Research on Network Public Opinion Events of COVID-19’s Post-epidemic Period Based on Topic Model and Community Detection Algorithm
摘要
COVID-19 has brought lots of network public opinion incidents. It is of great significance to study the characteristics of network public opinion events in the post-epidemic period and to guide public opinion in a timely and effective manner in order to maintain social stability. This paper selects Xi’an “pregnant woman’s miscarriage” incident during the post-epidemic period, and collects 21,767 related original Sina Weibo posts. The topic characteristics of the incident from different categories of users are analysed through topic models and community detection algorithms. It is found that during the post-epidemic period, officially certified users mainly released epidemic information and epidemic prevention measures, and published less posts related to public opinion events. Personally certified users have completely become users of information transmission, and their published content is highly consistent with officially certified users. Non-certified users actively expressed their emotions and opinions.