BACKGROUND A novel virus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has started a global pandemic of pneumonia since December 2019, when first cases were reported in Wuhan, China . It has caused 2.7 million confirmed cases and nearly 200,000 deaths as of April 24 , 2020 . Early warning systems with new technologies should be established to avoid such disasters .
OBJECTIVE This study aimed to explore the possibility of early detecting the SARS-CoV-2 outbreak in 2019 using social media .
METHODS WeChat Index is a data service that shows how frequent a specific keyword has appeared in posts, subscriptions, and search over a period of last 90 days on WeChat, the most popular Chinese social media . We plotted daily WeChat Index from Nov 17 , 2019 to Feb 14 , 2020 for keywords related to the SARS-CoV-2 disease .
RESULTS WeChat Index for``Feidian"that is SARS in Chinese language had stayed at low levels until 16 days ahead of the outbreak announcement on Dec 31 , 2019 by the local authority when the index increased significantly . Later, the index persisted at relative high levels from Dec 15 , 2019 to Dec 29 , 2019 and rose rapidly on Dec 30 , 2019, the day just before the announcement . WeChat Index also spiked or increased for keywords `` SARS '', `` coronavirus '', `` novel coronavirus '', `` shortness of breath '', `` dyspnea '', and``diarrhea '', but not as meaningful as``Feidian"in early detection of the outbreak .
CONCLUSIONS Using WeChat may detect the SARS-CoV-2 outbreak in 2019 about two weeks earlier than the outbreak announcement . WeChat may offer a new approach to early detect disease outbreaks . CLINICALTRIAL