Twitter data can create health predictions

Twitter data can be a useful tool to predict the effects of lifestyle factors on health, researchers at the University of Rochester in New York report. Researchers have used Twitter to model how factors like social status, exposure to pollution, interpersonal interaction and others influence health, a university release said Friday. "If you want to know, down to the individual level, how many people are sick in a population, you would have to survey the population, which is costly and time-consuming," postdoctoral researcher Adam Sadilek said. "Twitter and the technology we have developed allow us to do this passively, quickly and inexpensively; we can listen in to what people are saying and mine this data to make predictions." Many tweets are geo-tagged, he said, which means they carry GPS information showing exactly where the user was when he or she tweeted. In a test using tweets collected in New York City over a period of a month, researchers looked at factors like how often a person takes the subway, goes to the gym or a particular restaurant, their proximity to a pollution source and their online social status, and then analyzed whether these had a positive, negative or neutral impact on the users' health based on what users said in tweets. The researchers used their studies to develop a web application called GermTracker that color-codes Twitter users (from red to green) according to their health and, using the GPS data encoded in the tweets, place them on a map, which allows anyone using the application to see their distribution. "This app can be used by people to make personal decisions about their health. For example, they might want to avoid a subway station if it's full of sick people," Sadilek said. "It could also be used in conjunction with other methods by governments or local authorities to try to understand outbursts of the flu."