webstationlogos3 KHTK-sports-1140_FINAL-social_125x35b

News

Study: Facebook May Be Able To Predict Divorce

View Comments
File photo of the Facebook home page. (Photo by NICHOLAS KAMM/AFP/GettyImages)

File photo of the Facebook home page. (Photo by NICHOLAS KAMM/AFP/GettyImages)

Get Breaking News First

Receive News, Politics, and Entertainment Headlines Each Morning.
Sign Up

SACRAMENTO (CBS SACRAMENTO) – A new study suggests that Facebook can predict when a married user will get divorced even before the user may know.

The study, by Jon Kleinberg, a computer scientist at Cornell University, and Lars Backstrom, a senior engineer at Facebook, was published online before being presented at a social computing conference in February.

Researchers used a data set of 1.3 million randomly selected users aged 20 and up, each with 50 to 2,000 friends on the social networking site. Within each profile, the user had a romantic partner or spouse listed in their profile.

When a couple’s mutual friends are not well connected to one another it’s called high dispersion and proved to be the best indicator of romantic involvement. This basically means that the number of mutual friends that two people share is a weak predictor of whether they’re in a relationship or not.

“A spouse or romantic partner is a bridge between a person’s different social worlds,” Kleinberg explained in an interview according to the Mother Nature Network.

The study found that a couple listed in a relationship without a high dispersion were 50 percent more likely to break up over the next two months than a couple with a high dispersion making it possible for Facebook to predict which couple’s relationship will end before the users even know.

Predicting a user’s spouse wasn’t always predictable by high dispersion, but it proved to be very accurate with a 60 percent correct prediction.

Researchers note that the study also shows how the ideal partner who will last is one that connects a user with a different network of people that they would not otherwise socialize with.

View Comments
blog comments powered by Disqus