Students’ learning habit factors during COVID-19 pandemic using multilayer perceptron (MLP)

• Published in: International Journal of Advanced Technology and Engineering Exploration
• Main Author: Mangshor N.N.A.; Ibrahim S.; Sabri N.; Kamaruddin S.A.
• Format: Article
• Language: English
• Published: Accent Social and Welfare Society 2021
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85101835862&doi=10.19101%2fIJATEE.2020.S1762140&partnerID=40&md5=29d67c25e4d0b852c705e6aa79b108e2

Rapid dissemination of coronavirus disease 2019 (COVID-19) across the globe has necessitated the introduction of social distance interventions to slow the spread of the disease. Online learning has become essential, considering the implications of this virus to be spread among the students during physical classes. Hence, educational institutions have shifted the traditional physical classes to online classes. Due to this implementation worldwide, a study on student learning habits is crucial to analyse students learning habits as it is one of the main factors that affecting students’ performance in learning. Fifteen independent variables as inputs to one of the well-known Artificial Neural Network algorithms, Multilayer Perceptron (ANN-MLP) has been used to investigate the student’s learning habit factors during the COVID-19 pandemic. Through analysing original survey data from 420 secondary students (Grade 6-12) in Hanoi shows that the ANN-MLP model is stable for both ANN-MLP optimization algorithms which are for Adjusted Normalized, to be concise. The hours spend for self-learning before COVID-19 is observed to be the most influential factors of student’s learning habit during COVID-19 pandemic. Moreover, the promising Sum of Squares Error (SSE) and Relative Error (RE) values obtained signify that the ANN-MLP model is appropriate in identifying the student’s learning habit factors during COVID-19 pandemic. © 2021 Nur Nabilah Abu Mangshor et al.