Towards the Identification of Student Learning Communities using Centrality

Emergence of universities towards “digital university” has already been present for some years. The use of digital is largely developed to ensure a good quality of education. Universities therefore use large-scale learning management systems to manage the interaction between learners and teachers. Teachers can provide online training and educational materials for students following their classes and courses, monitor their participation and evaluate their performance. Students can use interactive features such as discussion threads, videoconferences, and discussion forums. These online tools make it possible to create new social networks or connect online social interactions. This will allow us to understand the structure of this complex network and extract useful information. In this article, we report our research on the detection of student learning communities based on learner activity. We found that it is possible to group students in communities through their messages and response structures using standard community detection algorithms. Also, that their behaviours can be strongly correlated with their closest peers who belong to the same community.