week before Europe get it on it had a COVID-19 problem , warning signal were already appearing on Twitter . Moreover , the placement of tweet touch on to “ pneumonia ” and “ juiceless cough ” equalize the places where SARS - CoV-2 would be find to be most usual a calendar month or so afterward . The discovery represents a massive miss chance to have verify the spread of the virus before it took hold , but also offers hope for preventing next pandemic .
Tracking search locomotive utilisation of terms associated with colds and flu has beenshown to bean effective means for wellness authorities to detect upsurge in respiratory disease before conventional examination procedures capture up . There is even evidencereviews of scented candleshave turn more minus because multitude with COVID-19 blame their unfitness to smell out on the taper . Professor Massimo Riccaboniof IMT School for Advanced Studies imagine societal media might bid something similar . Riccaboni test the idea by reckon for evidence of post before prescribed diagnosis began , testing the question of whether SARS - CoV-2 wascirculating in Europewell before news from Wuhan alerted health authorities to the problem .
Riccaboni searched Twitter for references to “ pneumonia ” ( and its equivalent in six other speech ) in December 2019 and January 2020 , liken it with data proceed back to December 2014 to serve as a mastery . InScientific Reports , Riccaboni and carbon monoxide gas - source uncover a spectacular upsurge in pneumonia - link tweets during that fateful winter . Although this is influenza time of year in the Northern Hemisphere , the influenza outbreak that class was mild compare to the previous one . Nevertheless , pneumonia tweets were up , even after removing those discussing newsworthiness theme .
The same practice was seen for “ dry cough ” , the implication of which would have escaped the great unwashed at the time , but turned out to be a warning of one of COVID-19 ’s more typical symptoms .
If Riccaboni ’s observations were limited to timing , there would be many alternative account . For example , as shortly as news seeped out of China about a newfangled respiratory disease , masses with grippe might have become more inclined to talk about their symptom online .
However , when the squad bet at the regions where more than 13,000 tweets include the term pneumonia originated , they found the surge was pore in places where COVID-19 was first found to be unwashed a calendar month or two after . The fact there was a surge in Lombardy and Madrid , but not in parts of Europe that did n’t get come to by the pandemic until substantially later , is very improbable to be a coincidence in the writer ' purview .
" Our study tot on to the subsist grounds that societal medium can be a utile tool of epidemiologic surveillance . They can help intercept the first signs of a new disease , before it proliferates undetected , and also track its banquet , " Riccaboni said in astatement .
The newspaper purport the organisation of an “ integrated digital surveillance system of rules ” to identify signs of infectious disease through societal media and web searches and pinpoint city and realm in risk .
The benefits would be in particular large for fast - displace diseases like COVID-19 , where interventions to trim back transmission system made just a few days earlier would have a striking event on the size of the eventual peak .
