Labels

Your Facebook Likes may reveal more than you probably like




Users' expressions of approval on the social network can accurately predict personality traits, sexual orientation, and intelligence, researchers say.




Facebook users' Likes on the social network may be unintentionally revealing more about their personality traits, sexual orientation, and intelligence, according to a new study.

By studying the Likes of 58,000 Facebook users on the social network, researchers at the University of Cambridge say they were able to determine users' IQ, gender, sexual orientation, political and religious beliefs, and even substance use, with an accuracy rate of more than 80 percent
Users' expressions of approval on the social network for things such as photos, friends' status updates, as well as pages for sports, musicians, and books were analyzed by researchers employing a model that reduced the number of random variables under consideration. When compared with user-provided demographic profiles and other psychometric tests, researchers learned they had correctly predicted sexual orientation 88 percent of the time, ethnicity 95 percent of the time, and political leanings in 85 percent of the cases.


 "This study demonstrates the degree to which relatively basic digital records of human behavior can be used to automatically and accurately estimate a wide range of personal attributes that people would typically assume to be private," researchers said in the study, which was published today in Proceedings of the National Academy of Sciences (PDF).

"Likes represent a very generic class of digital records, similar to Web search queries, Web browsing histories, and credit card purchases," researchers said. "In contrast to these other sources of information, Facebook Likes are unusual in that they are currently publicly available by default."
While recognizing that predicting attributes and preferences could be used to improve a wide range of products and services, researchers noted that there were considerable negative implications to the predictability model, especially when digital records are analyzed without individuals knowledge or consent.
"Commercial companies, governmental institutions, or even one's Facebook friends could use software to infer attributes such as intelligence, sexual orientation, or political views that an individual may not have intended to share," researchers concluded. "One can imagine situations in which such predictions, even if incorrect, could pose a threat to an individual's well-being, freedom, or even life."