This paper analyzes the evolution of online public opinion during the initial COVID-19 outbreak in China using over 45 million Weibo posts from December 1, 2019, to April 30, 2020. A novel text emotion extraction method based on an emotional ontology dictionary was employed. The study reveals significant emotional fluctuations tied to holidays and key events like the announcement of human-to-human transmission and the Wuhan lockdown. The findings highlight the stronger emotional responses (especially fear) in major cities compared to surrounding areas and offer insights for public opinion monitoring during similar events.
