Computer algorithm accurately profiles you using your Facebook likes — try it here!

Researchers from Cambridge and Stanford have devised a computer algorithm capable of predicting your personality using the things you’ve “liked” on Facebook. Their results, published in the Proceedings of the National Academy of Sciences, suggests that the program can better judge of your personality than your closest friends.

The study examined a sample of 86,220 volunteers on Facebook using a 100-question assessment conducted through the app called ‘myPersonality.’ Once completed, the app compiled a baseline score showcasing how the subject ranked in terms of the five major person traits: openness, conscientiousness, extraversion, agreeableness, and neuroticism. Afterward, friends and family were asked to judge them using a similar survey. 

The ends results demonstrated that the computer model could predict users’ personality far more accurately than their friends or roommates with as little as 70 likes; a parent or sibling with 150; and a spouse with more than 300. The average number of likes per user in the study was 227.

When I sat down with the program, it determined I am 27 years old (correct), most likely to have an education in the arts (incorrect; that would be business management), and a very agreeable, open, and semi-neurotic person (I’ll take that). Apparently, my life satisfaction is 63%. Visit Apply Magi Sauce to try the test for yourself.

Michal Kosinski, researcher at Stanford University and the study’s co-author, explains that computer software can do a much better job creating an overall picture of personality given machines are a bit more arbitrary in their overall assessment. He says, “big data and machine-learning provide accuracy that the human mind has a hard time achieving, as humans tend to give too much weight to one or two examples, or lapse into non-rational ways of thinking,”

Back when Facebook was new and unused by neither grandmother, nor tween, “liking” inappropriate or unrelated content was insignificant. Nowadays, doing so may not only brand you in an inappropriate manner before your social acquaintances, but may do so in whatever social-engineering database collects this stuff. 

Source: DiscoveryNews