Supervised Educational Data Mining to Discover Students’ Learning Process to Improve Students’ Performance

Online learning has social impact on students. Some students might experience impoverished learning due to high social isolation, less face-to-face interaction, difficulty in performing teamwork activities, low understanding, and lack of concentration on learning activities. However, some students can thrive on online learning. Knowledge discovery from students’ event logs generated from their online learning can help to understand their level of understanding and concentration on the learning subject. Subsequently, this knowledge can be used to predict students’ academic performance on their final grade. This paper presents supervised educational data mining, namely J48 decision tree approach to classify students based on their learning process and activities extracted from event logs in online learning system to predict their final grade. The generated model can be used to offer helpful recommendations to improve students’ learning process and academic performance, especially to students that experience impoverished learning, and it also allows instructors to provide appropriate feedbacks and advice to the students in a timely manner.