An Early Intervention Technique for At-Risk Prediction of Higher Education Students in Cloud-based Virtual Learning Environment using Classification Algorithms during COVID-19

Abstract

Higher Education is considered vital for societal development. It leads to many benefits including a prosperous career and financial security. Virtual learning through cloud platforms has become fashionable as it is expediency and flexible to students. New student learning models and prediction outcomes can be developed by using these platforms. The appliance of machine learning techniques in identifying students at-risk is a challenging and concerning factor in virtual learning environment. When there are few students, it is easy for identification, but it is impractical on larger number of students. This study included 530 higher education students from various regions in India and the outcomes generated from online survey data were analyzed. The main objective of this research is to predict early identification of students at-risk in cloud virtual learning environment by analyzing their demographic characteristics, previous academic achievement, learning behavior, device type, mode of access, connectivity, self-efficacy, cloud platform usage, readiness and effectiveness in participating online sessions using four machine learning algorithms namely K Nearest Neighbor (KNN), Support Vector Machine (SVM), Linear Discriminant Analysis (LDA) and Random Forest (RF). Predictive system helps to provide solutions to low performance students. It has been implemented on real data of students from higher education who perform various courses in virtual learning environment. Deep analysis is performed to estimate the at-risk students. The experimental results exhibited that random forest achieved higher accuracy of 88.61% compared to other algorithms.

Ed-Net: Multivariate Time Series Approach for Uncovering Student Learning Outcome in Higher Education Using Blended Deep Learning Technique

“…This study compares the results among classical machine learning algorithms and the proposed model gives 70-75% accuracy. Rose et al, [20] suggested a model to predict at-risk students in the early stage of the course in a cloud virtual learning environment. The dataset contains 530 records with 46 features, including student demographic details, academic progress, learning style, and other online usage information.…”