Come here often? asks new Cambridge social network

A new way of predicting which people may become friends on social networks – based on the type of places they visit – has been formulated by University of Cambridge researchers.

Most social networking sites like Facebook and LinkedIn rely on the ‘friend-of-a-friend’ approach to try to determine which people may be connected.

Now Salvatore Scellato, Anastasios Noulas and Cecilia Mascolo, of Cambridge’s Computer Laboratory, have devised a new approach that not only looks at friends of friends, but also the places people visit – with incremental weightings given to different places such as airports and gymnasia.

Scellato said: “Essentially this is a way in which we can predict how people will make new friends. 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 that they have specific characteristics.”

Historically, the problem facing social networks has been the sheer volume of users. While millions of users may represent good news from a business perspective, it means the task of recommending friends can become an exponentially difficult one, if, as in the case of Facebook, you have 750 million active users.

The standard two-hop approach – sharing at least a common friend – has, to date, ignored the possibilities of recommending new friends based on the places where users ‘check-in’.

The trio’s research is an extension of long-standing sociological theory that people who tend to frequent the same places may be similarly-minded individuals likely to form a connection with one another – but applied to social networking sites.

Scellato added: “For our research we analysed the location-based social network Gowalla to see how users created social connections over a period of four months.

“We discovered that about 30 per cent of all new social links appear among users that check-in to the same places. Thus, these ‘place friends’ represent disconnected users becoming direct connections.

“By combining place friends with friends-of-friends, we can make the prediction space about 15 times smaller and yet, cover 66 per cent of new social ties.

“It turns out that the properties of the places we interact can determine how likely we are to develop social ties. Offices, gyms and schools are more likely to aid development rather than other places such as football stadia or airports. In those places, it’s highly unlikely people will develop a social connection.

“Our results show it’s possible to improve the performance of link prediction systems on location-based services that can be employed to keep the users of social networks interested and engaged with that particular website.”

Share and Enjoy

Germany questions Facebook about facial recognition feature

IDG News Service - Facebook is facing fresh concerns from German data protection officials that its automatic facial recognition feature may violate European privacy regulations.

Hamburg’s Data Protection Agency (DPA) sent a letter to Facebook on Tuesday saying the social networking site should get users’ consent before their biometric data, used to enable the tagging feature, is stored, said Johannes Caspar, head of the agency, on Thursday. Although users can opt out of the feature, the DPA contends that the process is unclear, he said.

Facebook enabled the facial recognition feature in December in the U.S. and has now rolled it out in most countries. The system makes suggestions for tags based on faces in other photographs that have been tagged. Users are notified only after they’ve been tagged.

Users can opt out of the facial recognition feature within the privacy settings on their Facebook accounts. To do that, a user would need to go into the “Customize Settings” panel and disable “Suggest photos of me to friends.” A person can still be tagged manually but only by their friends.

Caspar said European Union privacy regulations require that users give their consent before their data is stored, including data used to enable tagging.

“It is clear that everybody whose data will be stored has to consent, and consent is something more than not to reject,” Caspar said.

Facebook has two weeks to respond to the letter. The DPA has also notified the Article 29 Data Protection Working Party, which advises the European Commission on data protection issues.

In a statement, Facebook said “we will consider the points the Hamburg Data Protection Authority have made about the photo tag suggest feature but firmly reject any claim that we are not meeting our obligations under European Union data protection law.”

The company further contended that its users like the photo tag suggest feature, “which makes it easier and safer for them to manage their online identities.”

If the two sides can’t reach an agreement, Caspar could fine Facebook up to €300,000 (US$426,000). But Caspar said his agency has a good working relationship with Facebook, and the two sides reached agreement earlier this year on Facebook’s “Friend Finder” feature.

Friend Finder imports e-mail addresses from user contact lists on other e-mail services and then sends out invitations to non-Facebook users to join the site. The DPA contended Facebook was collecting e-mail addresses without a user’s consent and that it was unclear to users why they were receiving an invite.

Under the agreement, Facebook tweaked its systems so that a person who is not signed up with the social networking site can opt out of receiving further invitations from that initial invitation.

“We had a successful negotiation,” Caspar said.

Hamburg’s DPA has taken a leading role in data protection issues in Europe. In 2009, the agency launched an extensive investigation into Google’s Street View imagery program, questioning how the company stored data for users who did not want their properties shown and how thoroughly it censors parts of images such as people’s faces.

Google and the DPA eventually reached an agreement on a dozen or so concerns the agency had about Street View.

Send news tips and comments to jeremy_kirk@idg.com

Share and Enjoy