Researchers have found that just by analyzing your Facebook Likes, a computer can judge your personality better than even your close friends. They went even further than that, and calculated how many Likes the algorithm has to analyze to figure your personality traits.

This is a graph showing accuracy of computer model’s personality judgement compared with humans.
Credit: Wu Youyou/Michal Kosinski

You are what you Like – that goes for many  in today’s society, especially considering how some 400 million people in the world are addicted to the internet. That was the thought which launched this study; researchers from Cambridge and Stanford wanted to see if, by mining what a person liked on Facebook, they can predict his or her personality traits. They then compared their software to the person’s friends and family.

The results were quite surprising – given a sufficient amount of Likes to analyze, only the spouse was able to rival the computer’s accuracy.

“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 lead author Wu Youyou, from Cambridge’s Psychometrics Centre. “In this context, the human-computer interactions depicted in science fiction films such as Her seem to be within our reach.”

The study analyzed 86,220 volunteers on Facebook who completed a 100-item personality questionnaire through the ‘myPersonality‘ app, as well as providing access to their Likes. Researchers were then able to have 17,622 participants judged by one friend and 14,410 judged by two. They also correlated these results with previous decades of psychological research, finding that their results regarding how well friends know each other are coherent with their own results.

Dr Michal Kosinski, co-author and researcher at Stanford, says AI has the potential to know us better than even our closest friends and family, mostly because it can efficiently analyze vast quantities of information (Big Data).

“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,” he said. Nevertheless, the authors concede that detection of some traits might be best left to human abilities, those without digital footprints or dependant on subtle cognition.

Do we really want computers to know us that well? Image via PS Mag.

Authors explain that there are many potential applications in improving company hirings, ecommerce and dating sites.

“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,” said Cambridge co-author Dr David Stillwell. “The results of such data analysis can be very useful in aiding people when making decisions.”

Indeed, cheap and effective personality tests clearly can be applied in many areas.

Youyou explains: “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,” she said.

However, there is also a matter of privacy violation. Do we actually want computers to know us that well? Is it a breach of privacy if Facebook can understand our personality better than our friends? As technology continues to develop, will we completely lose control over our personality’s privacy? Authors also point these problems out.

It’s a concern shared by the researchers. “We hope that consumers, technology developers, and policy-makers will tackle those challenges by supporting privacy-protecting laws and technologies, and giving the users full control over their digital footprints,” said Kosinski.

 

Enjoyed this article? Join 40,000+ subscribers to the ZME Science newsletter. Subscribe now!