Detecting Overlapping Communities in Social Networks with Voronoi and Tolerance Rough Sets
In this work, we propose a novel method based on Voronoi diagrams and tolerance rough set method (TRSM) to detect overlapping communities. In the proposed Voronoi TRSM approach, a social network is represented as a graph. A Voronoi diagram is a partitioning of a plane into regions based on closeness to points in a specific set of sites (seeds). These seeds are used as a core for determining tolerance classes. The upper approximation operator from TRSM is used to obtain overlapping nodes. We have experimented with three well-known real networks and compared with Fuzzy-Rough and a Matrix Factorization-based approach. The results with proposed Voronoi TRSM approach are promising in terms of the extended modularity measure and the dense communities measure.
KeywordsCommunity detection Density-based clustering Social networks Soft computing Tolerance rough sets Voronoi diagram
- 2.Campigotto, R., Céspedes, P.C., Guillaume, J.L.: A generalized and adaptive method for community detection. ArXiv preprint arXiv:1406.2518 (2014)
- 10.Newman, M.E.J., Girvan, M.: Finding and evaluating community structure in networks (2004). http://arxiv.org/pdf/cond-mat/0308217v1:PDF
- 19.Whang, J.J., Gleich, D.F., Dhillon, I.S.: Overlapping community detection using seed set expansion. In: Proceedings of ACM International Conference onIinformation & Knowledge Management, pp. 2099–2108 (2013)Google Scholar