Salvatore Scellato, Anastasios Noulas and Cecilia Mascolo, of Cambridge’s Computer Laboratory developed a new approach to social networking that relies on more than just friends of friends. It also includes the places people visit.
The idea is to predict how people will make new friends. According to Scellato, we know that we are likely to become friends with ‘friends of friends’, but what we find is there are specific places which foster the creation of new friendships and they have specific characteristics.
The idea is pretty simple but seems rather involved. The developers see the problem facing social networks has been the sheer volume of users. With millions of users, it may seem lucrative for business. The task of recommending friends can become exponentially unfathomable as in the case of Facebook. You have 750 million active users.
The trio is adding another dimension to the friends of friend approach. This time they are including a very basic phenomenon of recommending new friends based on the places where users ‘check-in’.
The trio analyzed the location-based social network Gowalla. They wanted to see how users created social connections over a period of four months. They found out that about 30 per cent of all new social links appear among users that check-in to the same places. Consequently these ‘place friends’ showed disconnected users becoming direct connections.
People who frequent the same places may be similarly-minded individuals. Eventually, they are likely to form a connection with one another. Why not apply that connection to social networking sites?
Obviously, there are places where people interact more than others: offices, gyms, sport teams, schools and dance classes. This type of social network would aid development of friends. But, places like the airport or sports arena is highly unlikely people will develop a social connection.