Like curly fries? You’re clever. Like motorbikes? You’re not: the science of Facebook 'likes'

New study reveals how Facebook “likes” say a lot more about a person than you first think
  • @jerometaylor

Enjoy curly fries, thunderstorms and Morgan Freeman’s voice? Chances are you’re highly intelligent.

But if Tyler Perry, Harley Davidsons and the American country group Lady Antebellum are your thing, you may not be the sharpest tool in the box.

These are just some of the conclusions of a new study by Cambridge psychologists into what can be deduced about a person by analysing their Facebook “likes”.

Researchers used a complex algorithm to find it was possible to accurately predict what a person is like in real life – including sexual orientation, religion, political views, intelligence, and even drug use – based on what might otherwise appear to be innocuous preferences. The academics warned that similar tools could be used by repressive regimes to predict the political beliefs or sexual orientation – even of those who avoid making obvious statements online.

For example, researchers found that only five per cent of gay users clicked on obvious links such as “gay marriage” but they were nonetheless able to predict with 88 per cent accuracy a man’s sexual preference by monitoring the other things they liked on Facebook – such as films and pop groups.

Michael Kosinski, a computational psychologist at the University of Cambridge’s Psychometrics Centre, told The Independent that similar techniques were used by companies to tailor advertising or services to consumers. But he said online behaviour could also be used to accurately predict deeply personal details.

“On one hand I want to share as much data as possible with online services,” he said. “I want an online book store, for example, to know about my book tastes so I get better recommendations the next time I log on. But on the other hand by revealing the kind of books I’m reading I’m also allowing different companies or institutions to predict quite accurately other traits I might not want to share.”

Scientists studied 58,000 predominantly-American Facebook users who have signed up to a free online psychology test in return for the anonymous use of their data. That allowed psychologists to build a computer program that could start trawling through public posts and predict what sort of person someone is like in real life. The programme was able to determine race with 95 per cent accuracy, political leanings with 85 per cent accuracy and religion 82 per cent of the time.

* Individual traits and attributes can be predicted to a high degree of accuracy based on records of users' Likes.

For example, the best predictors of high intelligence include “Thunderstorms,” “The Colbert Report,” “Science,” and “Curly Fries,” whereas low intelligence was indicated by “Sephora,” “I Love Being A Mom,” “Harley Davidson,” and “Lady Antebellum.”

Good predictors of male homosexuality included “No H8 Campaign,” “Mac Cosmetics,” and “Wicked The Musical,” whereas strong predictors of male heterosexuality included “Wu-Tang Clan,” “Shaq,” and “Being Confused After Waking Up From Naps.” Although some of the Likes clearly relate to their predicted attribute, as in the case of No H8 Campaign and homosexuality, other pairs are more elusive; there is no obvious connection between Curly Fries and high intelligence.

Moreover, note that few users were associated with Likes explicitly revealing their attributes. For example, less than 5% of users labeled as gay were connected with explicitly gay groups, such as No H8 Campaign, “Being Gay,” “Gay Marriage,” “I love Being Gay,” “We Didn't Choose To Be Gay We Were Chosen.” Consequently, predictions rely on less informative but more popular Likes, such as “Britney Spears” or “Desperate Housewives” (both moderately indicative of being gay).

Research also showed the average levels of personality traits and age for several popular Likes.

Each Like attracts users with a different average personality and demographic profile and, thus, can be used to predict those attributes. For example, users who liked the “Hello Kitty” brand tended to be high on Openness and low on “Conscientiousness,” “Agreeableness,” and “Emotional Stability.” They were also more likely to have Democratic political views and to be of African-American origin, predominantly Christian, and slightly below average age.

Although liking “Barack Obama” is clearly related to being a Democrat, it is also relatively popular among Christians, African Americans, and Homosexual individuals.