Toward Cyclic A.I. Modelling of Self-Regulated Learning: A Case Study with E-Learning Trace Data

Abstract

Many e-learning platforms claim, or desire to help improve students’ self-regulated learning (SRL), but SRL theory models are not easily represented with modern machine learning or A.I. technologies because of their cyclic and undirected nature. We apply SRL inspired features to trace data in order to improve modelling of students’ SRL activities. We demonstrate that these features improve predictive accuracy and validate the value of further research into cyclic modelling techniques for SRL.

Presenters

Andrew Schwabe
Student, PhD, University of St. Andrews Primary, Pennsylvania, United States

Details

Presentation Type

Innovation Showcase

Theme

2025 Special Focus: Human Learning and Machine Learning—Challenges and Opportunities for Artificial Intelligence in Education.

KEYWORDS

Artificial Intelligence, Self Regulated Learning, E-Learning