Report: Artificial Intelligence Can Predict If Your Relationship Will Last

AP Photo/David Guttenfelder
AP Photo/David Guttenfelder

Artificial intelligence can predict whether your relationship will last based on how you speak to your partner, according to a report.

According to, the research “analysed the vocal characteristics of 134 couples undergoing therapy.”

“Researchers from the University of Southern California used computers to extract standard speech analysis features from recordings of therapy session participants over two years. The features – including pitch, variation in pitch and intonation – all relate to voice aspects like tone and intensity,” they explained. “A machine-learning algorithm was then trained to learn a relationship between those vocal features and the eventual outcome of therapy. This wasn’t as simple as detecting shouting or raised voices – it included the interplay of conversation, who spoke when and for how long as well as the sound of the voices.”

“It turned out that ignoring what was being said and considering only these patterns of speaking was sufficient to predict whether or not couples would stay together,” the report continued, adding that the AI had a success rating of 79.3 percent.

When the data was analyzed by human experts instead, they boasted a lower 75.6 percent success rating. However, the report claims that “the best results came from combining the automated assessment with the experts’ assessment (79.6% correct).”

This month, it was reported that artificial intelligence could determine whether someone was straight or gay by using photographs of faces.

According to The Guardian, the computer algorithm “could correctly distinguish between gay and straight men 81% of the time, and 74% for women,” however the research was heavily criticized by popular LGBT groups, including GLAAD and The Human Rights Campaign, who called the report “junk science” and “dangerous.”

Charlie Nash is a reporter for Breitbart Tech. You can follow him on Twitter @MrNashington and Gab @Nash, or like his page at Facebook.


Please let us know if you're having issues with commenting.