A Model For Evaluating The Efficacy Of E-learning In Higher Educational Institutions Using Educational Data Mining

Abstract

Educational Data Mining (EDM) and Learning Analytics (LA) play a key role in developing methods for discovering student learning patterns and behaviors by interrogating this robust set of data now available in learning environments. The main objective of this study is to develop a model for evaluating efficacy of eLearning at Higher Educational Institutions (HEI’s). To measure the efficacy of eLearning, data on student activity within eLearning LMS and student academic performance is analyzed. In this study, Orange data mining tool is used for the analysis of the data. Support Vector Machine, Random Forest, Decision Tree, Nave Bayes, Logistic Regression, and Neural Network are among the categorization techniques provided within Orange. These classifiers are compared based on their accuracy. The selected classifiers are evaluated against a k-fold cross validation, accuracy, precision, recall, and F-score. According to the empirical findings, the Support Vector Machine (SVM) algorithm was the best data mining model for estimating students' academic achievement.