Random graph generator for leader and community detection in networks

In complex network analyses, mainly in social networks, the detection of communities is an important source of information for revealing an internal organization of nodes. On the other hand, if the network reveals a leadership structure, it is possible to understand the mechanisms of information dissemination on it. The detection of leaders and communities is a big challenge depending on the complexity level of the network. In the literature, there are some metaheuristic algorithms for detecting leaders and communities based on pattern recognition on the graph associated with the network. In this paper, we developed a random graph system to generate a synthetic network instance with leader and community structures that define a ground truth. We compare this ground truth to determine the performance of the algorithms LCDA 1 and LCDA 2 for detecting leaders and communities. The results corroborate that the benchmarking system would help in selecting useful configurations for practical applications.