Multi-attribute group decision-making considering opinion dynamics

Multi-attribute group decision-making (MAGDM) is a complicated cognitive process that involves evaluation of opinion expression, information fusion, and analysis of multi-source uncertainties. In the incipient stage of MAGDM, decision makers (DMs) express their opinions on alternatives for each attribute and tend to interact with others. Despite the opinions of DMs are dynamically evolved, the traditional information fusion techniques are always relying on the data acquired at a static decision-making time point, which leads to the loss of information. In this study, we introduce a novel MAGDM method considering opinion dynamics, which employs the 2-tuple linguistic model for the representation of linguistic judgements and the technique for order preference by similarity to an ideal solution (TOPSIS) as the decision-making framework, to reduce the loss of information from the dimension of opinion formation. Moreover, a modified opinion dynamics model is as well as developed by extending the hypothesis of bounded confidence, where the opinion similarity, the credibility of DMs, and the human bounded rationality are collectively regarded as influential factors within the process of opinion evolution. Subsequently, three simulations are carried out to verify the feasibility of the extended bounded confidence model. And finally, a case study of supplier selection, as a typical MAGDM problem, is implemented and a comparison analysis is conducted to demonstrate the rationality of the proposed method.