Detection of Social Groups in Class by Affinity Propagation

Abstract

The social groups often represent the groups within which are dense connections and between which are sparse connections. The social groups are actually the clusters. In this paper, we propose a simple but powerful method to combine the content and link information of the social network in the class, and analyze the results of different graph clustering algorithms, our experimental result shows that social groups detection by Affinity Propagation algorithm outperforms than the other clustering algorithms. In addition, we analyze the centrality of the detected communities and find the groups detected can significantly help to improve the quality of the teaching and learning.