Researchers from Cambridge University and Stanford University have come up with a new software that can reveal your personality better and clearly than your friends by analysing posts that you “like” on Facebook.
The software based on mining Facebook “likes”, shows the computer model can predict a person’s personality better than close friends and family, the only exception being one’s wife.
“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 study author Wu Youyou from Cambridge’s psychometrics centre.
The researchers studied a sample of 86,220 volunteers on Facebook who filled in a 100 questions related to personality questionnaire through the ‘myPersonality’ app, besides providing access to their “likes” list.
The researchers found that the computer model could accurately predict the person’s personality more than his or her work colleague by analysing just 10 “likes”, more than a friend with 70 “likes”, a family member like parent or sibling with 150 and a spouse with 300 “likes”.
Given that an average Facebook user has about 227 “likes” currently, the researchers say the software with this kind of artificial intelligence has the potential to know us better than our closest companions, except wife or husband.
Michal Kosinski, co-author of the study at Stanford, said machines have in fact more advantages to make these results possible, especially the ability to retain and access vast quantities of information and the ability to analyse it with algorithms – the techniques of “Big Data”.
The automated, accurate and cheap personality assessments could improve societal and personal decision-making from recruitment to romance.
“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,” added another Cambridge co-author David Stillwell.
However, the results may trigger privacy concerns once again over Facebook as such technology may give away one’s own personality to others, who in turn, try to cash in on or exploit in the future. The findings have been published in the journal Proceedings of the National Academy of Sciences.