Students’ Activeness Measure in Moodle Learning Management System Using Machine Learning

Chandrakumar Thangavel
Valliammai S E (Thiagarajar College of Engineering)
Amritha P. P (Thiagarajar College of Engineering)
Karthik Chandran (Jyothi Engineering College)
Subrata Chowdhury (Sri Venkateswara College of Engineering &Technology (A))
Nguyen Thi Thu (Hanoi University of Industry)
Bo Quoc Bao (Hanoi University of Industry)
Duc-Tan Tran (Phenikaa University)
Duc-Nghia Tran (Vietnam Academy of Science and Technology)
Do Quang Trang (Vietnam National Post and Telecommunication Group)

Journal of Applied Engineering and Technological Science (JAETS)
Vol. 6 No. 1 (2024): Journal of Applied Engineering and Technological Science (JAETS)

Due to COVID-19, the need for online education has increased worldwide, prompting students to shift from traditional learning methods to online platforms as guided by higher education departments. Higher learning institutes are focused on developing constructive online learning platforms. This research aims to measure students’ academic performance on an online learning platform – Moodle Learning Management System (LMS) – using machine learning techniques. Moodle LMS, a popular free and open-source system, has seen significant growth since the COVID-19 lockdown. Many researchers have analyzed student performance in online learning, yet there remains a need to predict academic outcomes effectively. In this study, data were collected from a higher learning institute in Tamil Nadu, and linear regression was applied to predict students' final course outcomes. The analysis, based on students' activity in Moodle LMS across both theory and laboratory courses, helps faculty identify students at risk of failing and adjust instructional methods and assignments accordingly. This approach aims to reduce failure rates by providing timely warnings and encouraging students to improve their engagement with LMS resources.