In Journal of medical Internet research ; h5-index 88.0
BACKGROUND : The emergence of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2 or COVID-19) has given rise to a global pandemic affecting 215 countries and over 40 million people as of October 2020. Meanwhile, we are also experiencing an infodemic induced by the overabundance of information, some accurate and some not, spreading rapidly across social media platforms. Social media has arguably shifted the information acquisition and dissemination of a considerable large population of internet users towards higher interactivities.
OBJECTIVE : This study aimed to investigate the COVID-19 related health beliefs on one of the mainstream social media platforms, Twitter, as well as the potential impacting factors associated with the fluctuations in health beliefs on social media.
METHODS : We used COVID-19-related posts from the mainstream social media platform Twitter to monitor health beliefs. 92,687,660 tweets corresponding to 8,967,986 unique users from January 6 to June 21, 2020 were retrieved. To quantify the health beliefs, we employed the health belief model (HBM) with four core constructs: perceived susceptibility, perceived severity, perceived benefits, and perceived barriers. We utilized natural language processing (NLP) and machine learning techniques to automate the process of judging the conformity of each tweet with each of the four HBM constructs. 5,000 tweets were manually annotated for training the machine learning architecture.
RESULTS : The machine learning classifiers yielded AUCs over 0.86 for the classification of all the four HBM constructs. Our analyses revealed a basic reproduction number R_0 of 7.62 for trends in the number of Twitter users posting health belief-related contents over the study period. The fluctuations in the number of health belief-related tweets could reflect dynamics in cases and death statistics, systematic interventions, and public events. Specifically, we observed scientific events, such as scientific publications, and non-scientific events, such as speeches of politicians, are comparable in their abilities to influence health beliefs trends on social media through a Kruskal-Wallis test (P-value = .78 and .92 for perceived benefits and perceived barriers, respectively).
CONCLUSIONS : As an analogy of the classic epidemiology model where an infection is considered to be spreading in a population with an R_0>1, the number of users tweeting about COVID-19 health beliefs is amplifying in an epidemic manner and could partially intensify the infodemic. It is "unhealthy" that both scientific and non-scientific events constitute no disparity in impacting the health belief trends on Twitter since non-scientific events, such as politicians' speeches, might not be endorsed by substantial evidence and could be misleading sometimes.
Wang Hanyin, Li Yikuan, Hutch Meghan, Naidech Andrew, Luo Yuan