International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 National Conference on Advances in Engineering and Technology (AET- 29th March 2014) Maharishi Markandeshwar University 5 | Page A Comprehensive Review of Overlapping Community Detection Algorithms for Social Networks Ashish Kumar Singh 1 , Sapna Gambhir 2 1 (YMCA University of Science and Technology Email: ashwebdeveloper@gmail.com) 2 (YMCA University of Science and Technology Email: sapnagambhir@gmail.com) Abstract— Community structure is an interesting feature found in many social networks which signifies that there is intense interaction between some individuals. These communities have a tendency to overlap with each other as there are nodes that can belong to multiple communities simultaneously. Detection of such overlapping communities is a challenging task; it still remains a topic of interest for the researchers as it answers many questions about the behavior of the network and its operation as a function of its structure. This paper reviews overlapping community detection techniques proposed so far and points out their strengths and weaknesses. The paper also presents insightful characteristics and limitations of the existing state of art algorithms to solve the problem of overlapping community detection. Keywords—Overlapping Community detection, Online Social Networks, Complex Networks, Community Structure. I. INTRODUCTION Online social networks have become a primary means of communication nowadays; they attract a wide variety of audience. Nearly every person has a profile on Facebook, Google plus, Orkut, Twitter etc which are collectively termed as Social Networking Sites (SNS). People usually communicate to others via these SNS and this communication has attracted a lot of research focus in recent years under the domain named Social Network Analysis. A social network is a graphical representation of the communication among people, where people are represented as nodes and the edges between a pair of nodes represent some kind of communication between them. A very interesting feature in social networks is the formation of Communities. A community is a group of individuals in a social network who communicate more frequently with each other than with others outside the group. When a the social network is represented as a graph G (V, E), where V representing the individuals and E representing the connections among them, then a community C G such that the number of edges going outside from the vertices in C is far less than the number of edges with both vertices inside C. The detection of such communities is not trivial and is quite challenging as it is completely different from two similar and well studied problems in computer science namely Clustering and Graph Partitioning. The first most challenge in the domain of community detection is that there is no generally accepted definition of a community; still there are a large number of community detection algorithms available which produce effective results. Most of the community detection algorithms do not take in to account the overlapping between communities, which is a serious case in SNSs. Communities in social networks, tends to overlap with each other which means that a vertex which is a member of one community can also be a member of another community as shown in Fig 1. The idea of overlapping communities makes the problem of community detection tougher as the result of the algorithms would now be a Cover, a set of communities of which a vertex is a member. Most of the community detection algorithms start resulting in bad assignments of communities to vertices in the overlapping case as they generally merge two communities with dense overlaps into a single community. Fig 1: Illustration of overlapping communities, nodes shown in red color RESEARCH ARTICLE OPEN ACCESS