Application of personalized individual semantics in MAGDM with preference information

Subjective and objective evaluations are often utilized simultaneously in Multi-Attribute Group Decision Making (MAGDM) problems. Decision makers’ different understanding of linguistic terms, i.e., personalized individual semantics, may influence decision making results. In this study, we propose a novel MAGDM model to deal with these problems based on two types of preference information: an objective multi-attribute linguistic decision matrix and subjective alternative rankings. In the first stage, we introduce a consistency-driven model to obtain the personalized interval numerical scales associated with each linguistic term and attribute weights. In the second stage, we introduce dynamic personalized individual semantics to maximize consensus by minimizing the discrepancy between individual opinions and collective opinion. The optimal alternative is then determined based on overall scores of the alternatives. We finally apply the proposed model in the selection of new energy vehicles, and conduct simulation experiments and comparative analysis. The results show that considering personalized individual semantics and weights of the decision makers brings much benefit for consensus reaching process in group decision making. A high group consensus level can be reached in this model, and the computational complexity of this model is acceptable.