Concept: Personality psychology
- Proceedings of the National Academy of Sciences of the United States of America
- Published over 4 years ago
We show that easily accessible digital records of behavior, Facebook Likes, can be used to automatically and accurately predict a range of highly sensitive personal attributes including: sexual orientation, ethnicity, religious and political views, personality traits, intelligence, happiness, use of addictive substances, parental separation, age, and gender. The analysis presented is based on a dataset of over 58,000 volunteers who provided their Facebook Likes, detailed demographic profiles, and the results of several psychometric tests. The proposed model uses dimensionality reduction for preprocessing the Likes data, which are then entered into logistic/linear regression to predict individual psychodemographic profiles from Likes. The model correctly discriminates between homosexual and heterosexual men in 88% of cases, African Americans and Caucasian Americans in 95% of cases, and between Democrat and Republican in 85% of cases. For the personality trait “Openness,” prediction accuracy is close to the test-retest accuracy of a standard personality test. We give examples of associations between attributes and Likes and discuss implications for online personalization and privacy.
- Proceedings of the National Academy of Sciences of the United States of America
- Published almost 3 years ago
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.
The increasing prevalence of social media means that we often encounter written language characterized by both stylistic variation and outright errors. How does the personality of the reader modulate reactions to non-standard text? Experimental participants read ‘email responses’ to an ad for a housemate that either contained no errors or had been altered to include either typos (e.g., teh) or homophonous grammar errors (grammos, e.g., to/too, it’s/its). Participants completed a 10-item evaluation scale for each message, which measured their impressions of the writer. In addition participants completed a Big Five personality assessment and answered demographic and language attitude questions. Both typos and grammos had a negative impact on the evaluation scale. This negative impact was not modulated by age, education, electronic communication frequency, or pleasure reading time. In contrast, personality traits did modulate assessments, and did so in distinct ways for grammos and typos.
Associations between personality traits, mental wellbeing and good health behaviours were examined to understand further the social and psychological context of the health divide.
Cerebral palsy (CP) is a term that has been applied over the years to a group of children with motor disability and related service requirements. The first conceptions of cerebral palsy and our knowledge about aetiology and pathogeny allow us to assume that cerebral palsy existed in the Ancient World. Although there is lack of detailed medical descriptions from before the 19th century, mentions to cerebral palsy can be found in representational art, literary sources and paleopathology; however, because of the poor medical documentation, the diagnosis of cerebral palsy must remain a more or less well-justified supposition. In the Ancient World, the first medical description of cerebral palsy was made by Hippocrates in his work “Corpus Hippocraticum”. Concrete examples and definitions of cerebral palsy, however, did not emerge until the early 19th century with observations by William John Little; thus, Little was the first personality to intensely engage cerebral palsy. Towards the end of the 19th century, two more personalities emerged, adding to the historical hallmarks of cerebral palsy: William Osler and Sigmund Freud. The significant developments that have followed since then are all due to the contributions of these three personalities in the field of cerebral palsy.
Unlike frozen snapshots of facial expressions that we often see in photographs, natural facial expressions are dynamic events that unfold in a particular fashion over time. But how important are the temporal properties of expressions for our ability to reliably extract information about a person’s emotional state? We addressed this question experimentally by gauging human performance in recognizing facial expressions with varying temporal properties relative to that of a statistically optimal (“ideal”) observer. We found that people recognized emotions just as efficiently when viewing them as naturally evolving dynamic events, temporally reversed events, temporally randomized events, or single images frozen in time. Our results suggest that the dynamic properties of human facial movements may play a surprisingly small role in people’s ability to infer the emotional states of others from their facial expressions.
Eating disorders (EDs) are common amongst women; however, no research has specifically investigated the lifetime/12-month prevalence of eating disorders amongst women in mid-life (i.e., fourth and fifth decade of life) and the relevant longitudinal risk factors. We aimed to investigate the lifetime and 12-month prevalence of EDs and lifetime health service use and to identify childhood, parenting, and personality risk factors.
Psychopathy is a personality disorder associated with a profound lack of empathy. Neuroscientists have associated empathy and its interindividual variation with how strongly participants activate brain regions involved in their own actions, emotions and sensations while viewing those of others. Here we compared brain activity of 18 psychopathic offenders with 26 control subjects while viewing video clips of emotional hand interactions and while experiencing similar interactions. Brain regions involved in experiencing these interactions were not spontaneously activated as strongly in the patient group while viewing the video clips. However, this group difference was markedly reduced when we specifically instructed participants to feel with the actors in the videos. Our results suggest that psychopathy is not a simple incapacity for vicarious activations but rather reduced spontaneous vicarious activations co-existing with relatively normal deliberate counterparts.
Rorschach inkblots have had a striking impact on the worlds of art and science because of the remarkable variety of associations with recognizable and namable objects they induce. Originally adopted as a projective psychological tool to probe mental health, psychologists and artists have more recently interpreted the variety of induced images simply as a signature of the observers' creativity. Here we analyze the relationship between the spatial scaling parameters of the inkblot patterns and the number of induced associations, and suggest that the perceived images are induced by the fractal characteristics of the blot edges. We discuss how this relationship explains the frequent observation of images in natural scenery.
Facial expressions are important for humans in communicating emotions to the conspecifics and enhancing interpersonal understanding. Many muscles producing facial expressions in humans are also found in domestic dogs, but little is known about how humans perceive dog facial expressions, and which psychological factors influence people’s perceptions. Here, we asked 34 observers to rate the valence, arousal, and the six basic emotions (happiness, sadness, surprise, disgust, fear, and anger/aggressiveness) from images of human and dog faces with Pleasant, Neutral and Threatening expressions. We investigated how the subjects' personality (the Big Five Inventory), empathy (Interpersonal Reactivity Index) and experience of dog behavior affect the ratings of dog and human faces. Ratings of both species followed similar general patterns: human subjects classified dog facial expressions from pleasant to threatening very similarly to human facial expressions. Subjects with higher emotional empathy evaluated Threatening faces of both species as more negative in valence and higher in anger/aggressiveness. More empathetic subjects also rated the happiness of Pleasant humans but not dogs higher, and they were quicker in their valence judgments of Pleasant human, Threatening human and Threatening dog faces. Experience with dogs correlated positively with ratings of Pleasant and Neutral dog faces. Personality also had a minor effect on the ratings of Pleasant and Neutral faces in both species. The results imply that humans perceive human and dog facial expression in a similar manner, and the perception of both species is influenced by psychological factors of the evaluators. Especially empathy affects both the speed and intensity of rating dogs' emotional facial expressions.