Using Reports of Own and Others' Symptoms and Diagnosis on Social Media to Predict COVID-19 Case Counts: Observational Infoveillance Study in Mainland China.

BACKGROUND: COVID-19 has affected more than 200 countries and territories worldwide. It poses an extraordinary challenge for public health systems, because screening and surveillance capacity-especially during the beginning of the outbreak-is often severely limited, fueling the outbreak as many patients unknowingly infect others.

OBJECTIVE: We present an effort to collect and analyze COVID-19 related posts on the popular Twitter-like social media site in China, Weibo. To our knowledge, this infoveillance study employs the largest, most comprehensive and fine-grained social media data to date to predict COVID-19 case counts in mainland China.

METHODS: We built a Weibo user pool of 250 million, approximately half of the entire monthly active Weibo user population. Using a comprehensive list of 167 keywords, we retrieved and analyzed around 15 million COVID-19 related posts from our user pool, from November 1, 2019 to March 31, 2020. We developed a machine learning classifier to identify "sick posts," which are reports of one's own and other people's symptoms and diagnosis related to COVID-19. Using officially reported case counts as the outcome, we then estimated the Granger causality of sick posts and other COVID-19 posts on daily case counts. For a subset of geotagged posts (3.10% of all retrieved posts), we also ran separate predictive models for Hubei province, the epicenter of the initial outbreak, and the rest of mainland China.

RESULTS: We found that reports of symptoms and diagnosis of COVID-19 significantly predicted daily case counts, up to 14 days ahead of official statistics, whereas other COVID-19 posts did not have similar predictive power. For the subset of geotagged posts, we found that the predictive pattern held true for both Hubei province and the rest of mainland China, regardless of unequal distribution of healthcare resources and outbreak timeline.

CONCLUSIONS: Public social media data can be usefully harnessed to predict infection cases and inform timely responses. Researchers and disease control agencies should pay close attention to the social media infosphere regarding COVID-19. On top of monitoring overall search and posting activities, leveraging machine learning approaches and theoretical understandings of information sharing behaviors is a promising approach to identifying true disease signals and improving the effectiveness of infoveillance.