Analyzing Student Online Learning Behaviors and Academic Performance in Science Education Using Machine Learning Techniques

Abstract

Listen

Translate article

This study investigates the factors influencing student engagement and performance in online science education through the application of machine learning models, specifically Random Forests, Decision Trees, and Support Vector Machines (SVM). With the rapid growth of online education, understanding students' adaptability and learning behaviors has become increasingly critical. A systematic analysis of features such as study duration, daily study habits, and demographic factors revealed significant insights into their impact on academic achievement in science subjects. The Random Forest model outperformed others in classification accuracy, achieving an accuracy of 81%. The findings emphasize the importance of tailored educational strategies that foster consistent study practices and address the unique needs of diverse learners, ultimately enhancing learning outcomes in online science education.