Original title: Explainable Fuzzy Learner Modelling and Learning Analytics for Human-Centered Teacher Decision Support: A Vocational Education Case Study
Eleni Papachristou, Christos Troussas, Akrivi Krouska, Christos Papakostas +1 · September 2026
Educational tools often separate personalized student help, adaptive feedback, and data analytics. They also rarely combine these tools into clear systems that help teachers make decisions. To solve this, researchers built the e-Teacher Assistant. It tracks student actions, models how students learn, and uses simple IF–THEN rules to make clear decisions. This setup gives students adaptive support while giving teachers helpful data. Researchers tested the system during a three-month course. They found strong student approval. Specifically, 95.7% of students found the feedback useful, 94.9% liked interacting with the AI Assistant, and 92.3% found it easy to use. Additionally, 88.0% felt it helped independent learning, and 86.3% rated it as fair and objective. All four teachers strongly agreed that it was useful and helped monitor progress. Finally, logged data showed that students used AI-assisted examination support across 64.42% of learner–chapter records.
Imagine a coach watching a team practice. If the coach only looked at the final score, they would not know which drill confused which player, and seeing every pass in real time would be too much detail. In this paper, the system watches learners' actions, builds a picture of each one's understanding, and turns that picture into simple rules the teacher can read and override. The teacher stays in charge, but now has a live summary instead of a guess.
For vocational educators, this matters because it shows AI can support teaching without replacing teacher judgment. The system gives teachers simple if-then rules and analytics, so they keep oversight while students get adaptive feedback. That addresses a central worry about AI in classrooms: transparency.
The abstract doesn't say much about limitations beyond describing the evidence as initial empirical support from a single three-month deployment in one vocational course. It does not report a control group or objective learning gains.
Ask anything about this paper. Answers come from its abstract, and say so when the abstract doesn't cover your question.
Explainable Fuzzy Learner Modelling and Learning Analytics for Human-Centered Teacher Decision Support: A Vocational Education Case Study — Eleni Papachristou, Christos Troussas, Akrivi Krouska et al. — Entropy — doi:10.3390/e28091036
Abstract licence: CC BY
Explanation generated by Synthesis from the abstract — it is not the original paper.