Abstract
As of March 7, 2020, the global number of confirmed cases of novel coronavirus disease (COVID-19) surpassed 100,000, covering more than 100 countries (World Health Organization, 2020a). As a growing number of confirmed cases of infections was reported, the Chinese government took prompt response measures to combat the virus. On January 9, 2020, the causative agent of this pneumonia was initially confirmed as a novel coronavirus. On January 20, the National Health Commission of the People’s Republic of China (NHFPC) classified COVID-19 as a category B infectious disease based on the Law on Prevention and Control of Infectious Diseases and took preventive and control measures for category A infectious diseases. On January 23, Wuhan City was put under lockdown to contain the outbreak. On February 2, Huoshenshan Hospital in Wuhan, a 1,000-bed makeshift hospital for treating infected patients, was built just in 10 days. On February 8, China completed work on Leishenshan Hospital, another 1,600-bed makeshift hospital in Wuhan. As of February 10, the number of confirmed cases of COVID-19 in China surpassed 42,000. In the early stages of the COVID-19 outbreak in China, there was a fierce race between the growth of patients and the allocation of medical resources. Coinciding with the Lunar New Year Festival, COVID-19 not only disrupted people's normal lives, it also attracted great attention from all circles of society. In these circumstances, billions of people eagerly acquired information about COVID-19 through social media. Topics and sentiments related to COVID-19 spread rapidly, thus influencing public behaviour during the epidemic. Analyses of public opinion are important for improving emergency responses, enhancing sentiment awareness, and supporting decision making. This study aimed to identify public opinion during the COVID-19 outbreak from social media and analyse its spatial-temporal characteristics from January 9 to February 10, 2020 in China. A topic extraction and classification model was built to identify the topics of COVID-19-related Weibo and uncover public sentiments in response to COVID-19. A series of topics and temporal and spatial distributions were identified and discussed.
