Modeling and predicting students' engagement behaviors using mixture Markov models

TL;DR

This paper introduces a mixture Markov model approach with a novel K-EM initialization method to classify student engagement behaviors, demonstrating promising results on real datasets and providing insights through visualization.

Contribution

The paper proposes a new clustering method using mixture Markov models with K-EM initialization to better understand student engagement patterns.

Findings

K-EM outperforms other EM variants in clustering accuracy.

Visualization of clusters reveals meaningful engagement behavior patterns.

Method shows promising results on real educational datasets.

Abstract

Students' engagements reflect their level of involvement in an ongoing learning process which can be estimated through their interactions with a computer-based learning or assessment system. A pre-requirement for stimulating student engagement lies in the capability to have an approximate representation model for comprehending students' varied (dis)engagement behaviors. In this paper, we utilized model-based clustering for this purpose which generates K mixture Markov models to group students' traces containing their (dis)engagement behavioral patterns. To prevent the Expectation-Maximization (EM) algorithm from getting stuck in a local maxima, we also introduced a K-means-based initialization method named as K-EM. We performed an experimental work on two real datasets using the three variants of the EM algorithm: the original EM, emEM, K-EM; and, non-mixture baseline models for both datasets. The proposed K-EM has shown very promising results and achieved significant performance difference in comparison with the other approaches particularly using the Dataset. Hence, we suggest to perform further experiments using large dataset(s) to validate our method. Additionally, visualization of the resultant clusters through first-order Markov chains reveals very useful insights about (dis)engagement behaviors depicted by the students. We conclude the paper with a discussion on the usefulness of our approach, limitations and potential extensions of this work.