Network visualization algorithms to evaluate students in online discussion forums: A simulation study

Abstract

The purpose of this study is to detect at-risk students in online discussion forums in the platform Moodle. In this context, this paper presents a simulation study with a large database centralized on 4000 learners and 117988 interactions to evaluate students. To achieve our goal, we are used Gephi as a social network learning analytics tool to visualize the learners social network graphs and to implement three algorithms of layout and clustering to identify the learning community in order to predict the students' status (At-risk or safe). Finally, we discussed the result of each algorithm to improve the best one.