<p>The detection of community structures in complex networks has garnered significant attention in recent years. Given its NP-hardness, numerous evolutionary optimization-based approaches have been proposed. However, there is still a need for improvement, since no previous method has been able to find the true community structure on all benchmark networks. In this paper, we propose a multi-objective approach based on the social-based algorithm (SBA). SBA is a hybrid of the imperialist competitive algorithm and the standard evolutionary algorithm. SBA has demonstrated remarkable performance in finding optimal solutions and can effectively identify correct community structures. In our method, instead of a single solution, a set of non-dominated solutions is produced, each representing a different compromise between the objective functions. To evaluate the performance of the proposed algorithm, various tests were conducted on synthetic and real-world datasets. The results of experiments on several social network benchmarks show up to a 57% improvement on benchmark networks compared to previous works. This indicates that the proposed algorithm performs well in community detection.</p>