A multi-agent-based approach for community detection using association rules

In recent years, community detection has emerged as an important field of research, exerting a profound influence on various domains such as Social networks, Recommender systems, Citation networks, and Enterprise network. Acknowledging the profound implications of this development, we introduce a novel approach integrating a data mining technique, leveraging topical attributes of a network’s components. This approach seamlessly integrates with Social Network Analysis, within a multi-agent architecture composing four distinct hierarchical levels. In this paper, we present a novel approach for community detection that redirects the focus from traditional topological properties to topical properties of nodes and edges. This topical analysis perspective, often-neglected, constitutes the core of the proposed three-step methodology. We leverage the power of association rule mining using the Apriori algorithm as the initial step, extracting valuable insights from the network. Subsequently, we meticulously select meaningful rules, preparing them for the final stage where the proposed algorithm execution identifies both overlapped and non-overlapped communities within the network. To evaluate the effectiveness of our multi-agent system approach, we conducted tests on several real-world social networks, and performed comparisons with six traditional methods, thereby confirming the foundations of our approach.