A novel utilite<acute accent>s additives-based social network group decision-making method considering preference consistency

Nowadays, social networks and mobile internet have become prominent features of daily life, leading to increasingly interconnected relationships among decision-makers (DMs). The social network group decision- making (SNGDM) method uses social network analysis technology to consider the impact of social trust relationships among DMs on decision results during the decision-making process. The Utilite<acute accent>s Additives (UTA) method can infer the DMs' preference structure based on the partial preference information. This method effectively resolves the consensus problem in SNGDM by utilizing the DMs' preference structure. This paper proposes a novel SNGDM method based on the UTA method that considers the consistency of preference information provided by DMs in the form of pairwise comparisons. Firstly, since the trust relationship between DMs is asymmetric and DM's opinions are usually different, a new preference conflict degree between DMs in SNGDM is defined. Then, to consider the opinion differences and social trust relationship between DMs in the clustering process, a clustering method based on the preference conflict degree is proposed. Furthermore, to obtain the maximal subsets of consistent pairwise comparisons for each DM, we designed a simulation algorithm involving an optimization model to examine the pairwise comparisons provided by the DMs and to obtain the maximal subsets of consistent pairwise comparisons. Moreover, since using only preference information in the form of pairwise comparisons in the consensus reaching process (CRP) leads to a limited space for changes in DMs' opinions, a method for converting the opinions of DMs based on maximal subsets of consistent pairwise comparisons is proposed. This method transforms pairwise comparisons provided by DMs into fuzzy preference relations (FPRs). In addition, in the CRP, a method for adjusting the FPRs of DMs is proposed. Finally, a case study is conducted using real data on new energy vehicles from Autohome to illustrate the effectiveness of the proposed method.