Public sentiments arising from public opinion communication pose a serious psychological risk to public and interfere the communication of nonpharmacological intervention information during the COVID-19 pandemic. Problems caused by public sentiments need to be timely addressed and resolved to support public opinion management.
This study aims to investigate the quantified multidimensional public sentiments characteristics for helping solve the public sentiments issues and strengthen public opinion management.
This study collected the user interaction data from the Weibo platform, including 73,604 Weibo posts and 1,811,703 Weibo comments. Deep learning based on pretraining model, topics clustering and correlation analysis were used to conduct quantitative analysis on time series characteristics, content-based characteristics and audience response characteristics of public sentiments in public opinion during the pandemic.
The research findings were as follows: first, public sentiments erupted after priming, and the time series of public sentiments had window periods. Second, public sentiments were related to public discussion topics. The more negative the audience sentiments were, the more deeply the public participated in public discussions. Third, audience sentiments were independent of Weibo posts and user attributes, the steering role of opinion leaders was invalid in changing audience sentiments.
Since the COVID-19 pandemic, there has been an increasing demand for public opinion management on social media. Our study on the quantified multidimensional public sentiments characteristics is one of the methodological contributions to reinforce public opinion management from a practical perspective.