Identifying Learning Style Using Students Behavior in E-Learning Management Systems Based on JRIP Classifier

Abstract

in this paper, we introduce an adaptive mechanism that provides students with courses that fit their individual learning style. This mechanism helps in improving the learning process to obtain better results. The adaptive mechanism is based on an advanced student modeling approach which identifies learning styles as a way to predict students’ learning style from their past behavior that make learning easier for students and increase their learning progress. Datamining is really a multidisciplinary area focusing on methodologies for extracting valuable knowledge coming from students log files and there are many useful datamining methods to extract data. This knowledge can be used to increase the caliber of education and can be employed for selection making in educational process. It is applied on student’s previous performance data to generate the model that can be used to predict the student’s learning style to improve their performance. In this work a comparative study among nine different datamining techniques of classification in order to determine the best classifier to be used in predicting students learning style from their past behavior.