COVID-19 warnings were on Twitter long before the outbreak of the pandemic

Even before the public announcements of the first cases of COVID-19 in Europe were made, at the end of January 2020, signals indicating that something strange was happening were already circulating on social networks. A new study by researchers from the IMT School for Advanced Studies in Lucca, published in Scientific reports, identified avenues of growing concern regarding pneumonia cases on posts posted to Twitter in seven countries between late 2019 and early 2020. Analysis of the posts shows that these warnings originated from the exact geographic regions where the main outbreaks subsequently occurred. developed.

To conduct the research, the authors first created a single database with all messages posted on Twitter containing the keyword “pneumonia” in the seven most widely spoken languages ​​of the European Union: English, German, French , Italian, Spanish, Polish and Dutch. —December 2014 to March 1, 2020. The word “pneumonia” was chosen because the disease is the most serious illness induced by SARS-CoV-2, and also because the 2020 influenza season has been milder than the previous ones, which excludes him as a candidate for all mentions and concerns.

The researchers then made a number of adjustments and corrections to positions in the database to avoid overestimating the number of tweets mentioning pneumonia between December 2019 and January 2020 – that is, within weeks. between the announcement by the World Health Organization that the first “cases of pneumonia of unknown etiology” had been identified – on December 31, 2019 – and the official recognition of COVID-19 as a serious communicable disease , January 21, 2020. In particular, all tweets and retweets containing links to news about the emergence virus have been removed from the database to exclude media coverage of the emerging pandemic from the count.

The analysis shows an increase in tweets mentioning the keyword ‘pneumonia’ in most of the European countries included in the study as of January 2020, so as to indicate an ongoing concern and public interest in pneumonia cases. In Italy, for example, where the first lockdown measures to contain COVID-19 infections were introduced on February 22, 2020, the rate of increase in mentions of pneumonia in the first weeks of 2020 differs significantly from the rate seen in during the same weeks. in 2019. That is, potentially hidden infection hot spots were identified several weeks before the announcement of the first local source of a COVID-19 infection (February 20, Codogno, Italy). France exhibited a similar trend, while Spain, Poland and the UK experienced a two-week delay.

The authors also geotagged over 13,000 pneumonia-related tweets over the same period and found that they came from exactly the regions where the first cases of infections were later reported, such as the Lombardy region in Italy, Madrid, Spain and the island of France.

Following the same procedure as that used for the keyword “pneumonia,” the researchers also produced a new data set containing the keyword “dry cough,” one of the other symptoms later associated with COVID-syndrome. 19. Even so, they observed the same pattern, namely an abnormal and statistically significant increase in the number of mentions of the word in the weeks leading up to the outbreak of infections in February 2020.

“Our study adds to existing evidence that social media can be a useful tool for epidemiological surveillance. They can help intercept the first signs of a new disease, before it grows undetected, and also track its spread, ”says Massimo Riccaboni, full professor of economics at IMT school, who coordinated the research.

This is especially true in a situation like the current pandemic, when shortcomings in identifying early warning signals have left many national governments blind to the unprecedented scale of the looming public health emergency. In a successive phase of the pandemic, social media monitoring could help public health authorities mitigate the risks of a resurgence of contagion, for example by adopting stricter social distancing measures where infections appear to be on the rise, or vice versa. versa by releasing them in other regions. These tools could also pave the way for an integrated epidemiological surveillance system managed globally by international health organizations.

Provided by IMT School for Advanced Studies Lucca