Multiplex Community Detection in Social Networks Using a Chaos‐Based Hybrid Evolutionary Approach

Abstract

Network analysis involves using graph theory to understand networks. This knowledge is valuable across various disciplines like marketing, management, epidemiology, homeland security, and psychology. An essential task within network analysis is deciphering the structure of complex networks including technological, informational, biological, and social networks. Understanding this structure is crucial for comprehending network performance and organization, shedding light on their underlying structure and potential functions. Community structure detection aims to identify clusters of nodes with high internal link density and low external link density. While there has been extensive research on community structure detection in single‐layer networks, the development of methods for detecting community structure in multilayer networks is still in its nascent stages. In this paper, a new method, namely, IGA‐MCD, has been proposed to tackle the problem of community structure detection in multiplex networks. IGA‐MCD consists of two general phases: flattening and community structure detection. In the flattening phase, the input multiplex network is converted to a weighted monoplex network. In the community structure detection phase, the community structure of the resulting weighted monoplex network is determined using the Improved Genetic Algorithm (IGA). The main aspects that differentiate IGA from other algorithms presented in the literature are as follows: (a) instead of randomly generating the initial population, it is smartly generated using the concept of diffusion. This makes the algorithm converge faster. (b) A dedicated local search is employed at the end of each cycle of the algorithm. This causes the algorithm to come up with better new solutions around the currently found solutions. (c) In the algorithm process, chaotic numbers are used instead of random numbers. This ensures that the diversity of the population is preserved, and the algorithm does not get stuck in the local optimum. Experiments on the various benchmark networks indicate that IGA‐MCD outperforms state‐of‐the‐art algorithms.