User community discovery from multi-relational networks

Zhongfeng Zhang, Qiudan Li, Daniel Zeng, Heng Gao

Research output: Contribution to journalArticle

36 Scopus citations

Abstract

Online social network services (SNS) have been experiencing rapid growth in recent years. SNS enable users to identify other users with common interests, exchange their opinions, and establish forums for communication, and so on. Discovering densely connected user communities from social networks has become one of the major challenges, to help understand the structural properties of SNS and improve user-oriented services such as identification of influential users and automated recommendations. Previous work on community discovery has treated user friendship networks and user-generated contents separately. We hypothesize that these two types of information can be fruitfully integrated and propose a unified framework for user community discovery in online social networks. This framework combines the author-topic (AT) model with user friendship network analysis. We empirically show that this approach is capable of discovering interesting user communities using two real-world datasets.

Original languageEnglish (US)
Pages (from-to)870-879
Number of pages10
JournalDecision Support Systems
Volume54
Issue number2
DOIs
StatePublished - Jan 1 2013

Keywords

  • Author topic model
  • Community discovery
  • Multi-relational network
  • Non-negative matrix factorization

ASJC Scopus subject areas

  • Management Information Systems
  • Information Systems
  • Developmental and Educational Psychology
  • Arts and Humanities (miscellaneous)
  • Information Systems and Management

Fingerprint Dive into the research topics of 'User community discovery from multi-relational networks'. Together they form a unique fingerprint.

  • Cite this