Evolution of Online Public Opinions and Situational Control During the COVID-19 Pandemic: A case study from Chengdu, China

In the age of big data, online public opinions breed and erupt when health emergencies occur. Tourism destinations have attracted much attention because of their unique high traffic and frequent population movements. It is crucial to take reasonable measures to cope with the outbreak of negative public opinion during the COVID-19 Pandemic. This paper uses Python to crawl the sentiment perceptions of tourists towards Tourism destinations during public health emergencies and classifies the sentiment as the dataset. Then, using Netlogo software to build an online opinion model, we simulate four scenarios for what a tourist destination should do to reduce the outbreak of negative public opinion: the release of information by opinion leaders, the change in the number of people contacted by negative public opinion, the change in the speed of dissemination of negative public opinion, and the release of relevant policies. In the four scenarios, it was found that the scenario in which relevant departments issued regulations have the greatest impact on negative public opinions. Changing the speed of public opinion dissemination is the least significant scenario.