Your Facebook 'likes' could be revealing more than even you know about your intimate life!
Researchers were able to accurately infer a Facebook user's race, IQ, sexuality, substance use and political views, just by analysing their Facebook likes.
A new study by the University of Cambridge involved more than 58,000 Facebook users in the US, who volunteered their 'likes', demographic profiles and psychometric testing results through the application myPersonality, and gave their permission for that information to be analysed.
Experts created "statistical models" designed to predict people's personal details using only their Facebook 'likes'.
The models turned out to be 88 per cent reliable for determining male sexuality, 95 per cent right when distinguishing African-American from Caucasian American, and 85 per cent accurate in differentiating Republican from Democrat.
Christians and Muslims were correctly classified in 82 per cent of cases and good prediction accuracy was achieved for relationship status and substance abuse - between 65 and 73 per cent, the study published in the journal PNAS said.
"Few users clicked 'likes' explicitly revealing these attributes. For example, fewer than five per cent of gay users clicked obvious 'likes' such as gay marriage. The predictionsrelied on inference - aggregating huge amounts of less informative but more popular 'likes' such as music and TV shows to produce incisive personal profiles," a spokesman for the research team said in a statement.
"Even seemingly opaque personal details such as whether users' parents separated before the user reached the age of 21 were accurate to 60 per cent, enough to make the information worthwhile for advertisers," the spokesman said.
"Some 'likes' had a strong but seemingly incongruous or random link with a personal attribute, such as Curly Fries with high IQ, or That Spider is More Scared Than U Are with non-smokers.
"When taken as a whole, the researchers believe the varying estimations of personal attributes and personality traits gleaned from Facebook like analysis alone can form surprisingly accurate personal portraits of potentially millions of users worldwide," he said.
Researchers say the results also suggest "a possible revolution in psychological assessment" which could now be carried out without costly assessment centres and
questionnaires. But they also warn it may pose a threat to privacy.
They say companies, governments, and even individuals could use it for their own, rather than the users', advantage.
"We believe our results, while based on Facebook 'likes', apply to a wider range of on-line behaviours. Similar predictions could be made from all manner of digital data, statistically predicting sensitive information people might not want revealed," Michael Kosinski, operations director at the Psychometric Centre, said.
Researchers were able to accurately infer a Facebook user's race, IQ, sexuality, substance use and political views, just by analysing their Facebook likes.
A new study by the University of Cambridge involved more than 58,000 Facebook users in the US, who volunteered their 'likes', demographic profiles and psychometric testing results through the application myPersonality, and gave their permission for that information to be analysed.
Experts created "statistical models" designed to predict people's personal details using only their Facebook 'likes'.
The models turned out to be 88 per cent reliable for determining male sexuality, 95 per cent right when distinguishing African-American from Caucasian American, and 85 per cent accurate in differentiating Republican from Democrat.
Christians and Muslims were correctly classified in 82 per cent of cases and good prediction accuracy was achieved for relationship status and substance abuse - between 65 and 73 per cent, the study published in the journal PNAS said.
"Few users clicked 'likes' explicitly revealing these attributes. For example, fewer than five per cent of gay users clicked obvious 'likes' such as gay marriage. The predictionsrelied on inference - aggregating huge amounts of less informative but more popular 'likes' such as music and TV shows to produce incisive personal profiles," a spokesman for the research team said in a statement.
"Even seemingly opaque personal details such as whether users' parents separated before the user reached the age of 21 were accurate to 60 per cent, enough to make the information worthwhile for advertisers," the spokesman said.
"Some 'likes' had a strong but seemingly incongruous or random link with a personal attribute, such as Curly Fries with high IQ, or That Spider is More Scared Than U Are with non-smokers.
"When taken as a whole, the researchers believe the varying estimations of personal attributes and personality traits gleaned from Facebook like analysis alone can form surprisingly accurate personal portraits of potentially millions of users worldwide," he said.
Researchers say the results also suggest "a possible revolution in psychological assessment" which could now be carried out without costly assessment centres and
questionnaires. But they also warn it may pose a threat to privacy.
They say companies, governments, and even individuals could use it for their own, rather than the users', advantage.
"We believe our results, while based on Facebook 'likes', apply to a wider range of on-line behaviours. Similar predictions could be made from all manner of digital data, statistically predicting sensitive information people might not want revealed," Michael Kosinski, operations director at the Psychometric Centre, said.