course: An Experience Report

Authors:

Isabel Sofia Brito and João Paulo Barros

Abstract: This paper reports the students’ perceptions regarding active learning (AL) activities in a pandemic context and the use of AL and related tools to improve soft skills, such as critical thinking and teamwork. This work describes the active learning activities applied in a pandemic context for a Software Engineering course and presents students’ survey results. Based on students’ opinions, we conclude that AL and the associated tools, while promoting soft skills, also promoted motivation and student engagement for face-to-face and remote classes in the pandemic context by minimizing the negative impact it may have caused on the students.
Download

Paper Nr: 15
Title:

A Study on Teachers’ Design Choices Regarding Online Collaborative Learning

Authors:

Francesca Pozzi, Flavio Manganello and Donatella Persico

Abstract: This study aims to contribute to our understanding of whether and to what extent collaboration is a consolidated teaching practice in Italian schools. The paper reports the results of a survey of Italian teachers (N=268) that investigated (self-reported) behaviours regarding the design of collaborative learning activities (prior to and during the pandemic). Results show that even if collaborative learning approaches are implemented to some extent by Italian teachers and were also proposed online as part of Emergency Remote Teaching during the lockdown - their design choices are not always in line with recommendations widely agreed by the Computer Supported Collaborative Learning (CSCL) research community.
Download

Paper Nr: 59
Title:

Virtualization of Data to Improve Pedagogical Approaches the Case of Higher Education in Morocco in the Face of the COVID-19 Pandemic

Authors:

Ismail Nanou, Hassna Akhasbi, Bouchaib Riyami and El Houssine Labriji

Abstract: The world in general and the educational community in particular will remember well the COVID-19 pandemic, which forced schools and educational institutions to close their doors and switch abruptly to distance teaching and learning where the success of the pedagogical continuity of the 2019/2020 academic year became a challenge of high importance. Students and teachers, mostly unprepared for the pedagogy supported by digital technology, have experienced great difficulties in assuming a quality pedagogical continuity. To this effect, the experience we are living, due to this pandemic, pushes us to rethink our pedagogical tools and practices as well as our technical devices set up, at a distance learning, via Information and Communication Technologies (ICT). In this context, it seems useful that these pedagogical activities, whatever the tools, techniques and platforms put in place, during this period of pandemic, should be able to be re-verified. To this end, a modelling based on five layers has been proposed, in order to analysis the feedbacks of the different actors participating in the learning process (students, teachers, and administrative agents), and this with the aim of proposing a data virtualization approach to help decision making and to improve the distance learning device and the different activities of the pedagogical approaches.
Download

Paper Nr: 99
Title:

Development of an Information and Reference Application for Vocational Guidance of Students

Authors:

Aigerim Sarzhanova, Rui Pedro Lopes, Aigul Tungatarova and Gauchar Borankulova

Abstract: The problem of choosing a specialty and direction when entering higher education, is now more and more urgent. Every year, according to statistics in Kazakhstan, more than 60% of university graduates do not work in their speciality of choice. This problem is more often associated with the fact that students choose a speciality and apply for a grant, and in the process of learning they understand that they do not want to work as a engineer for example and tries to find another work. Some of that problem could have been prevented if professional orientation in secondary education had been conducted in schools of Kazakhstan. Career guidance is a number of activities that need to be carried out systematically in primary and high schools. There is a lot of information available in the Internet, but being a schoolboy, a student of grade 9-10, it is very difficult to find reliable information. Consciously make an admission plan and go step by step to the goal. In my application there will be one centralized database, which would allow you to first undergo diagnostics, then make the right choice of direction and speciality. As a result, get a plan for admission to a university in any country. This article reviews the information and reference material, analyzes the market and current specialties in Kazakhstan for further employment, as well as all the necessary information to diagnose their abilities and build an individual plan for admission to university.
Download

Area 5 - Domain Applications and Case Studies

Full Papers
Paper Nr: 74
Title:

Design, Implementation, and Evaluation of Blockchain-based Trusted Achievement Record System for Students in Higher Education

Authors:

Bakri Awaji and Ellis Solaiman

Abstract: With a growing number of institutions involved in the global education market, it has become increasingly challenging to verify the authenticity of academic achievements such as CVs and diplomas. Blockchain is an enabling technology that can play a key role in solving this problem. This study introduces a blockchain-based achievement record system that produces a verifiable record of achievements. The proposed system aims to facilitate the process of authentication and validation of certificates reliably, easily and quickly, leveraging the unique capabilities offered through Blockchain technology (public Ethereum Blockchain) and smart contracts. We present the design and implementation of the system and its components and tools. We then evaluate the system through a number of studies to measure the system’s; usability, effectiveness, performance, and cost. A System Usability Scale (SUS) test gave a scale of 77.1. Through a literature survey we demonstrate that this system is a significant improvement on legacy systems, being both more user-friendly and more efficient. We also conduct a detailed cost analysis and discuss the positives and limitations of alternative blockchain solutions.
Download

Paper Nr: 80
Title:

Exploring Students’ Experiences and Perceptions of Computer Science: A Survey of Austrian Secondary Schools

Authors:

Sara Hinterplattner, Marina Rottenhofer, Iris Groher and Barbara Sabitzer

Abstract: Companies regularly report difficulties in recruiting ICT specialists. The shortage of skilled women in this domain is especially prominent. Research shows that early exposure to STEM may spark children’s interest and influence their future choice of careers. Children’s understanding and conceptualization of their physical environment strongly influence their ability to grasp STEM concepts and learning outcomes in related subjects. The goal of our work is to provide a better picture of children’s conceptions before they are confronted with computer science as a subject at school. To investigate students’ preconceptions of computer science, a study of 188 fifth-grade students was conducted before they first experienced computer science lessons at school. We asked them about their perceptions and experiences of computer science. Our results show that both students who identify as female and those who identify as male have a narrow view of computer science and associate the field mainly with working with computers. Despite the narrow view, many students show an interest in computer science but few want to work in this field in the future. Students who identify as male have a significantly higher interest in the field than those who identify as female.
Download

Short Papers
Paper Nr: 43
Title:

Adaptive Blended Learning Platform based on the 4Cs Architecture

Authors:

Iraklis Katsaris, Ilias Logothetis, Konstantinos Katsios and Nikolaos Vidakis

Abstract: In recent years institutions try to adapt their courses based on the students' needs. Research is focused on what data to extract from students and how to use them to provide personalized learning material. This article introduces the architecture of an Adaptive Blended Learning Platform that aims to help students develop 4Cs. The suggested platform is based on the principles of Bloom’s Taxonomy, the Felder-Silverman Learning Styles Model and Blended Learning. A simple interface is provided to the teacher to create and manage courses and classroom material. Additionally, through the platform personalized worksheets for a selected course are created. For the creation of such worksheets an algorithm acts as an assistant to the teacher that suggests which learning objects suit each student better. Finally, the materials available to students consist of digital and non-digital tools to make them more active and to stimulate their interest, such as activities, exercises and games that can be practiced both at classroom and at home.
Download

Paper Nr: 105
Title:

Outreach in K-12 Programming: A Systematic Literature Review on Audience and Purpose

Authors:

Agnese Addone and Vittorio Scarano

Abstract: Outreach Programs are informal educational initiatives that schools and universities, as well as companies and associations, promote: they represent a significant variety of courses and camps for learners, whether students or teachers. In this paper we provide an overview of the publications on Outreach Programs in K-12 Programming, in the last decade 2011-2021. The survey methodology adopted is the Systematic Literature Review: we classified the papers around two different axis, the audience and purpose of the Outreach Programs.
Download

Paper Nr: 133
Title:

Programming Experience Requirements for Future Visual Development Environments

Authors:

Anthony Savidis

Abstract: Visual programming is widely adopted for teaching purposes, considered as an appropriate starting base before introducing learners to typical programming languages. However, the progress in such tools is very slow and limited compared to standard programming environments. Moreover, there is no systematic classification regarding the most important requirements to improve the support of visual programming tasks. In this context, we introduce programming experience as the context-specific notion of user- experience for the programming domain. Then, we identify three groups of requirements relating to language, interaction and tools, and elaborate with specific requirements per group. In this analysis, we study related examples from current tools in various domains, while we propose scenarios inspired from source-based programming environments.
Download

Paper Nr: 150
Title:

Configurable Templates for Assistive Technology Mobile Apps: A Block-based Programming Approach

Authors:

Luís Filipe Garcia, João-Paulo Barros and Candida Viriato

Abstract: Simple computer activities have been used for a long time for cognitive and physical training in the context of rehabilitation or mental stimulation. An example is training the skills needed by users with special needs to access the computer through scanning access, which is an access method used by persons with major motor difficulties. The increased availability of less expensive mobile devices with large displays provides an ideal platform for these applications. This work-in-progress paper presents an ongoing work to empower rehabilitation therapists and special education teachers with no previous computer programming experience with a set of highly configurable apps supporting several types of activities for scanning access training. The apps are made available as open projects written in a block-based programming language. This way, they may be configurable by non-programmers while also allowing further changes depending on the programming skills of each rehabilitation therapist or special education teacher. This study intends to validate this approach among this group of users and formulate a set of guidelines concerning software architecture and organization and user interaction, to be used in the development of this kind of application.
Download

Paper Nr: 63
Title:

Collaborative Transdisciplinary Educational Approaches in AI

Authors:

Adriana Mihaela Coroiu, Alina Delia Călin and Horea-Bogdan Mureşan

Abstract: In this paper we present a transdisciplinary approach towards teaching and applying AI methods, to mitigate climate change related issues. The proposed method is a course with a student-centred approach, enabling collaborative experiential learning and multi-disciplinary exploration with specialists from different fields of expertise internationally. The study covered data collected through questionnaires, observations and evaluation, and was proven to stimulate creativity, motivation and innovation in using AI to effectively solve real-life problems, which is the aim of the course.
Download

Paper Nr: 95
Title:

Teaching BDD in Active Learning Environments: A Multi-study Analysis

Authors:

Nicolas Nascimento, Alan Santos, Afonso Sales and Rafael Chanin

Abstract: Software development practices to enhance software quality and help teams better develop collaboratively have received attention by the academic community. Among these techniques is Behavior-Driven Development (BDD), a development approach which proposes software to be developed focusing primarily on its expected behavior. Teaching-wise, introducing BDD on software engineering classes and/or training courses for software developers has become important. In this context, this study presents a body of knowledge on the impacts of teaching BDD in active learning environments (ALE). To achieve this, we have triangulated data from four data sources: (i) a systematic literature review; (ii) an expert panel with active-learning experts, (iii) a survey with participants in a software development course which teaches through active learning, and (iv) a case study on the effects of teaching and using BDD in an ALE. This study results are (i) the-state-of-the-art literature on this topic, (ii) an assessment of benefits and challenges of BDD in ALEs, and (iii) a set of best practices when teaching BDD in ALEs. We concluded that BDD has more positive than negative outcomes and we present a body of knowledge regarding BDD in ALEs.
Download

Area 6 - Ubiquitous Learning

Short Papers
Paper Nr: 25
Title:

Software Design and Modeling Practices in an Online Software Engineering Course: The Learners’ Perspective

Authors:

Mahum Adil, Ilenia Fronza and Claus Pahl

Abstract: Background. Global Software Engineering (GSE) education is an established practice in academia. Several methods and tools support communication and programming activities, but earlier development stages, such as software design and modeling practices, are less explored. Aim. The goal of this work is to analyze the learners’ perspective during an online Software Engineering course. In particular, we focus on planning/organization activities and socio-technical challenges during the software design and modeling process. Method. We used a mixed-method approach to collect data from 30 undergraduate students enrolled in an online Software Engineering course. We combined questionnaires and interviews to analyze four GSE elements (i.e., communication practices, team collaboration, task allocation and distribution, and usage of collaboration tools). Moreover, we analyzed the socio-technical challenges faced by the teams. Results. Brainstorming is the most common practice used for planning software design and modeling activities. According to students, the usage of variant design notation is among the technical challenges. Despite the challenges, students would prefer to continue working in distributed teams. Conclusions. The result shares the lessons learned that can be helpful to build best practices for managing software design and modeling activities in GSE project-based courses. It includes the need to define standard architectural terminologies, standard list of collaboration tools, early identification of architectural artifact dependencies, frequent design reviews, and face-to-face kick-off meetings.
Download

Paper Nr: 126
Title:

Communication Support System for Deaf and Hard of Hearing People by Captions Considering Sound Source and Sound Direction

Authors:

Nobuko Kato and Marie Kepler

Abstract: For a deaf and hard of hearing (DHH) visitor to be able to understand all information in a museum, it is necessary to present not only the human voice as captions, but also the sounds in the environment in such a way that the DHH visitor can understand. For this reason, we investigated communication support methods in a way that not only presents speech content as captions but also presents sound information, such as the source and direction of the sound source. In this paper, we examine a case in which the direction of the sound source is indicated by flowing text, and another case where the sound source is indicated not only by text but also by photos and pictograms, using the following two presentation methods: wearable AR glasses and floor projection.
Download