Researchers at the University Of Rochester (New York) have been able to determine when healthy people are about to get sick with an accuracy level of some 90 percent, just by analyzing Tweets.
If you’re out in public, coming into contact with coughing and sneezing people, then common sense tells us that you might be about to get sick too.
So how did Adam Sadilek at the University of Rochester and colleagues use Twitter to predict when individual people will become ill? They started with over 4 million tweets from people in New York City. They analyzed Tweets containing sick and flu-symptom words.
To get the data down to the level of the individual, Sadilek and his team used the GPS location tagging data in some Tweets.
The researchers were able to predict when healthy people were about to fall ill – and then tweet about it – with about 90 per cent accuracy out to eight days in the future.