Background and Value Proposition

Self-Regulated Learning (SRL) is a critical determinant of academic success. Our research focuses on identifying which specific learning strategies correlate with improved performance and subjective well-being in students.

Why We Are Doing This

Many students struggle to accurately gauge their own comprehension (Metacognitive Monitoring) or effectively manage their study time (Forethought phase). By integrating directly with Moodle, the SRL Advisor provides minimal-friction behavioral data collection, for the intent of offering interventions—prompting students to select a learning strategy at the start of a unit and reflect on its usefulness afterward. In early versions we analyze user behaviors, and later, we will be able to provide recommendations based on statistical simulation and predictive analysis of student's Moodle activity.

The Value We Hope to Prove

  • TODO

Research Team

Andrew Schwabe, Lead Researcher & Developer

PhD Student

Özgür Akgün

Academic Advisor

Ella Haig

Academic Advisor


Foundational References

Schwabe, A., Akgün, Ö., & Haig, E. (2025). A Modular Approach to Cyclical Self-Regulated Learning Modeling with Machine Learning. AIEd Journal ???
Schwabe, A., Akgün, Ö., & Haig, E. (2025). Toward Cyclic A.I. Modelling of Self-Regulated Learning: A Case Study with E-Learning Trace Data. arXiv preprint arXiv:2507.02913.