Analyzing Sensitive Factors Affecting Online Academic Performance in the New Normal: A Machine Learning Perspective

Online distance learning (ODL) is one extension of the distance learning approach introduced by the Department of Education (DepEd) as part of its learning continuity in the new normal (COVID - 19 times). Despite the advantages brought by online learning in continuing learners' learning experiences and improving learners' academic performance during the pandemic, it is still of vital importance to examine what factors are sensitive to changes in learner's online academic performance. In this study, sensitive factors affecting online academic performance are examined through the lens of machine learning (ML) methods: Boruta algorithm (BA) for feature selection; multilayer perceptron neural network (MLP NN) for model formulation; and partial derivatives method (PDM) for sensitivity analysis. Data used in the analysis are responses in the survey participated by N = 978 senior high and junior school students of a private high school institution in the Philippines. Out of eighteen factors considered in the analysis, BA revealed only six relevant factors that contributes greater information to changes in student's online academic performance. Formulated MLP NN model achieved a high testing accuracy of 0.932 with a kappa coefficient of 0.891 and an f - measure of 0.924, that aided the sensitivity analysis using PDM to have better results. Sensitivity analysis showed that motivation and mental well- being are the most sensitive factors affecting both below average and above average online academic performance.

Keywords: Computer aided insturction, Analytical models, Machine learning algorithms, Sensitivity analysis, Pandemics, Machine learning, Artificial neural networks.  

To cite:  Lumacad, G. S., Damasing, J. V. C., Tacastacas, S. B. M., & Quipanes, A. R. T. (2022, October). Analyzing Sensitive Factors Affecting Online Academic Performance in the New Normal: A Machine Learning Perspective. In 2022 XVII Latin American Conference on Learning Technologies (LACLO) (pp. 01-07). IEEE.