Managing Group Confidence and Consensus in Intuitionistic Fuzzy Large Group Decision-Making Based on Social Media Data Mining

Social media has played an increasingly important role in decision-making for public issues, and the concerns of the public, an important reference for which is in social media, have increasingly attracted attention in the field of large group decision-making (LGDM). On this basis, this paper presents a novel LGDM model based on social media data mining to manage group confidence and consensus. The proposed model comprises three processes, namely (1) term frequency-inverse document frequency (TF-IDF) keyword extraction, (2) the management of group confidence and consensus, (3) the selection process. In the first process, natural language processing (NLP) technology is used to extract keywords from social media data, and the topic of concern by the public is regarded as the evaluation criteria of decision-making alternatives. Then the TF-IDF weighting method is used to determine the weight of each criterion. Regarding the second process, the concept of the confidence correlation degree is defined, and a novel confidence-consensus model is proposed to manage group confidence and consensus. In the group consensus-reaching process (CRP), if the most incompatible cluster (or subgroup) has a higher confidence correlation degree regarding its own opinions, then it is advised that the weight of the cluster be reduced; if the most incompatible cluster has a lower confidence correlation degree regarding its own opinions, then it is advised that the cluster changes its opinions. In the third process, the weights of the criteria determined by the TF-IDF measure are aggregated, and the decision results are obtained. A case study is provided to illustrate the application of the proposed method, and the results of a comparative analysis reveal the features and advantages of this model.