A large-scale group decision-making method based on improved affinity propagation algorithm and adjustable minimum-cost consensus model in social networks

The rapid development of information technology has made social network large-scale group decision-making (SN-LSGDM) a focus of the field of decision science. Clustering and consensus-reaching process (CRP) are widely used methods in SN-LSGDM. In this paper, we propose an improved affinity propagation (AP) clustering algorithm that fully consider the trust and similarity attributes to obtain clustering results that are more in line with the expert preferences. Furthermore, we propose an adjustable minimum-cost consensus (MCC) model that considers trust-polymerization degree, which takes into account variations in expert weights and cluster diversity. And the cuckoo search (CS) algorithm is utilized to solve the model. Finally, the applicability and advantages of the proposed methods are demonstrated through a case and comparative analysis.