Assessment of the level of student understanding in the distance learning process using artificial intelligence

Abstract

As technology develops, data mining technology is created which is used to analyse the level of understanding of students. This analysis is conducted to group students according to their ability to understand and master the subject matter. This research can provide guidance and insight for educators, as well as artificial intelligence, machine learning, association techniques, and classification techniques. Researchers and policymakers are working to optimise learning and improve the quality of student understanding. This study aims to analyse the level of student understanding in simple and structured terms. Using the Machine learning method to analyse the level of student understanding has the potential to impact the quality of education significantly. In addition, machine learning categories are qualified to be applied to the concept of data mining. The data mining techniques used are association and classification. Association techniques are used to determine the pattern of distance student learning. The following process of classification techniques is used to determine the variables to be used in this study using the Logistic Regression model where data that have been classified are grouped or clustered using the K-Means algorithm into three, namely the level of understanding is excellent, sound, and lacking, based on student activity, assignment scores, quiz scores, UTS scores, and UAS scores.