CONICET | Buscador de Institutos y Recursos Humanos

PurposePersonality trait detection is a problem that has been gaining much attention in the computer science field recently. By leveraging users? personality knowledge software ap- plications are able to adapt their behaviour accordingly. To detect personality traits au- tomatically users must substantially interact with software applications to gather enough information that describe their behaviour. For addressing this limitation, we explore the use of online video games as an alternative approach to detect personality dichotomies.Design/methodology/approachWe analyse the use of several online video games that exhibit features related with Myers-Briggs Sensitive-Intuitive personality dichotomy. Then, we build a user profile that describes users? behaviour when interacting with online video games. Finally, we identify users? personality by analysing their profile with different classification algorithms.FindingsThe results show that games that obtained better results in the personality dichotomy detection exhibit features that better match with the Sensitive-Intuitive dichotomy pref- erences. Moreover, the results show that the classification algorithms should satisfactorily deal with unbalanced datasets, since it is natural that the frequencies of the dichotomies types are unbalanced. In addition, in the context of personality trait detection, online video games posses several advantages over other type of software applications. By using games, users do not need to have previous experience, since they learn how to play during gameplay. Furthermore, the information and time needed to predict the Sensitive-Intuitive dichotomy using games is little.Originality/valueThis study shows that online video games are a promising environment in which the users? personality dichotomies can be detected.