Current DateSeptember 17, 2021

An algorithm to predict the next movements of the Covid-19 pandemic

An international team recently reported that they were working on an algorithm that could help during this Covid-19 pandemic. It uses a wealth of data, particularly from social networks, to predict the evolution of the pandemic. According to the researchers, this is about supporting political actors in their decision-making.

Help make choices

Although the current Covid-19 pandemic has some precedents, it seems to have surprised everyone. In the United States, as in other countries, policy makers communicated and acted rather late and often inappropriately. Management is therefore quite flawed, so that the threat of a second wave hovers over our heads. Inevitably, state authorities will have to make new decisions.

In a publication on the arXiv platform on July 3, 2020, an international team explains that it is working on a forecasting algorithm. The objective is to anticipate the evolution of the pandemic with an advance of about two weeks. However, this period would be sufficient to take appropriate measures. Deconfinement? Reconfinement? School opening / closing? To restore the economy. The algorithm in question could in theory help decision-makers.

Data diversification

Lead researcher Mauricio Santillana of Harvard University in the United States provided further details. The algorithm in question would assess the danger 14 days before a large increase in cases. The latter uses both real-time monitoring of Twitter as well as searches typed on Google by Internet users. In addition, the system also integrates mobility data from smartphones.

For the leaders of the project, it is a matter of observing changes in the behavior of citizens. According to them, the study found that “early signals of an increase in the prevalence of Covid-19” could be revealed by “next generation alternative data sources”. Here is the example given by the researchers: a week before the explosion of the number of Covid-19 cases in New York, the number of messages published on Twitter had increased sharply.

Unable to deploy currently

The study is however to be taken with a grain of salt. Indeed, arXiv is a pre-publication platform. In other words, the studies published there have not yet been peer reviewed. In addition, the authors of the study recognize the limits of their algorithm themselves, and this despite the interest that it could arouse. According to them, no technology can predict sudden changes in the behavior of the masses. Proof of this is the demonstrations that followed the murder of George Floyd and the creation of the Black Lives Matter movement.

In addition, social networks and search engines could be less and less revealing in times of pandemic. In fact, citizens are getting used to the presence of the virus and do less keyword research. According to the researchers, it is not yet a question of applying their algorithm because the risks are too great. Before a possible application, these models must be checked and validated over time.