Exploring Students Digital Activities and Performances through Their Activities Logged in Learning Management System Using Educational Data Mining Approach

• Published in: Interactive Technology and Smart Education 2023-02, Vol.20 (1), p.58-72
• Main Authors: Bessadok, Adel, Abouzinadah, Ehab, Rabie, Osama
• Format: Article
• Language: English
• Subjects: Academic Achievement; Clustering; Cognitive style; Colleges & universities; COVID-19; Data Analysis; Data mining; Distance learning; Educational Environment; Electronic Learning; Empirical analysis; Foreign Countries; Learning Activities; Learning Analytics; Learning Management Systems; Learning Processes; Online Courses; Online instruction; Profiles; Student Behavior; Students; Teaching Methods; Undergraduate Students
• ISSN: 1741-5659; 1758-8510
• DOI: 10.1108/ITSE-08-2021-0148

Purpose: This paper aims to investigate the relationship between the students' digital activities and their academic performance through two stages. In the first stage, students' digital activities were studied and clustered based on the attributes of their activity log of learning management system (LMS) data set. In the second stage, the significance of the relationship between these profiles and the associated academic performance was tested statistically. Design/methodology/approach: The LMS delivers E-learning courses and keeps track of the students' activities. Investigating these students' digital activities became a real challenge. The diversity of students' involvement in the learning process was proven through the LMS which characterize students' specific profiles. The Educational Data Mining (EDM) approach was used to discover students' learning profiles and associated academic performances, where the activity log file exemplified their activities hosted in the LMS. The sample study data is from an undergraduate e-course hosted on the platform of Blackboard LMS offered at a Saudi University during the first semester of the 2019-2020 academic year. The chosen undergraduate course had 25 sections, and the students attending came from science, technology, engineering and math background. Findings: Results show three clusters based on the digital activities of the students. The correlation test shows the statistical significance and proves the effect of the student's profile on his academic performance. The data analysis shows that students with different profiles can still get similar academic performance using LMS. Originality/value: This empirical study emphasizes the importance of the EDM approach using clustering techniques which can help the instructor understand how students use the provided LMS content to learn and then can deliver them the best educational experience.