Tutorials
The role of the tutorials is to provide a platform for a more intensive scientific exchange amongst researchers interested in a particular topic and as a meeting point for the community. Tutorials complement the depth-oriented technical sessions by providing participants with broad overviews of emerging fields. A tutorial can be scheduled for 1.5 or 3 hours.
Tutorial proposals are accepted until:
April 10, 2026
If you wish to propose a new Tutorial please kindly fill out and submit this
Expression of Interest form.
Tutorial on
AI in Qualitative Education Research: Learn Peer-Reviewed Tools and Workflows with >90% Validated Accuracy
Instructor
|
James Goh
AILYZE
United States
|
|
|
|
|
Abstract
Generative AI is now widely available to education researchers, yet many continue to face practical and methodological barriers: how to integrate AI into qualitative analysis without compromising rigour, interpretive depth, transparency, or ethics; and how to produce an auditable analysis that reviewers and journals will trust.
This hands-on tutorial addresses these challenges by drawing on multiple peer-reviewed education studies that document field-tested, publication-ready AI-assisted qualitative tools and workflows. Across these studies, AI-supported coding and thematic analysis have been validated against human qualitative analysis with reported human-AI agreement exceeding 90% in specific benchmarked contexts.
Participants will learn to apply the same step-by-step workflows used in these published projects and adapt them to their own qualitative data and research aims. The tutorial explicitly emphasises a researcher-in-the-loop approach, clarifying where human judgement remains essential (e.g., defining analytic focus, resolving ambiguity, refining themes) and how to document these decisions transparently.
The session also demonstrates practical safeguards for grounding AI outputs in data, including evidence-linked summaries, quote-first theme development, and targeted checks for bias and hallucination. Participants will leave with a reusable, review-ready workflow that can be applied immediately after the conference.
Keywords
AI in education; qualitative research; thematic analysis; human-AI collaboration; research ethics; learning analytics; NLP
Aims and Learning Objectives
The tutorial aims to equip education researchers with practical, defensible methods for integrating AI into qualitative research while maintaining methodological integrity.
By the end of the tutorial, participants will be able to:
- Prepare qualitative education datasets for AI-assisted analysis, including transcription, translation, and data governance decisions.
- Conduct AI-assisted thematic coding with human oversight using inductive and deductive approaches.
- Validate and stabilise findings through structured quality checks that reduce overreach and surface uncertainty.
- Produce traceable outputs, including coded excerpts linked to source data, theme summaries, cross-segment comparisons, and visual reports suitable for publication.
- Use evidence-grounded analysis chatbots that always reference quotations and document locations.
- Design AI avatar interviewers for piloting and scaling qualitative data collection in education research contexts.
Target Audience
Education researchers
Doctoral and postgraduate students
Learning analytics researchers
Educational technology researchers
Practitioners conducting qualitative evaluation in education settings
Prerequisite Knowledge of Audience
None
Detailed Outline
Total duration: 90 minutes
0–10 minutes — Orientation
What generative AI can and cannot do in qualitative education research
When AI support is methodologically appropriate
Examples from peer-reviewed education studies
Maintaining interpretive control and researcher accountability
10–25 minutes — End-to-End Demonstration
Full workflow walk-through: raw text → coding → theme development → cross-segment comparison → evidence-linked reporting
Illustration of human-in-the-loop checkpoints
25–75 minutes — Guided Hands-On Practice
Participants work with their own data or provided datasets to:
Import qualitative data
Choose inductive or deductive analytic routes
Generate and review codes and themes
Refine interpretations using evidence links
Conduct subgroup comparisons
Produce a visual report and run structured chatbot queries
75–90 minutes — Ethics and Reviewer Readiness
Privacy and confidentiality safeguards
Bias and hallucination checks
Documenting AI use, decision points, and audit trails
Aligning reporting with education research and publication ethics expectations