Multi-Perspective Analysis of Public Opinion Related to COVID-19
Based on Online Media
HUANG Xiaohui1,2, LU Yan1, TANG Xijin1,2
Author information+
1. Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190;
2. University of Chinese Academy of Sciences, Beijing 100190
COVID-19 which outbroke in early 2020, is the most
significant
public health emergency in recent years. Excavating the characteristic and evolution
tendency of social public opinion about medical supplies during the epidemic
period will help us understand the evolution of this emergency and the social
response mechanism. This study conducts research from the perspective of
topic evolution and event structure. Based on the ``mask" related news corpus,
this study uses the LDA topic model to dig some hot topics from the news
under different periods during the epidemic. Therefore, the relationship
and evolution path of some main topics, which are about the
social epidemic situation, social epidemic prevention, mask production and
supervision, and the import and export of mask, are analyzed. In view of the customs
seizures in the import and export of masks, this study builds a co-occurrence
keywords network based on the keywords in the events, learns the main four
types of seizure events, and obtains the relationship between the customs
and the seizure event keywords through the construction of the bipartite networks of custom-keywords.
HUANG Xiaohui, LU Yan, TANG Xijin.
Multi-Perspective Analysis of Public Opinion Related to COVID-19
Based on Online Media. Journal of Systems Science and Mathematical Sciences, 2021, 41(8): 2182-2198 https://doi.org/10.12341/jssms21042