Overlapping community detection in social networks with multi objective social based metaheuristic optimization

Parallel to growth of the Internet, social networks have become more attractive as a research topic in many different disciplines and many real systems can be denoted as a complex network. A common feature of complex network is community structure, groups of nodes in the network that are more densely connected internally than with the rest of the network. Identifying major clusters and community structures allow us to expose organizational principles in complex network such as web graphs and biological networks. Generally, it has been shown that communities are usually overlapping. Overlap is one of the characteristics of social networks, in which a person may belong to more than one social group. In recent years, overlapping community detection has attracted a lot of attention in the area of social networks applications. Many methods have been developed to solve overlapping community detection problem, using different tools and techniques. This thesis study proposes a multi-objective approach social based metaheuristic algorithm, Parliamentary Optimization Algorithm (POA), with the aim to acquire a better solution to overlapping community detection problems. The proposed algorithm optimized two objective functions, the modularity and internal density. The experimental results on synthetic and real world complex networks show that the multi-objective community detection algorithm provides beneficial method for discovering overlapping community problem. Key Words: Social Networks, Overlapping Community Detection, Multi-Objective Optimization, Parliamentary Optimization Algorithm.