Multi-stage Internet public opinion risk grading analysis of public health emergencies: An empirical study on Microblog in COVID-19

• Published in: Information processing & management Vol. 59; no. 1; p. 102796
• Main Authors: Liu, Jun, Liu, Liyi, Tu, Yan, Li, Shixuan, Li, Zongmin
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.01.2022; Elsevier Science Ltd
• Subjects: AHPSort II-SW; Analytic hierarchy process; Coronaviruses; COVID-19; Decision making; Emergencies; Empirical analysis; Fuzzy systems; Internet; Internet public opinion; MCDM; Microblogs; Multiple criterion; Public health; Public health emergencies; Public opinion; Risk analysis; Risk assessment; Risk grading; Risk levels; Sensitivity analysis; Social networks; Stability analysis; Viral diseases; COVID-19; Risk grading; AHPSort II-SW; MCDM; Public health emergencies; Internet public opinion
• ISSN: 0306-4573; 1873-5371; 0306-4573
• DOI: 10.1016/j.ipm.2021.102796

In the period of Corona Virus Disease 2019 (COVID-19), millions of people participate in the discussion of COVID-19 on the Internet, which can easily trigger public opinion and threaten social stability. This paper creatively proposes a multi-stage risk grading model of Internet public opinion for public health emergencies. On the basis of general public opinion risk grading analysis, the model continuously pays attention to the risk level of Internet public opinion based on the time scale of regular or major information updates. This model combines Analytic Hierarchy Process Sort II (AHPSort II) and Swing Weighting (SW) methods and proposes a new Multi-Criteria Decision Making (MCDM) method – AHPSort II-SW. Intuitionistic fuzzy number and linguistic fuzzy number are introduced into the model to evaluate the criteria that cannot be quantified. The multi-stage model is tested using more than 2,000 textual data about COVID-19 collected from Microblog, a leading social media platform in China. Seven public opinion risk assessments were conducted from January 23 to April 8, 2020. The empirical results show that in the early COVID-19 outbreak, the risk of public opinion is more serious on macroscopic view. In details, the risk of public opinion decreases slowly with time, but the emergence of important events may still increase the risk of public opinion. The analysis results are in line with the actual situation and verify the effectiveness of the method. Comparative analysis indicates the improved method is proved to be superior and effective, sensitivity analysis confirms its stability. Finally, management suggestions was provided, this study contributes to the literature on public opinion risk assessment and provides implications for practice. •Risk grading of Internet public opinion is conducted in the context of COVID-19.•A multi-stage Internet public opinion grading risk evaluation model is established.•AHPSort II-SW method is proposed to grade the risk levels.•Effectiveness of the method is verified by empirical analysis of Microblog.