Global Vaccination Progress During COVID-19 Outbreak based on Data mining

Konferenz: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
17.12.2021 - 19.12.2021 in Shenyang, China

Tagungsband: ICMLCA 2021

Seiten: 7Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Autoren:
Tan, Chen; Lin, Jianzhong (Mathematics Department, Shanghai Jiao Tong University, Shanghai, China)

Inhalt:
In the context of the COVID-19 epidemic, the development and popularization of vaccines have effectively alleviated people’s panic. Twitter, as one of the world’s largest social platforms, promptly reflects the trend of emotional changes in screen names. Currently, vaccines such as Pfizer, Sputnik, and Moderna have successfully made a large number of people gain high immunity against the COVID-19 virus. However, a few cases of death due to vaccines have caused some people to question and worry about the safety of vaccines. A comprehensive understanding of progress of vaccine popularization is conducive making wiser decisions and calming people's panic. Since the large number of Tweets updated daily on Twitter can represent attitudes of netizens on the progress of vaccination, we used Bert model to predict and classify emotion categories to which different Tweets belong, with an accuracy rate of 80%. It is found that with the promotion of vaccination, fluctuation of netizen sentiment for vaccine progress has gradually decreased. Tweets with neutral sentiment still account for a majority of proportion, and the proportion of tweets with positive sentiment has gradually increased. In addition, we used LSTM model to predict the growth of cases with MSE less than 0.001. The growth of new cases in most countries gradually decreased to less than 10,000 people per day after June. Therefore, most vaccines have made significant progress in both winning public support and preventing COVID-19 infection.