AdPisika: an adaptive e-learning system utilizing k-means clustering, decision tree, and bayesian network based on felder-silverman model to enhance physics academic performance

Abstract

Amid the shift to online learning during the COVID-19 outbreak, the academic performance of students has become a concern. To address this, Adaptive Learning Systems (ALS) have emerged, these help in assessing students and delivering personalized content. This study develops an ALS incorporating K-means Clustering, Decision Tree, and Bayesian Network techniques, based on the Felder-Silverman Learning Style Model (FSLSM). The aim is to optimize learning materials based on students' current Knowledge Level (KL) and their Learning Style (LS). The students who utilized the proposed system showed substantial improvements in their performance across the Electromagnetic Spectrum, Light, Electricity, and Magnetism modules, with increases of 28.8%, 41.4%, 31.9%, and 32.9%, respectively. These findings provide strong evidence that the adaptive e-learning system had a significant positive impact on post-test scores compared to pre-test scores, surpassing the outcomes achieved with the traditional learning approach. With a silhouette score of 0.7 for K-Means clustering, an accuracy of 87.5% for Decision Tree, and a 95.1% acceptance value for the distribution of learning objects using the Bayesian Network, the proposed adaptive system demonstrated successful implementation of these machine learning algorithms. Furthermore, the proposed system received "excellent" ratings for functional stability, performance efficiency, compatibility, and reliability, with mean values of 4.49, 4.43, 4.43, 4.8, and 4.47 respectively.