Innovative Integration of Q-learning in BSO Algorithm for Adaptive Community Detection in Social Networks

Community detection in social networks remains a challenging yet crucial task in social network analysis, offering insights into the underlying structures and dynamics of social systems. This study introduces QB-COM, a novel integration of reinforcement learning using Q-learning with Brain Storm Optimization algorithm (BSO), tailored for effective community detection. The proposed approach’s design is distinguished by its utilization of diverse data sources, including the network structure, evolving knowledge from BSO, and Q-learning intelligence, all intended to enhance solution generation and guide the search process adeptly. A thorough comparative analysis is carried out to assess the effectiveness of our algorithm, covering a range of meta-heuristics and heuristics used in community detection. This analysis utilizes diverse real-world networks and evaluation techniques. The results demonstrate QB-COM’s superior performance in accurately identifying true community structures within social networks.