Computational personality recognition in social media

Golnoosh Farnadi, Geetha Sitaraman, Shanu Sushmita, Fabio Celli, Michal Kosinski, David Stillwell, Sergio Davalos, Marie-Francine Moens, Martine De Cock
2016 User modeling and user-adapted interaction  
A variety of approaches have been recently proposed to automatically infer users' personality from their user generated content in social media. Approaches differ in terms of the machine learning algorithms and the feature sets used, type of utilized footprint, and the social media environment used to collect the data. In this paper, we perform a comparative analysis of state-of-the-art computational personality recognition methods on a varied set of social media ground truth data from
more » ... Twitter and YouTube. We answer three questions: (1) Should personality prediction be treated as a multi-label prediction task (i.e., all personality traits of a given user are predicted at once), or should each trait be identified separately? (2) Which predictive features work well across different online environments? and (3) What is the decay in accuracy when porting models trained in one social media environment to another? Keywords Big Five personality · Social media · User generated content · Multivariate regression · Feature analysis Introduction Research in psychology has suggested that behavior and preferences of individuals can be explained to a great extent by underlying psychological constructs: personality traits [42] . Knowledge of an individual's personality allows us to make predictions about preferences across contexts and environments, and to enhance recommendation systems [33] . Personality can affect the decision making process and has been shown to affect preferences for websites [31] , products, brands and services [32] , and for content such as movies, TV shows, and books [9] .
doi:10.1007/s11257-016-9171-0 fatcat:33aojvt255hnljkvsiaoonikiq