# Students Behavioural Analysis in an Online Learning Environment Using Data Mining (ICIAfS)

**Authors:** I. P. Ratnapala, R. G. Ragel, S. Deegalla  
**arXiv:** [1412.7813](https://arxiv.org/abs/1412.7813)  
**Date:** 2014-12-25  
**Summary page:** https://www.summarizepaper.com/en/paper/1412.7813v1/

## Key points

- The study aimed to use Educational Data Mining (EDM) techniques to conduct a quantitative analysis of 412 students' interaction with an e-learning system through instructor-led non-graded and graded courses.
- The research was conducted to establish guidelines for a series of online short courses for the students.
- More than 40% of the student group were passive online learners in both graded and non-graded learning environments.
- The difference in learning environments could change the online access behaviour of a student group.
- Clustering divided the student population into five access groups based on their course access behaviour, with the least access group (NG-41% and G-42%) and highest access group (NG-9% and G-5%) being identified very clearly due to their distinct variation from other groups.
- This research provides valuable insights into how different types of e-learning environments can impact student engagement levels, which can inform future development of online courses to better support active learning strategies.

## Summary

The study titled "Students Behavioural Analysis in an Online Learning Environment Using Data Mining" aimed to use Educational Data Mining (EDM) techniques to conduct a quantitative analysis of 412 students' interaction with an e-learning system through instructor-led non-graded and graded courses. The research was conducted to establish guidelines for a series of online short courses for the students. The students' access behaviour in the e-learning system was analysed, and they were grouped into clusters using K-Means clustering method according to their course access log records. The results showed that more than 40% of the student group were passive online learners in both graded and non-graded learning environments. Additionally, the study found that the difference in learning environments could change the online access behaviour of a student group. Clustering divided the student population into five access groups based on their course access behaviour, with the least access group (NG-41% and G-42%) and highest access group (NG-9% and G-5%) being identified very clearly due to their distinct variation from other groups. This research provides valuable insights into how different types of e-learning environments can impact student engagement levels, which can inform future development of online courses to better support active learning strategies.