EAS faculty Cuihua Cindy Shen, Jingwen Zhang, and Bo Feng's new research on social media data and COVID-19 in China

Reports of Own and Others' Symptoms and Diagnosis on Social Media Predict COVID-19 Case Counts in Mainland China

Cuihua Shen (1), Anfan Chen (2), Chen Luo (3), Wang Liao (1), Jingwen Zhang (1), Bo Feng (1) ((1) University of California, Davis, (2) University of Science and Technology of China, (3) Tsinghua University)

Can public social media data be harnessed to predict COVID-19 case counts? We analyzed more than 12 million COVID-19 related posts on Weibo, a popular Twitter-like social media platform in China, from November 20, 2019 to March 3, 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. We then modeled the predictive power of sick posts and other COVID-19 posts on daily case counts. We found that reports of symptoms and diagnosis of COVID-19 significantly predicted daily case counts, up to seven days ahead of official statistics. But other COVID-19 posts did... [READ MORE]

[Submitted on 13 Apr 2020 (this version), latest version 19 May 2020 (v2)]