Analysis of Student Study of Virtual Learning Using Machine Learning Techniques

Abstract

Since COVID-19 was released, online education has taken center stage. Educational performance analysis is a central topic in virtual classrooms and across the spectrum of academic institutions. This research analyzed students' studies in virtual learning using many machine-learning classifiers, which include LogitBoost, Logistic Regression, J48, OneR, Multilayer Perceptron, and Naive Bayes, to find the ideal one that produces the best outcomes. This research evaluates algorithms based on recall, precision, and f-measure to determine their efficacy. Accordingly, the authors try to perform a comparative analysis of the algorithms in this research by employing two distinct test models: the use of training sets and the 10 cross-fold models. The research results demonstrate that the training set model outperforms the 10 cross-fold model. The findings demonstrate that the multilayer perceptron classifier utilizing the use training set model performs much better in terms of predicting student study in virtual learning.