sciencetech-blog

comments

Many people are guilty of oversharing on Facebook, but even the most reserved users may be giving away more about their personality than they realise.

By 'mining' for Likes on the social network, software has been developed that can accurately predict how open, conscientious, outgoing and neurotic an individual user is. 

And, in the majority of cases, these predictions were found to be more accurate than those made by close friends and family.

Using this data, the University of Cambridge has created an online test that lets you see what your Facebook profile is revealing about you. 

Take the interactive test below: You will need to connect the app to your Facebook account, but it only accesses your Likes and does not post to your wall

The research, and online test (pictured), were created by PhD student Wu YouYou from Cambridge University's Psychometrics Centre. Users will need to connect the test to their Facebook account, but it only accesses Likes and does not post to their wall

During tests, only a spouse's judgement rivalled the computer's ability to sum up broad psychological traits.

The research, and online test, were created by PhD student Wu YouYou from Cambridge University's Psychometrics Centre.

In addition to predicting a user's personality, the test estimates a user's age, relationship status, intelligence levels, life satisfaction, political and religious beliefs, and education.

To collect the data, Ms Youyou's team asked 86,220 Facebook users to complete a 100-item personality questionnaire, designed to provide personality scores for traits including openness, conscientiousness, extraversion, agreeableness, and neuroticism.

As part of the process, the members also allowed the researchers to access and analyse which pages on Facebook they had Liked. 

The research, and online test, was created by PhD student Wu YouYou from Cambridge University's Psychometrics Centre. In addition to predicting a user's personality (pictured), the test predicts a user's age, relationship status, intelligence levels, life satisfaction, political and religious beliefs and education

By 'mining' for Likes on the social network, software has been developed that can accurately predict how open, conscientious, outgoing and neurotic that individual user is. And, in the majority of cases, these predictions were found to be more accurate than those made by close friends and family

Analysis of this data revealed which Likes equated with higher levels of particular traits.

For instance, liking Salvador Dali, TED talks, or pages about meditation revealed a high degree of openness.

People with higher levels of extraversion commonly Liked reality TV star Snooki, and pages about dancing.

The results of the questionnaire were then compared with judgements of friends and family members made using a shorter version of the personality test.

Given enough Likes, the software was able to match people's self-reported personality traits more closely than siblings, parents or friends.

In particular, the researchers found their software could predict a participant's personality more accurately than a work colleague from analysing just 10 Likes.

Inputting 70 Likes allowed it to obtain a truer picture of someone's character than a friend, while 150 Likes outperformed a parent or sibling.

It took 300 Likes before the software was able to judge character better than a spouse, though.

Given that an average Facebook user has about 227 Likes, the researchers said this kind of artificial intelligence (AI) has the potential to know us better than our closest companions.

'In the future, computers could be able to infer our psychological traits and react accordingly, leading to the emergence of emotionally-intelligent and socially skilled machines,' said Ms Youyou.

'In this context, the human-computer interactions depicted in science fiction films such as Her seem to be within our reach.'

In Her, starring Joaquin Phoenix, a man develops a close relationship with an intelligent computer operating system called Samantha, personified by a female voice.

But the scientists admit there may be concerns about privacy as such technology develops, and say they support policies giving users full control over their digital footprint.

Analysis of the data revealed which Likes equated with higher levels of particular traits. For instance, liking Salvador Dali (picutred) , TED talks, or pages about meditation revealed a high degree of openness. The results of the computerised assessment were compared with judgements of friends and family members

The software predicted a participant's personality more accurately than a colleague using just 10 Likes. Inputting 70 Likes allowed it to obtain a truer picture of character than a friend, while 150 Likes outperformed a parent or sibling. It took 300 Likes before the software could judge character better than a spouse, though

The work, reported in the journal Proceedings of the National Academy of Sciences, builds on a previous study by Cambridge University scientists which showed that a variety of psychological and demographic characteristics can be predicted through Facebook Likes.

Co-author Dr David Stillwell, also from Cambridge University, added: 'The ability to judge personality is an essential component of social living - from day-to-day decisions to long-term plans such as whom to marry, trust, hire, or elect as president.

'The results of such data analysis can be very useful in aiding people when making decisions.'

People with higher levels of extraversion commonly Liked reality TV star Snooki (pictured), and pages about dancing, according to the research. Given that an average Facebook user has about 227 Likes, the researchers said this kind of software has the potential to know people better than their closest companions

Lead researcher Wu Youyou said: 'In this context, the human-computer interactions depicted in science fiction films such as Her seem to be within our reach.' In Her, starring Joaquin Phoenix, (pictured) a man develops a close relationship with an operating system personified by a female voice, called Samantha

Phd student Ms Youyou continued: 'Recruiters could better match candidates with jobs based on their personality; products and services could adjust their behaviour to best match their users' characters and changing moods.

'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.'