Exploring Behavioral Patterns for Data-Driven Modeling of Learners' Individual Differences

Abstract

Educational data mining research has demonstrated that the large volume of learning data collected by modern e-learning systems could be used to recognize student behavior patterns and group students into cohorts with similar behavior. However, few attempts have been done to connect and compare behavioral patterns with known dimensions of individual differences. To what extent learner behavior is defined by known individual differences? Which of them could be a better predictor of learner engagement and performance? Could we use behavior patterns to build a data-driven model of individual differences that could be more useful for predicting critical outcomes of the learning process than traditional models? Our paper attempts to answer these questions using a large volume of learner data collected in an online practice system. We apply a sequential pattern mining approach to build individual models of learner practice behavior and reveal latent student subgroups that exhibit considerably different practice behavior. Using these models we explored the connections between learner behavior and both, the incoming and outgoing parameters of the learning process. Among incoming parameters we examined traditionally collected individual differences such as self-esteem, gender, and knowledge monitoring skills. We also attempted to bridge the gap between cluster-based behavior pattern models and traditional scale-based models of individual differences by quantifying learner behavior on a latent data-driven scale. Our research shows that this data-driven model of individual differences performs significantly better than traditional models of individual differences in predicting important parameters of the learning process, such as performance and engagement.

Evaluating the Effectiveness of Bayesian Knowledge Tracing Model-Based Explainable Recommender

“…It should be noted that in this study, students with perfect scores on the pre-test were excluded in order to investigate the extent to which students who initially could not perform well improved. Similar pre and post-test scaling was used in evaluating the e-learning system (Akhuseyinoglu & Brusilovsky, 2022).…”

Exploration and Visualization of Learning Behavior Patterns From the Perspective of Educational Process Mining

“…Using process mining techniques to take course trajectories as research process, Salazar-Fernandez et al [29] analyzed the course trajectories of students based on courses they failed and validated the proposed model, finding that specific courses are associated with dropout rates. Akhuseyinoglu et al [30] applied sequential pattern mining methods to construct individual models of learners' practical behaviors and explored connections between learner behaviors and incoming and outgoing parameters of the learning process. It is shown that data-driven individual difference models significantly outperform traditional individual difference models in predicting important parameters of the learning process, such as performance and engagement.…”

A Study of Worked Examples for SQL Programming

“…Both tests had 10 problems, including 5 multiple-choice and 5 SQL fill-in-the-blank problems, which concentrated on SQL SELECT statements. Pre and post-test problems were isomorphic 1 .…”

“…In our prior work [1], we found out that learners exhibited two divergent practice behaviors in a similar SQL Practice System. Some students tended to learn by exploring worked-out examples and then solving SQL problems.…”