Study sees relationship signals in Facebook data

Mike Krumboltz
Facebook logo (Photo: Facebook)

Think your relationship is strong? Think there is nothing in this world that could possibly tear you and your beloved apart? Have a seat, grab a tissue. Facebook would like a word with you.

Cornell University computer scientist Jon Kleinberg and Lars Backstrom, a senior engineer at Facebook, have written a research paper that explains how the giant social networking site can use its data to anticipate which personal relationships might fail.

The process is rather complicated, but The New York Times broke it down in an easy-to-understand blog post.

One might think that a relationship's strength is best illustrated by the number of friends two people have in common on Facebook. The new study say that isn't the case.

Using a data set of roughly 1.3 million Facebook users, all over the age of 20, all with a significant other and all with 50 to 2,000 friends, the researchers found that a network measure called "dispersion" is a better indicator of romantic relationships.

From the New York Times:

(Dispersion) measures mutual friends, but also friends from the further-flung reaches of a person’s network neighborhood. High dispersion occurs when a couple’s mutual friends are not well connected to one another.

So when a couple has a high dispersion rate, their relationship is likely to be easier for an algorithm to identify and is probably stronger, the research suggested.

Via the New York Times:

Particularly intriguing is that when the algorithm fails, it looks as if the relationship is in trouble. A couple in a declared relationship and without a high dispersion on the site are 50 percent more likely to break up over the next two months than a couple with a high dispersion, the researchers found. (Their research tracked the users every two months for two years.)

Of course, Facebook doesn't have a monopoly on prophesy. Twitter has long been lauded for its ability to predict things like elections and flu outbreaks. Some computer scientists have even used the social network to predict where you are most likely to get food poisoning.