Classification of Student Success in Online Courses Using Feature Selection and Convolutional Neural Network

ABSTRACT

During the Covid 19 pandemic, the number of online learning environments that were previously used but not widespread has increased. Machine learning methods and estimation and classification studies of student success on learning analytics data in these environments have gained importance in recent years. In this study, a method based on OHE (one-hot encoding) representation of course activities, feature selection, and convolutional neural network is proposed for the classification of student success. In order to demonstrate the effectiveness of the proposed method, comparative evaluations were presented with incoming machine learning algorithms (RF, MLP, k-NN) and literature. Experiments on the UK Open University online learning dataset, which is available to researchers, show that the proposed method improves current study success in the literature. © 2022 IEEE.