Mining relationships in learning‐oriented social networks

Abstract The widespread use of computing and communications technologies has enabled the popularity of social networks oriented to learn. In this work, we study the nature and strength of associations between students using an online social network embedded in a learning management system. With datasets from three offerings of the same course, we mined the sequences of questions and answers posted by the students to identify structural properties of the social graph, patterns of collaboration among students and factors influencing the final academic achievements. The results show some hints to understand how users react to incentives in online social learning systems, useful for instance to measure the effectiveness of the learning tasks based on the patterns of students’ participation in the platform and adapt their design, or as early predictors of academic performance.