Skip to content

Facebook Can Now Predict If Your Relationship Is Doomed, Study Reveals

November 1, 2013

Who you are friends with on Facebook could determine when you will break up with your partner.

A study from Cornell University in America has worked out a way of accurately predicting which couples will separate just by seeing who they’re friends with on the site.

Lars Backstrom and Jon Kleinberg looked at over 1.3 million Facebook users to come up with the method.

Couples who had lots of mutual friends were not the strongest duos – their mutual friends also had to know each other as well.

Called “low dispersion,” this means that your friends meet your partner’s friends and merge to form one large social group.

 ”A spouse or romantic partner is a bridge between a person’s different social worlds,” Kleinberg explained to the New York Times.

Using this, Backstrom and Kleinberg were able to correctly identify who somebody’s spouse was 60 per cent of the time and correctly guess somebody’s partner a third of the time.

Relationships that hadn’t been spotted using the dispersion algorithm were 50 per cent more likely to break up over the next two months, compared to those that had been identified by looking at friendships of mutual friends.

Facebook is not planning on integrating this information into the website just yet, however.

A spokeswoman told “The specific findings from this study are not currently being used in making News Feed a better product.”

“It has helped the team think about things and informed some of the features we use in ranking.”

Posted from WordPress for BlackBerry.

From → Lifestyle

Leave a Comment

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: