Multi-view Community Detection in Facebook Public Pages

Abstract

Community detection in social networks is widely studied because of its importance in uncovering how people connect and interact. However, little attention has been given to community structure in Facebook public pages. In this study, we investigate the community detection problem in Facebook newsgroup pages. In particular, to deal with the diversity of user activities, we apply multi-view clustering to integrate different views, for example, likes on posts and likes on comments. In this study, we explore the community structure in not only a given single page but across multiple pages. The results show that our method can effectively reduce isolates and improve the quality of community structure.

Multidimensional community discovering in heterogeneous social networks

“…Also, authors in Xin et al 39 have used the modularity measure aiming to detect communities in Facebook newsgroup pages based on user activities. However, the main limitation of this approach is that the overlapping communities cannot be discovered.…”

“…Thus, the aggregation process of graphs could lose the effective heterogeneity of the network dimensions. In this thesis, we attempt to address the problem of how to efficiently cluster the entities in a network taking into account all types of relations among them. Most discovering multidimensional community approaches 14,31,39 on different network structures have especially focused on the topological properties of social networks, ignoring the semantic information (ie, shared properties between vertices). However, in many applications, the social networks can be presented to communities that involve a set of users' attributes that are used to detect more effective communities.…”