1. Learning Analytics as a Predictive Tool in Assessing Students' Online Learning Navigational Behavior and Their Performance
- Author
-
Shalini Nagaratnam, Christina Vanathas, Muhammad Naeim Mohd Aris, and Jeevanithya Krishnan
- Abstract
Learning Analytics (LA) captures the digital footprint of students' online learning activity. This study describes students' navigational behavior in an e-learning setting by processing the LA data obtained from Blackboard LMS. This is an attempt to understand the navigational behavior of students and the relationship with learning performance. The study was carried out with 88 learners from a Malaysian private university. The course sites' log data and students' performance were analyzed, and the results were as follows: 4 navigational behaviors played an important role in student's academic performance which are active days, total learning time, number of views, and days delayed in accessing the assessment. Active learning from Tuesdays to Thursdays had a significant positive effect on performance. It was found that the higher activities (total learning time, number of journals viewing) translate to better performance. Days delayed in attempting assessments had a significant but mixed effect on performance, depending on the type of assessment. However, the number of logins is insignificant. The findings of this study provide empirical evidence of the importance of self-discipline in online learning and provide instructors with a predictive measure as a call for early intervention to help online students. [For the full proceedings, see ED654100.]
- Published
- 2023