By feeding 630,000 New York City residents’ 4.4 million tweets into an algorithm, researchers at the University of Rochester were able to predict when healthy people would fall ill with about 90 per cent accuracy out to eight days in the future. Importantly, each tweet the team analyzed was tagged with GPS location data. That allowed researchers to track the spread of flu symptoms across space and time, enabling them to predict who would contract the flu even before any symptoms were exhibited. The algorithm was taught the difference between tweets by healthy people, who might say something like ‘I am so sick of this traffic!’, and someone who is actually sick and showing signs of the flu.
Subscribe for counterintuitive, surprising, and impactful stories delivered to your inbox every Thursday
What’s the Big Idea?
Data from the analysis also showed that people who go to the gym regularly are moderately less likely to get sick and that people with low socioeconomic status are much more likely to become ill. The research shows the power of Big Data to positively influence our lives.”Such information could one day be used to power a smartphone app that warns you when you’ve entered a public place with a high incidence of flu. Or after a big day out, it might buzz you with a message to say you are at high risk of getting sick over the next few days.” The system would be limited to helping people who tweet reliably about their symptoms.