Learning Data Analysis Using Educational Data Mining Techniques

Abstract

The main purpose of this research paper is to analyze Moodle data and identify the most influencing features to develop a predictive model. The research applies a wrapper-based feature selection method called Boruta for selecting the best predicting features. Data were collected from 81 students enrolled in the Human Computer Interaction (COMP341) course offered by the Department of Computer Science and Engineering. The dataset contained eight features: Assignment.Click, Chat.Click, File.Click, Forum.Click, System.Click, Url.Click, and Wiki.Click as independent features, and Grade as the dependent feature. Five classification algorithms, namely K Nearest Neighbour, Naïve Bayes, Support Vector Machine (SVM), Random Forest, and CART decision tree, were applied to the Moodle data. The findings show that SVM has the highest accuracy compared to other algorithms. It suggested that File.Click and System.Click were the most significant features. This type of research helps in the early identification of students’ performance. The growing popularity of the teaching-learning process through an online learning system has attracted researchers to work in the field of Educational Data Mining (EDM)