ACFC: ant colony with fuzzy clustering algorithm for community detection in social networks. (14th May 2019)

• Record Type: Journal Article
• Authors: Noveiri, Ehsan; Naderan, Marjan; Alavi, Seyed Enayatollah
• Is Part Of: International journal of ad hoc and ubiquitous computing. Volume 31:Number 1(2019)
• Page Start: 36
• Page End: 48
• Publication Date: 2019-05-14
• Subjects: community detection -- social networks -- ant colony -- Q modularity -- fuzzy clustering; Ubiquitous computing -- Periodicals; Embedded computer systems -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; Wireless communication systems -- Periodicals; Computer architecture -- Periodicals; 004.2
• Languages: English
• ISSNs: 1743-8225

Abstract

In this paper, we suggest a bipartite algorithm, based on ant colony with fuzzy clustering, namely ACFC, for finding communities in social networks. First, we use artificial ants to traverse the network modelled by a graph based on a set of rules to find a 'good region' of edges. Next, we construct the communities after which local optimisation methods are used to further improve the solution quality. Finally, we use the fuzzy C-means (FCM) clustering algorithm to fine tune the result. In our method ants are only used to identify good regions of the search space and construction methods are used to build the final solution. Experimental results on several synthetic graphs and four real world social networks compared to six other well known methods show that our ACFC algorithm is very competitive against current state-of-the-art techniques for community detection and it is more accurate than existing algorithms as it performs well across many different types of networks.