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

TL;DR

This paper explores cyclic AI models for self-regulated learning in e-learning, using trace data to enhance prediction and understanding of students' learning behaviors, emphasizing the importance of cyclic and explainable models.

Contribution

It introduces SRL-informed features for modeling student activities, demonstrating improved prediction accuracy and advocating for cyclic modeling approaches in SRL.

Findings

SRL-informed features improve predictive accuracy

Cyclic models better capture SRL dynamics

Validation supports further research into cyclic SRL models

Abstract

Many e-learning platforms assert their ability or potential to improve students' self-regulated learning (SRL), however the cyclical and undirected nature of SRL theoretical models represent significant challenges for representation within contemporary machine learning frameworks. We apply SRL-informed features to trace data in order to advance modelling of students' SRL activities, to improve predictability and explainability regarding the causal effects of learning in an eLearning environment. We demonstrate that these features improve predictive accuracy and validate the value of further research into cyclic modelling techniques for SRL.