Facebook knows us better as friends & partners

„I like it“-Clicks on Facebook show a lot about personality

01/15/2015

Anyone posting on Facebook „I like it“ always shows something about preferences and personality traits. Now, US researchers have found that computers based on a sufficient number „Likes“ It may even be easier to judge character traits than friends, family, and the partner.

Users show preferences about sharing and liking posts
Whether group affiliations, parts of contributions or the famous „I like it“-Button: Facebook users often reveal a lot about themselves to the public. But apparently computers based on the Facebook activity can still determine much more concrete characteristics than friends or even your own partner. This is the conclusion of a recent study by Cambridge and Stanford Universities, which has just been published in the journal Proceedings of the National Academy of Sciences (PNAS), following a previous study by the University of Cambridge in 2013.

Researchers evaluate data from more than 86,000 subjects
Accordingly, the study had shown that a special software by the so-called „Likes“ Characteristics of Facebook users could determine more accurately than related parties. The researchers had analyzed the data of more than 86,000 subjects who had previously answered questions about their personality and had access to their likes on Facebook. The five characteristics of openness, sociability, sense of duty, compatibility and impulsiveness were the focus of the evaluation, such as the favor of the surrealist painter Salvador Dali or the theme „meditation“ could be interpreted as an indication of a very open mind, the scientists said.

Computer makes on the basis of Likes more details than work colleagues and family
The sympathies and interests of the users were analyzed by a computer in the next step, while friends, relatives and partners could also answer questions about the character of the respective person via an app. The scientists then compared this information from about 32,000 participants with those of the computer analysis and came to an interesting conclusion: „In the study, a computer could predict the personality of the subjects more accurately than a colleague by analyzing only ten likes; more than a friend or a partner (roommate) with 70, a family member (parents, siblings) with 150, and a spouse with 300 likes“, so the announcement of the University of Cambridge.

People are prone to non-rational thinkinge
According to Dr. Michal Kosinski, co-author and researcher at Stanford University, said this was possible because the machines had some key advantages over humans: the ability to store data, access huge amounts of information, and the ability to use algorithmic techniques analyze. „Big data and machine learning provide accuracy that will be hard to achieve for the human mind, as people tend to put too much weight on one or two examples or fall into non-rational ways of thinking, "Kosinski continues.

Computer analysis could help people with important decisions
„This sort of data analysis could help people to reinforce their own views and judgments in important life decisions“, said the lead author of the study, Wu Youyou from the Center for Psychometrics in Cambridge. „The ability to judge a personality is an integral part of social life-in day-to-day decisions and long-term plans, as well as who we marry, who we trust, who we choose to be president, Cambridge adds. Author Dr. David Stillwell. (Nr)

Picture: Peter Derrfuss