AUTHOR=Pi Zhongxu , Feng Hao 

TITLE=The evolution of public sentiment toward government management of emergencies: Social media analytics

JOURNAL=Frontiers in Ecology and Evolution

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/ecology-and-evolution/articles/10.3389/fevo.2022.1026175

DOI=10.3389/fevo.2022.1026175

ISSN=2296-701X

ABSTRACT=At present, social media has become the main media of network public opinion (PO) dissemination. By analyzing the emotional development trend of public emergencies, we can explore the evolution law of PO and identify potential risks, which provides decision support for government management guidance and control. Firstly, based on the concept of critical point in complex system, this paper establishes the evolution model of public sentiment (PS) under public emergencies, and proposes an algorithm to identify the critical point of PS based on microblog data analysis; In addition, the BC-BIRCH algorithm is used to construct the topic clustering model of public emergencies, which improves the effect of topic discovery by merging multiple topic clusters. The evolution of public emergencies is analyzed by calculating the emotional heat value of different topic events. Finally, the experimental results show that the emotion of netizens fluctuates greatly in the initial stage of PO under different themes. The method used in this paper has achieved good results in topic clustering, critical point prediction and PO evolution analysis of public emergencies. The main contribution of this paper is to analyze the evolution of the internal mechanism of public sentiment, and to identify and predict the key nodes such as the outbreak and extinction of netizens' sentiment based on data-driven methods, so as to provide the basis and support for the government and related media as the main body of prevention and control to respond in advance and guide timely.