A public and large-scale expert information fusion method and its application: Mining public opinion via sentiment analysis and measuring public dynamic reliability

Abstract With the rapid development of social media, reliable information released by the public on social media can provide important decision-making support. Therefore, the consideration of the public as another decision-making body participating in large-scale group decision-making (LSGDM) problems has become an extensively researched topic. However, the participation of the public as a decision-making body with decision-making experts faces several issues, such as the acquisition of public opinion, the reliability of public opinion, the integration of public and expert opinions, etc. Given this, this paper proposes a public and large-scale expert information fusion method that considers public dynamic reliability via sentiment analysis and intuitionistic fuzzy number (IFN) expressions. First, sentiment analysis technology is used to process public social media data and obtain IFNs as the opinions of the public decision-making body. Second, the concept of public dynamic reliability is defined to measure the degree of integration of public opinion. Third, a novel information entropy measure of IFNs is proposed, and a new method is introduced to determine the criteria weights under the two different decision-making bodies. Finally, an optimization model that considers the consensus levels of expert subgroups is proposed to determine the weights of different decision-making bodies. The public and expert opinions are then aggregated to obtain collective decision-making information. A case study is proposed to illustrate the application of the proposed method, and the comparative analysis reveals the features and advantages of this model.