The Teacher in the Loop: Co-design Approaches to Increase Teacher Agency with Learning Analytics
Alejandra Martínez-Monés, Universidad de Valladolid, Spain
AI for Adaptive Tutoring and College Student Success
Zach A. Pardos, UC Berkeley, United States
The Potential of Social Robots in Higher Education
Birgit Lugrin, Julius-Maximilians-Universitat Wurzburg, Germany
The Teacher in the Loop: Co-design Approaches to Increase Teacher Agency with Learning Analytics
Alejandra Martínez-Monés
Universidad de Valladolid
Spain
Brief Bio
Alejandra Martínez Monés is Associate Professor of Computer Science, specialising in Human-Computer Interaction, at the University of Valladolid, Spain. She is a member of the interdisciplinary research group GSIC-EMIC. Her research interests focus on how to help teachers to design and implement active pedagogies through learning analytics approaches and tools, adopting a human-centred perspective. She coordinates the Spanish Network on Learning Analytics (SNOLA) and is co-leader of the European SIG on Learning Analytics. She has been associate editor of IEEE Transactions on Learning Technologies for the last 5 years and is co-author of 28 articles indexed in ISI-JCR journals, as well as more than 100 conference papers and book chapters.
Abstract
The adoption of learning analytics (LA) and other intelligent technologies by teachers has faced obstacles, with one major issue being that existing tools often fail to align with teachers' needs and the specific constraints of their teaching environments. This misalignment has had a detrimental effect on teachers' agency. To address this issue, human-centred approaches applied to the design of learning technologies advocate for the use of co-design methods that enable teachers express their needs and goals. In this talk, I will present several examples of how teachers can be supported by processes, models, and tools at different stages of the design process of LA-based tools and interventions. Drawing on these examples I will discuss how co-design approaches relate to the trustworthiness of intelligent technologies in the classroom, with a particular emphasis on promoting teacher’s agency.
AI for Adaptive Tutoring and College Student Success
Zach A. Pardos
UC Berkeley
United States
https://bse.berkeley.edu/zachary-pardos
![]()
Brief Bio
Zachary Pardos is an Associate Professor of Education at UC Berkeley studying adaptive learning and AI. His early scholarship focused on formative assessment using Knowledge Tracing, the predominant model used for estimating skill mastery in computer tutoring system contexts. His recent work designing Human-AI collaborations to pave pathways to and within systems of higher education has been published in venues such as SIGCHI, AAAI, The Internet and Higher Education, and Science. This work has included the development of high-quality tools used by tens of thousands of users, including course recommender systems (AskOski), a Python library for Knowledge Tracing (pyBKT), and an open-source adaptive tutoring system and creative commons content library (OATutor).
He earned his PhD in Computer Science at Worcester Polytechnic Institute. Funded by a National Science Foundation Fellowship (GK-12), he spent extensive time with K-12 educators and students working to integrate educational technology into the curriculum as a formative assessment tool. After completing his PhD in 2012, he spent one year as a Postdoctoral Associate at the Massachusetts Institute of Technology. At Cal, he directs the Computational Approaches to Human Learning research lab, teaches in the data science undergraduate program, and is an affiliated faculty in Cognitive Science.
Abstract
Despite the decades-long establishment of effective computer tutoring software, no adaptive tutoring system has been developed and open-sourced to the field. The absence of such a system inhibits researchers from replicating adaptive learning studies, experimenting with new AI capabilities, and exploring various tutoring system design directions. For this reason, the Open Adaptive Tutor project aims to create more equitable access to adaptive learning technology with the introduction of the first open-source adaptive tutoring system based on Intelligent Tutoring System principles. This system and its completely Creative Commons adaptive textbook library of Algebra, Stats, and Calculus content, have been iteratively developed over three years with field trials in seven college math classrooms, drawing feedback from students, educators, and researchers. In this talk, I will describe how this system can be used as a foundation for exploring integrations of generative AI and share nascent results from initial evaluations of ChatGPT for hint and question generation. I will also discuss connections to transfer and articulation in higher education as well as future avenues for community involvement.
The Potential of Social Robots in Higher Education
Birgit Lugrin
Julius-Maximilians-Universitat Wurzburg
Germany
Brief Bio
Birgit Lugrin (birth name Birgit Endrass) is a professor for Media Informatics at the Julius-Maximilians-Universität Würzburg, Germany. In her research she focuses on the implementation and evaluation of socially interactive agents (intelligent virtual agents and social robots), exploring their potential in various domains such as education, storytelling or managing bias, and has published over 100 papers in this domain. Her work is interdisciplinary oriented, combining methods and knowledge from computer science, in particular human-computer interaction, and the cognitive sciences. Since prototypes including socially interactive agents are designed for intuitive use by human users, she uses a human-centered design approach to implement these prototypes and empirically evaluates them with the target user groups. Birgit Lugrin is one of the editors of ACM’s "The Handbook on Socially Interactive Agents”, a large collection of surveys that introduce, summarize, and discuss the last 20 years of research in the domains of embodied conversational agents, intelligent virtual agents, and social robotics.
Abstract
Social Robots (SRs) are designed to interact with people and one another in a socially interactive manner using multimodal communicative behaviors, with the goal to support humans in various social domains. Since the social component plays a crucial role in learning and teaching, SRs bear great potential to scaffold computer supported education by bringing in an interactive embodied social entity that can take different roles such as tutor or peer. In higher education one-to-one tutoring and personalization is rare but could be realized by the deployment of SRs. In my talk, I will introduce the potential benefits of SRs in higher education and explore different scenarios including SRs, both from a research and an applied perspective.