ABSTRACT
In this paper, we propose a method for analyzing social trends related to the coronavirus disease (COVID-19) pandemic by using social media data. The proposed method reveals that there is a correlation between tweets posted by users in Twitter and the number of infected people in a certain period. Specifically, the proposed method extracts tweet features based on the relationship between the contents and keywords of tweets. Compared to the previous approaches which focus only on the number of tweets, the proposed method can capture more richer information. Therefore, high correlation between the tweet features and the number of infected people can be obtained. For analyzing the tweets related to COVID-19, the proposed method consider not the number of tweets but the contents of the tweets. This is the main contribution of this paper. We verify the effectiveness of the proposed method through experiments on real-world datasets. © 2021 IEEE.