Predicting learning result of learner in e-learning course with feature selection using SVM

In recent years, data mining targeting educational data has been widely performed. With the spread of the e-learning system, activities of various learners have been recorded. By analyzing this record, research is being conducted to evaluate the achievement level of the learner and to find hidden problems. In this paper, we compare the existing method and the method by SVM using feature selection for the method of classifying the final result from the learner's activity record. This confirms the effectiveness of the method using feature selection. Next, we confirmed that the click stream which is the activity data in the elearning system is more effective than the learner's profile in classification of grades. In the classification of learners with good grades, the connection records and the number of clicks in the latter period of the learning period are important factors, further the difference in the important features by the grade evaluation was shown.