Social networking site like Twitter has already used to interact with friends and celebrities, but now researchers believe it could be used to track disease. A team from the University of Rochester has already used Twitter to track flu as it spreads through New York with the help of heat map of users who complain of being ill.
Lead researcher Adam Sadilek and colleagues examined four-and- half millions GPS-tagged Tweets from over six-hundred-thousand users in New York over the period of one month in 2010. They created an artificial intelligence algorithm that ignored tweets by healthy people and the algorithm only found those who were really ill.
The artificial intelligence algorithm looked not only the health of users’ friends’, but also strangers in the same area. The algorithm was correct by ninety percent of the time and about eight days in advance. Explaining about how algorithm works, Sadie, stated their models enable you to see the spread of infectious diseases, such as flu, throughout a real-life population observed through online social media.
The tweets were plotted on a map and were used to envisage when a specific users was at high risk of getting ill. They applied machine learning and natural language understanding techniques to determine the health state of Twitter users at any given time. Since a large fraction of tweets is geo-tagged, they can plot them on a map, and observe how sick and healthy people interact.
Then their model predicts if and when a person will fall ill with high accuracy, thereby improving their understanding of the emergence of global epidemics from people’s day-to-day interactions. The heat maps show a city going through a flu epidemic. The more red an area is, the more people are afflicted by flu at that location, added Mr. Sadilek.
In contrast earlier techniques so called state-of-the-art methods including Google Flu Trends and government data, involve time lags from days to years. The study findings were presented at the Conference on Artificial Intelligence in Toronto, Canada.