Cambrige researchers tout new location-based method to predict friends on social networks

Friend suggestions on social networks may already be a little too eerily accurate for some, but a team of researchers from Cambridge University now say they can do one better. They've devised a method that doesn't simply rely the usual friends-of-friends approach, but on where those people tend to hang out. According to researcher Salvatore Scellato, "it turns out that the properties of the places we interact can determine how likely we are to develop social ties," and that places like offices and gyms are better indications of potential friends than football stadiums or airports. That notion was borne out in their research (conducted over a period of four months using Gowalla), which found that "about 30 percent of all new social links appear among users that check-in to the same places." With the two prediction methods combined, the researchers say they're able to account for 66 percent of all new social ties. No word if they've moved onto predicting crimes next.