Twitter Could be the Key to Early Detection of Pandemics

Researchers at UCI and UCLA are using Twitter to try and detect pandemics before they take off. By sifting through millions of tweets from the months leading up to COVID-19’s big splash, they are looking for anomalies and patterns that would have provided an early warning of the virus.

The National Science Foundation agreed and bestowed nearly $1 million on the 10-member UCI-UCLA team under its new Predictive Intelligence for Pandemic Prevention grant program. Chen Li, a professor of computer science who’s leading the effort at UCI, likens the project to “weather forecasting, where advances in big data analytics have led to significant improvements in our ability to predict weather patterns days or weeks in advance.”

Noymer says that, unfortunately, the method has only discovered “interesting pandemic signals from March 2020”–about a month too late to be of any use. The goal of the grant is to instead enable health officials with tipoffs about the coronavirus from as early as late 2019 so they can begin issuing warnings sooner.

The study has a significant drawback in that the coronavirus started in China, where Twitter is not accessible. Therefore, the team will also search for early monkeypox clues as a test case. The next step is to “cast a wider net” by incorporating data from Google, Facebook, and other social media platforms, as well as Internet searches, Noymer says.

Despite the challenges, the team remains optimistic that their work could help lead to the development of an effective pandemic warning system.

With this new grant, the team hopes to develop a pandemics warning system that could be used to predict and track the effects of future pandemics.