A risky large group emergency decision-making method based on topic sentiment analysis. (1st June 2022)

• Record Type: Journal Article
• Authors: Cao, Jing; Xu, Xuanhua; Yin, Xuanpeng; Pan, Bin
• Is Part Of: Expert systems with applications. Volume 195(2022)
• Publication Date: 2022-06-01
• Subjects: Topic sentiment analysis -- Large group -- Risky emergency decision; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.116527
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A novel method is proposed for public intuition fuzzy attribute preference. Large group decision risk measure based on credibility is proposed. A risk-consensus control mechanism to achieve high consensus and low risk is constructed. A risky large group emergency decision-making method is proposed. Abstract: This study proposes a decision-making method based on topic sentiment analysis to address the problem of completely data-driven attribute information acquisition and risk control of the intuitionistic fuzzy preference in large group emergency decision-making. First, Latent Dirichlet Allocation (LDA) topic mining is applied to rank public topics and construct an emergency sentiment dictionary for topic sentiment analysis. The attribute system structure and weight information of large group emergency decision-making can be obtained by transforming the high-concern topic sentiment value. Second, with the public attention attribute and public attribute preference as references for large group emergency decision-making, risk measurement under the intuitionistic fuzzy preference model is based on risk credibility. The risk–consensus feedback mechanism of large group emergency decision-making is designed to obtain the high-consensus and low-risk alternative. Finally, the applicability and effectiveness of the method are demonstrated using a case study involving a serious explosion accident.