The researchers at Cambridge University have come up with a method for predicting potential friends on social networks on the basis of common places visited.
Currently, social networks like Facebook and Twitter offer friend suggestions by following the ‘friends-of-friends’ approach. However, the new method developed by the researchers is based on the places people visit in the real world.
This method, when combined with the method currently in use, could result in highly efficient friend suggestions.
“We wanted to investigate the properties of places that encourage connections between visitors and how this could be incorporated into a system that predicts friends,” said Salvatore Scellato, one of the researchers who developed the method.
He revealed that they studied user behaviour on location based social networking platform Gowalla.
“We monitored the behaviour of people going to places and the connections they made. We found that lots of people who go to the same places end up adding each other as friends, accounting for around 30 per cent of new social links,” he explained.
People have a good chance of becoming friends with someone who visits the same places as they do. This method could help social networks deal with the vast number of people on offer, when it comes to giving friend suggestions.