Overlapping Community Detection in Directed Heterogeneous Social Network
In social networks, users and artifacts (documents, discussions or videos) can be modelled as directed bi-type heterogeneous networks. Most existing works for community detection is either with undirected links or in homogeneous networks. In this paper, we propose an efficient algorithm OcdRank (Overlapping Community Detection and Ranking), which combines overlapping community detection and community-member ranking together in directed heterogeneous social network. The algorithm has low time complexity and supports incremental update. Experiments show that our method can detect better community structures as compared to other existing community detection methods.
KeywordsCommunity detection Directed heterogeneous social network Ranking
Unable to display preview. Download preview PDF.
- 1.Sun, Y., Han, J., Zhao, P., Yin, Z., Cheng, H., Wu, T.: Rankclus: integrating clustering with ranking for heterogeneous information network analysis. In: Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology, pp. 565–576. ACM (2009)Google Scholar
- 4.Yang, J., Leskovec, J.: Overlapping community detection at scale: a nonnegative matrix factorization approach. In: Proceedings of the Sixth ACM International Conference on Web Search and Data Mining, pp. 587–596. ACM (2013)Google Scholar
- 5.Yang, J., McAuley, J., Leskovec, J.: Detecting cohesive and 2-mode communities indirected and undirected networks. In: Proceedings of the 7th ACM International Conference on Web Search and Data Mining, pp. 323–332. ACM (2014)Google Scholar