Discrete Group Search Optimizer for community detection in multidimensional social network

Multidimensionality is a distinctive aspect of real world social networks. Multidimensional social networks appeared as a result of that most social media sites such as Facebook, Twitter, and YouTube enable people to interact with each other through different social activities, reflecting different kinds of relationships between them. Recently, studying community structures hidden in multidimensional social networks has attracted a lot of attention. When dealing with these networks, the concept of community detection problem changes to be the discovery of the shared group structure across all network dimensions, such that members in the same group are tightly connected with each other, but are loosely connected with others outside the group. Studies in community detection topic have traditionally focused on networks that represent one type of interactions or one type of relationships between network entities. In this paper, we propose Discrete Group Search Optimizer (DGSO-MDNet) to solve the community detection problem in Multidimensional social networks, without any prior knowledge about the number of communities. The method aims to find community structure that maximizes multi-slice modularity, as an objective function. The proposed DGSO-MDNet algorithm adopts the locus-based adjacency representation and several discrete operators. Experiments on synthetic and real life networks show the capability of the proposed algorithm to successfully detect the structure hidden within these networks compared with other high performance algorithms in the literature.