Identifying Student Communities in Blended Courses

TL;DR

This paper explores how students form communities in blended courses through online forum interactions, using community detection algorithms to analyze social networks and their correlation with student grades.

Contribution

It demonstrates that standard community detection algorithms can effectively identify student communities and reveals a significant correlation between peer groups and academic performance.

Findings

Students can be grouped into communities based on forum interactions.

Peer groupings are significantly correlated with students' grades.

Community detection algorithms are effective in educational social network analysis.

Abstract

Blended courses have become the norm in post-secondary education. Universities use large-scale learning management systems to manage class content. Instructors deliver readings, lectures, and office hours online; students use intelligent tutors, web forums, and online submission systems; and classes communicate via web forums. These online tools allow students to form new social networks or bring social relationships online. They also allow us to collect data on students' social relationships. In this paper we report on our research on community formation in blended courses based on online forum interactions. We found that it was possible to group students into communities using standard community detection algorithms via their posts and reply structure and that the students' grades are significantly correlated with their closest peers.