• Corpus ID: 12575534

Your digital image: factors behind demographic and psychometric predictions from social network profiles

  title={Your digital image: factors behind demographic and psychometric predictions from social network profiles},
  author={Yoram Bachrach and Thore Graepel and Pushmeet Kohli and Michal Kosinski and David Stillwell},
We demonstrate how information gathered from social network profiles can be used to predict personal attributes such as gender and age, religious and political views, intelligence, happiness and personality traits. Our approach is based on applying machine learning techniques to a large dataset of people who volunteered their Facebook profiles along with their demographic and psychometric test results. We combine various features from the profile, including the numbers or rates of posting… 
Mining User Interests to Predict Perceived Psycho-Demographic Traits on Twitter
This work analyzes the relation between user interests and their perceived psychodemographic attributes using Twitter data, training models for predicting various personal traits of users, and uses crowdsourcing to annotate user profiles with perceptions regarding their personal traits.
Social network profiling for cultural heritage: combining data from direct and indirect approaches
It seems that users’ cognitive profiles can be predicted from social media observations and user actions (i.e., playing games) for 3 out of the 4 MBTI dimensions.
Human judgments in hiring decisions based on online social network profiles
  • Yoram Bachrach
  • Psychology
    2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA)
  • 2015
It is found that in screening based on social network profiles, a profile owner's education and demographic traits correlate with their job-suitability rating, which is very different from CV based screening, where the dominant criterion is education and skills.
Predicting Gaming Related Properties from Twitter Profiles
A system for predicting gaming-related properties from Twitter profiles based on machine learning models trained on crowd-sourced data, motivated by the automated discovery of influential gamers in social media, and its potential for streamlining product campaigns.
Using emotions to predict user interest areas in online social networks
The propensity of a user to express various emotions correlates with their perceived degree of interest in various areas, and several models are presented that use the emotional distribution of a Twitter user, as reflected by their tweets, to predict whether they are interested or disinterested in a topic.
Predicting Gaming Related Properties from Twitter Accounts
A system for predicting gaming related properties from Twitter accounts based on machine learning models trained on crowd-sourced data that allows people to select Twitter accounts of their fellow gamers, and examines the trait predictions made by the system.
Talkographics: Measuring TV and Brand Audience Demographics and Interests from User-Generated Content
It is demonstrated that group-level predictions can be used reliably in the context of building affinity networks and propose a recommender system using these Talkographic profiles.
Predicting user behavior in electronic markets based on personality-mining in large online social networks
A personality-based product recommender (PBPR) framework to analyze social media data in order to predict a user’s personality and to subsequently derive its personality- based product preferences is proposed.
A Framework for Understanding the Relationship between Social Media Discourse and Mental Health
This work presents a framework for constructing rich feature spaces from digital text communications and demonstrates the efficacy of this framework by applying it to a dataset of private Facebook messages in a college student population (N=103).


Private traits and attributes are predictable from digital records of human behavior
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
Personality and patterns of Facebook usage
It is shown how multivariate regression allows prediction of the personality traits of an individual user given their Facebook profile, with the best accuracy achieved for Extraversion and Neuroticism and the lowest accuracy for Agreeableness.
Personality Impressions Based on Facebook Profiles
Ind impressions based on 133 Facebook profiles are examined, comparing them with how the targets see themselves and are seen by close acquaintances, and results show generally strong patterns of convergence, although the accuracy correlations vary considerably across traits.
Personality, Gender, and Age in the Language of Social Media: The Open-Vocabulary Approach
This represents the largest study, by an order of magnitude, of language and personality, and found striking variations in language with personality, gender, and age.
Personality and Website Choice
We find that preference for websites, like preference for objects in the offline world, is influenced by personality. We combine personality profiles and website choices of more than 160.000 users
Calculating the singular values and pseudo-inverse of a matrix
The use of the pseudo-inverse $A^I = V\Sigma ^I U^* $ to solve least squares problems in a way which dampens spurious oscillation and cancellation is mentioned.
Neo personality inventory–revised (NEO-PI-R) and NEO five-factor inventory (NEO-FFI) professional manual
  • Odessa, FL: Psychological Assessment Resources,
  • 1992
The 16PF fifth edition administrator's manual
  • The 16PF fifth edition administrator's manual
  • 1994