Facebook profiles may predict health problems

Facebook profiles can be ten times more effective at predicting health problems than looking at where people live, scientists say.
Alex Kogan, a social psychologist, and his colleagues at the University of Cambridge suggest Facebook may be a better tool for tracking health issues than geography.
The researchers claim to have built an algorithm that can 'learn' Facebook users' political preferences, health risks and levels of happiness.
The algorithm analyses users' likes, interactions and friendship groups to arrive at its conclusions, 'The Times' reported.
Most of the work is done by a computer that is fed large-scale survey responses and then crunches people's profiles to work out, for example, whether retweeting the Pope's Latin Twitter account makes you more or less likely to vote for Mitt Romney or liking 'OMG These Monkey Videos Will Make You Weep!' on Facebook suggests you are a smoker.

Using the algorithm, researchers found links between users' Facebook friends and health problems.
They found strong links between users' Facebook friends and their tendencies to smoke and drink, and have diabetes, high cholesterol and high blood pressure.