Fusion social network and regret theory for a consensus model with minority opinions in large-scale group decision making

The change in data structure and social paradigm have promoted the rapid development of decision sciences. Large-scale group decision making (LSGDM) has gained widespread attention as an effective approach for addressing complex decision making issues. However, a common challenge in LSGDM scenarios is how to appropriately deal with minority and non-consensus opinions of decision makers, since they have different backgrounds and expertise. In view of this issue, this paper establishes an LSGDM model with minority opinions handling (MOH) by fusing social network (SN) and regret theory (RT), referred to as the MOH-RTSN-LSGDM model. Notably, the model can effectively identify and manage minority opinions and facilitate the formation of group consensus. More specifically, this work first introduces a collaborative index based on opinion similarity and trust relationships, and uses it to guide the community detection and decision making process in SN. Further, considering that minority opinions usually are characterized by low consistency and small size but high authority, this study designed an objective mechanism to detect and manage minority opinions. In addition, a personalized consensus feedback strategy based on RT and SN is proposed by analyzing the psychological characteristics of regret and social influence of decision makers. Finally, in order to verify the reliability and superiority of the proposed model, a sensitivity analysis of the relevant parameters was conducted and compared with existing models of the same type. The experimental results show that the constructed MOHRTSN-LSGDM model has significant potential and advantages in dealing with minority opinions and irrational behaviors for LSGDM problems.