A computer can determine your personality better than your closest friends family by using your Facebook "likes" to judge your character, university researchers found.
The study of 86,220 volunteers highlighted how artificial intelligence can use data to accurately predict a person's traits. The researchers at the University of Cambridge and Stanford dubbed the findings an "important milestone" towards more social human-computer interactions.
"In this context, the human-computer interactions depicted in science fiction films such as "Her" seem to be within our reach," lead author Wu Youyou, from Cambridge's Psychometrics Centre, said in a press release. "Her" depicts the relationship between a man and an intelligent computer system.
The findings showed that by analyzing just 10 likes on Facebook, the computer could more accurately predict a subject's personality than a work colleague.
With 70 likes, it could know more about someone than their friends, and with 150 it would be more knowledgeable than a family member. With 300 likes it could determine your personality better than a spouse, although an average Facebook user has about 227 likes, the researchers pointed out.
Users can "like" Facebook posts such as pictures, statuses or groups by clicking the blue thumbs-up button on the social media website.
Volunteers in the study - which was published in the "Proceedings of the National Academy of Sciences" journal – gave friends and family a shorter version of the personality test they originally completed. This gave the researchers a chance to test their computer's assessment against a human with a close association to the subject.
"People may choose to augment their own intuitions and judgments with this kind of data analysis when making important life decisions such as choosing activities, career paths, or even romantic partners. Such data-driven decisions may well improve people's lives," Youyou said.
The study built on previous work at Cambridge University which found computers were able to identify a person's race, age, IQ, sexuality, personality, substance use and political views through Facebook likes.
"We hope that consumers, technology developers, and policy-makers will tackle those challenges by supporting privacy-protecting laws and technologies, and giving the users full control over their digital footprints," Michal Kosinski, co-author and researcher at Stanford, said in a press release.