Simultaneous community discovery and user interests extraction in social network based on probabilistic model. (1st January 2014)

• Record Type: Journal Article
• Authors: Bi, Juan; Qin, Zhiguang; Xiong, Hu; Huang, Jia
• Is Part Of: International journal of intelligent information and database systems. Volume 8:Number 3(2014)
• Page Start: 260
• Page End: 279
• Publication Date: 2014-01-01
• Subjects: community discovery -- latent dirichlet allocation -- LDA -- probabilistic generative model -- social networks; Database management -- Computer programs -- Periodicals; Information retrieval -- Computer programs -- Periodicals; Information storage and retrieval systems -- Computer programs -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligent agents (Computer software) -- Periodicals; 006.33
• DOI: 10.1504/IJIIDS.2014.066637
• Languages: English
• ISSNs: 1751-5858

Abstract

This article addresses the problem of discovering latent communities and topics simultaneously in social network. With the advent of online social networking, the automatic discovering communities is vital for understanding the cooperation and interaction patterns of users in these social networks. In this paper, we propose probabilistic generative models to detect latent communities by incorporating both the information of relationships and the textural content. Different from previous work, topics and user community memberships cannot be generated independently, but have a greater degree of correspondence between them. We assume that community membership is dependent on the user and a subset of topics which the user is really interested in. Furthermore, the heterogeneous relationship strengths were used to improve community discovery. These models treat community and topic as different latent variables but interdependent with each other and mutually reinforcing. Experiments on real-world dataset have shown that our models have the capability to detect well-connected and topically meaningful communities.