A social trust network-based classification consensus decision-making method with incomplete information: cross-classification adjustment perspective

The consensus decision-making problem based on classification requires placing alternatives in a predetermined category in a specific order, occupying an important position in group decision-making. To achieve a high level of group identification with the output results, the current research primarily focuses on modifying expert evaluation opinions to indirectly adjust the classification of alternatives, which may result in a significant deviation between the revised and initial opinions. Consequently, this paper constructs a classification consensus decision method with incomplete information from the perspective of cross-classification adjustment and social network analysis technology. Firstly, the node strength in the PageRank algorithm is used to acquire the weight of experts, and incomplete information is supplemented based on social trust network and opinion evolution. Secondly, the classification threshold model of the maximum group consensus is established, and the unified classification threshold of alternatives is calculated. In addition, the consensus-reaching process is achieved through the optimization model of cross-classification minimum adjustment, which directly adjusts the classification of the alternatives and avoids excessive modification of opinions. Further, taking the rating of green tourist scenic area buildings as an example, the applicability of the proposed method is tested. Ultimately, the efficacy and advantage of the presented approach are demonstrated via sensitivity analysis and contrast with current methodologies.