Social media has followed an exponential graph over the past few years with incorporating features which at one time seemed impossible. The social media has had an enduring effect on the thought process of the general populace. With the diverse nature of the population which take part in the daily chatting, tagging, posting and uploading on the virtual world, the study of such coalesce of communities. This paper aims at the mining and analysis of the communities with focus on the techniques

more »

... for the detection process. We discuss four methods of detection, beginning with the node-centric moving on to group centric, then to network centric and concluding with hierarchy centric method of detection. This paper also briefly discusses the applications of community detection in varied fields. Copy Right, IJAR, 2016,. All rights reserved. ...................................................................................................................... Introduction:- The past decade has witnessedthe rapid development of social networking sites which has empowered new ways of collaboration and communication. Social media also helps reshape business models, sway opinions and emotions, and opens up numerous possibilities to study human interaction and collective behavior in an unparalleled scale [2] . Hence, study of social network is of great importance in sociology, biology and computer science. Social network analysis is the mapping and measuring of relationships and flows between people, groups, organizations, computers, URLs, and other connected information/knowledge entities. Social network analysis provides both a visual and a mathematical analysis of human relationships. A valuable tool in the analysis of large complex networks is community detection. Community Detection:- Community is formed by individuals such that those within a group interact with each other more frequently than with those outside the group[1]. There are two types of communities in social networks-Explicit groups which are formed as a result of conscious human decision. Implicit groups which emerge from interactions and activities of users. Often communities are defined with respect to a graph, which consists of set of objects called vertices (V) and their relations called as edges (E). Therefore, according to computer science, community detection is identifying a group of vertices that are more densely connected to each other than the rest of the network [1]. Figure below shows a network with three communities. Node-Centric Community Detection:- Node-Centric community detection is commonly used in traditional social network analysis. In this type of community detection, each node in a group (community) satisfies certain properties. Complete Mutuality-To satisfy this criterion cliques in a graph are found. A clique is an ideal cohesive subgroup. It is a maximum complete sub graph in which all nodes are adjacent to each other [2] .To find maximum clique in large network recursive pruning procedure is applied. For a clique of size k, each node in the clique should maintain at least degree k − 1. Hence, those nodes with degree less than k − 1 cannot be included in the maximum clique, thus can be pruned [2] . The procedure is as follows  A sub-network is sampled from the given network. A clique in the sub-network can be found in a greedy manner, e.g., expanding a clique by adding an adjacent node with the highest degree.  The maximum clique found on the sub-network (say, it contains k nodes) serves as the lower bound for pruning. That is, the maximum clique in the original network should contain at least k members. Hence, in order to find a clique of size larger than k, the nodes with degree less than or equal to k − 1, in conjunction with their connections can be removed from future consideration. As social media networks follow a power law distribution for node degrees, i.e., the majority of nodes have a low degree, this pruning strategy can reduce the network size significantly.  This process is repeated until the original network is shrunk into a reasonable size and the maximum clique can either be identified directly, or have already been identified in one of the sub-networks. [2] 1502 Conclusion:- In this paper, we discussed the concept of graph-based community and community detection. Methods of community detection was explained using appropriate examples -Node centric community detection, group centric community detection, network centric community detection and hierarchy centric community detection. We also discussed applications of community detection-detection of suspicious events, recommendation systems, link prediction, detection of terrorist groups in social network and anomaly detection.