Analysis of sentiment changes in online messages of depression patients before and during the COVID-19 epidemic based on BERT+BiLSTM.

With the development of the Internet, more and more people prefer to confide their sentiments in the virtual world, especially those with depression. The social media where people with depression collectively leave messages is called the "Tree Hole". The purpose of this article is to support the "Tree Hole" rescue volunteers to help patients with depression, especially after the outbreak of COVID-19 and other major events, to guide the crisis intervention of patients with depression. Based on the message data of "Tree Hole" named "Zou Fan", this paper used a deep learning model and sentiment scoring algorithm to analyze the fluctuation characteristics sentiment of user's message in different time dimensions. Through detailed investigation of the research results, we found that the number of "Tree Hole" messages in multiple time dimensions is positively correlated to emotion. The longer the "Tree Hole" is formed, the more negative the emotion is, and the outbreak of COVID-19 and other major events have obvious effects on the emotion of the messages. In order to improve the efficiency of "Tree Hole" rescue, volunteers should focus on the long-formed "Tree Hole" and the user groups that are active in the early morning. This research is of great significance for the emotional guidance of online mental health patients, especially the crisis intervention for depression patients after the outbreak of COVID-19 and other major events.

Research on Quantitative Analysis of Multiple Factors Affecting COVID-19 Spread.

The Corona Virus Disease 2019 (COVID-19) is spreading all over the world. Quantitative analysis of the effects of various factors on the spread of the epidemic will help people better understand the transmission characteristics of SARS-CoV-2, thus providing a theoretical basis for governments to develop epidemic prevention and control strategies. This article uses public data sets from The Center for Systems Science and Engineering at Johns Hopkins University (JHU CSSE), Air Quality Open Data Platform, China Meteorological Data Network, and WorldPop website to construct experimental data. The epidemic situation is predicted by Dual-link BiGRU Network, and the relationship between epidemic spread and various feature factors is quantitatively analyzed by the Gauss-Newton iteration Method. The study found that population density has the greatest positive correlation to the spread of the epidemic among the selected feature factors, followed by the number of landing flights. The number of newly diagnosed daily will increase by 1.08% for every 1% of the population density, the number of newly diagnosed daily will increase by 0.98% for every 1% of the number of landing flights. The results of this study show that the control of social distance and population movement has a high priority in epidemic prevention and control strategies, and it can play a very important role in controlling the spread of the epidemic.

Discovering Correlations between the COVID-19 Epidemic Spread and Climate.

The outbreak of Corona Virus Disease 2019 (COVID-19) has affected the lives of people all over the world. It is particularly urgent and important to analyze the epidemic spreading law and support the implementation of epidemic prevention measures. It is found that there is a moderate to high correlations between the number of newly diagnosed cases per day and temperature and relative humidity in countries with more than 10,000 confirmed cases worldwide. In this paper, the correlation between temperature/relative humidity and the number of newly diagnosed cases is obvious. Governments can adjust the epidemic prevention measures according to climate change, which will more effectively control the spread of COVID-19.