/3dfa397c-9a73-11e4-8426-00144feabdc0.ht

  • Facebook understands you better than your spouse - FT.com
    http://www.ft.com/intl/cms/s/0/3dfa397c-9a73-11e4-8426-00144feabdc0.html

    New research suggests that a computer model is a better judge of an individual’s personality than those closest to them. The judgment is based on an analysis of what people “like” on Facebook.
    (…)
    In the study released on Monday, researchers analysed thousands of Facebook users, tracking the pages on which they clicked its “like” button, the blue thumbs-up symbol familiar to the social network’s 1.2bn users worldwide. These likes, of anything from company brands to a cat video, are seen by a user’s friends but can often be viewed by anyone else on the internet.
    Users on the site gave the scientists access to their Facebook “likes” and completed a personality questionnaire created by psychologists. More than 17,000 volunteers then invited friends and family to judge a user’s psychological traits through a different test. This allowed researchers to compare human judgment to machines, finding that when given enough data the computer model scored higher than siblings, parents and even spouses in understanding the character of a loved one.
    The model was able to judge personality more accurately than a work colleague though analysing just 10 Facebook likes, a friend with 70 likes, a family member through 150 likes, and a wife or husband using 300 likes. On average, a Facebook user has 227 likes on their social network profile.
    (…)
    Mr Stillwell [co-author of the study and deputy director of the psychometrics centre at Cambridge university] said he understood that some people might have privacy concerns with the findings. “It is creepy, but we should ask, why is it creepy?” he said. “It’s not necessarily a bad thing for computers to understand us as individuals. But [there are problems with] companies like Facebook and Google, which are not transparent on how they do their online advertising. They don’t explain why you’re seeing this advert.

    Facebook declined to comment.

    • Article accessible en ligne

      Computer-based personality judgments are more accurate than those made by humans
      http://www.pnas.org/content/early/2015/01/07/1418680112.abstract

      Abstract
      Judging others’ personalities is an essential skill in successful social living, as personality is a key driver behind people’s interactions, behaviors, and emotions. Although accurate personality judgments stem from social-cognitive skills, developments in machine learning show that computer models can also make valid judgments. This study compares the accuracy of human and computer-based personality judgments, using a sample of 86,220 volunteers who completed a 100-item personality questionnaire. We show that (i) computer predictions based on a generic digital footprint (Facebook Likes) are more accurate (r = 0.56) than those made by the participants’ Facebook friends using a personality questionnaire (r = 0.49); (ii) computer models show higher interjudge agreement; and (iii) computer personality judgments have higher external validity when predicting life outcomes such as substance use, political attitudes, and physical health; for some outcomes, they even outperform the self-rated personality scores. Computers outpacing humans in personality judgment presents significant opportunities and challenges in the areas of psychological assessment, marketing, and privacy.

    • How accurate is the computer, given an average person? Our recent estimate of an average number of Likes per individual is 227 (95% CI = 224, 230),‡ and the expected computer accuracy for this number of Likes equals r = 0.56. This accuracy is significantly better than that of an average human judge (z = 3.68, P < 0.001) and comparable with an average spouse, the best of human judges (r = 0.58, z = −1.68, P = 0.09). The peak computer performance observed in this study reached r = 0.66 for participants with more than 500 Likes. The approximately log-linear relationship between the number of Likes and computer accuracy, shown in Fig. 2, suggests that increasing the amount of signal beyond what was available in this study could further boost the accuracy, although gains are expected to be diminishing.


      Fig. 2. Computer-based personality judgment accuracy (y axis), plotted against the number of Likes available for prediction (x axis). The red line represents the average accuracy (correlation) of computers’ judgment across the five personality traits. The five-trait average accuracy of human judgments is positioned onto the computer accuracy curve. For example, the accuracy of an average human individual (r = 0.49) is matched by that of the computer models based on around 90–100 Likes. The computer accuracy curves are smoothed using a LOWESS approach. The gray ribbon represents the 95% CI. Accuracy was averaged using Fisher’s r -to- z transformation.