<![CDATA[This study explores the use of Big Data in personalizing online learning in higher education, focusing on student access and engagement patterns in e-learning platforms. The main problem faced is the inefficiency in monitoring student engagement, which impacts academic outcomes. The solution offered is learning analytics analysis using clustering and classification techniques to personalize learning materials. Data is taken from student activities on e-learning platforms for one semester. Data processing is done using machine learning tools such as K-Means Clustering and Decision Tree. The results show that active engagement in e-learning platforms is associated with better academic performance, where students with higher access frequencies tend to have better grades. The visualization graph shows the trend of access intensity in the evenings and weekends, as well as the positive relationship between access duration and exam scores. With a Big Data-based system, institutions can improve the online learning experience and provide more personalized recommendations to support student academic success]]>
Copyrights © 2024
