Detecting community structures in weighted social networks based on genetic algorithm

Detecting communities is one of the important research directions in social network analysis currently. However, complexity and size of real world networks makes it practically impossible to develop a unique mechanism for finding communities, which will show satisfactory results in almost any network. In this paper, we have proposed a genetic method that can detect communities in social networks extracted from the Web. Advantage of the method is that we can set an upper boundary to the number of clusters in the network. This is achieved by means of information centrality. When we choose top [Formula: see text] nodes, which shall be used in the algorithm iteration, we know that the number of clusters in the network is less that the number [Formula: see text]. Yet another advantage of the method is that it is fast with computational complexity equals [Formula: see text]. This is a huge improvement compared to most algorithms with convergence speed [Formula: see text]. The experimental results verify the superior performance of the proposed method.