Pu ZHANG (张谱)

Disaster-related online public opinion develops rapidly, the actual situation is complex and volatile, and the public opinion environment should be regulated through appropriate guidance. 2021 Zhengzhou 7-20 extraordinary rainstorm and flooding disaster has attracted widespread public attention. In order to analyze the online public opinion triggered by extraordinary rainstorm disasters and propose targeted management measures so as to improve the comprehensive disaster reduction efficiency. This paper collected information about the "Zhengzhou rainstorm" posted on the Sina Weibo platform from July 11 to August 14, 2021. We analyzed the characteristics of related Weibo from two dimensions: sentiment analysis and thematic analysis. The results are as follows: Online public opinion will be generated rapidly and last for a long time; the different emotional colors change at different periods of the disaster; the focus of online public opinion discussion varies at different periods of the disaster. Given this result, the following suggestions are made: the cooperation level between departments should be improved, and an early warning mechanism for public opinion should be established so that once the relevant public opinion is generated, a quick response can be made; a relevant responsibility mechanism should be established to realize that a specific department is responsible for the handling of public opinion in the corresponding section, to realize a scientific and practical normalized control mechanism for public opinion; Relevant departments should improve the openness and transparency of appropriate handling methods, to establish a public opinion control and guidance mechanism. This study has specific significance for improving the level of governance of online public opinion caused by sudden natural disasters.

Sorting out the changing characteristics of online public opinion triggered by a series of events in the investigation and assessment of major natural disasters is of great practical significance for optimizing the work of disaster investigation and assessment, governing the ecology of online public opinion, and enhancing the effect of comprehensive disaster reduction. In this paper, we collected relevant comments from several official media accounts, such as People’s Daily, and evaluated their emotional color using a sentiment analysis method based on the BERT fine-tuning model. Furthermore, keyword co-occurrence semantic network theme analysis is conducted for texts presenting negative emotional overtones to assess the changes in public opinion hotspots. The impact of the relevant online public opinion characteristics and the release of the disaster investigation report on them was assessed in the context of the investigation report itself. Based on sorting out the characteristics of online public opinion on several related topics, targeted public opinion governance initiatives and relevant suggestions for improving the disaster investigation system are proposed. This paper is of positive significance for studying disaster public opinion and improving the effectiveness of emergency management of rainstorms and flooding disasters.