The following is a list of publications. Papers that are still in submission (pending acceptance/rejection) and papers in press are indicated as such in the citation.
PsyOps: Personality Assessment Through Gaming Behavior – PDF – Variable List
Traditional personality assessment methods are based on behavioral, observational, and self-report measures, each of which suffers from weaknesses that stem from ambiguity (behavioral measures), cost-payoff ratio (professional observation), and reliability (self-report). Assessment through video game play offers a way of quantifying behavior, automating observations, and side-stepping self-report. To determine whether video games are a valuable addition to the arsenal of personality assessment methods, we set out to answer the question: Does the statistically trackable play style of a player significantly correlate to his personality? To find the answer, we conducted a survey among Battlefield 3 players. Through the use of a promotional campaign, dubbed ‘Psy-Ops’, the response to the survey ran up to 13,376 individuals. Each participant was asked to fill out a 100-item IPIP (International Personality Item Pool) Big Five personality questionnaire, and requested for permission to draw their game statistics from a public database. All in all, 173 game variables, 100 personality scores, and 5 personality dimensions were correlated for the total sample, and 11 demographic subsamples. We found that play style and personality do correlate signicantly, showing three key themes. (1) Conscientiousness is negatively correlated with speed of action. (2) The game variable Unlock Score per Second correlates most often and most strongly with personality, especially with Conscientiousness and Extraversion. (3) Work ethic correlates negatively with performance in the game. Apart from these three themes, subsamples differ in correlational patterns.
An additional result was found when performing a posthoc analysis on age. Correlations between age and play style were greater than those between play style and personality. While themes (1), (2) and (3) showed effect sizes up to the 0.2 range, age offered effect sizes in the 0.3 range for game performance and game length preference, as well as a correlation of r =-0.42 with Unlock Score per Second. Age and personality correlate with a similar eect size as play style and personality. Therefore, age correlates strongly to play style, while age and play style offer complimentary correlations to personality.
CITATION: S. Tekofsky, P. Spronck, A. Plaat, J. Van den Herik, and J. Broersen. Psyops: Personality assessment through gaming behavior. In Proceedings of the International Conference on the Foundations of Digital Games. FDG, 2013
Play Style: Showing Your Age – PDF
Age has been shown to influence our preferences, choices, and cognitive performance. We expect this influence to be visible in the play style of an individual. Player models would then benefit from incorporating age, allowing developers to offer an increasingly personalized game experience to the player. To investigate the relationship between age and play style, we set out to determine how much of the variance in a player’s age can be explained by his play style. For this purpose, we used the data from a survey (‘PsyOps’) among 13,376 ‘Battlefield 3’ players. Starting out with 60 play style variables, we found that 45.7% of the variance in age can be explained by 46 play style variables. Furthermore, similar percentages of variance in age are explained when the sample is divided along gaming platform: 31 play style variables explain 43.1% on PC; 30 play style variables explain 53.9% on Xbox 360; 28 play style variables explain 51.7% on Playstation 3. Our findings have a high external validity due to the large and heterogeneous nature of the sample. The strength of the relationship between age and play style is considered ‘large’ according to Cohen’s classification. Previous research indicates that the nature of the relationship between age and play style is likely to be based on life-time developments in cognitive performance, motivation, and personality. All in all, our findings merit a recommendation to incorporate age in future player models.
CITATION: S. Tekofsky, P. Spronck, A. Plaat, J. Van den Herik, and J. Broersen. Play Style: Showing Your Age. In Proceedings of the IEEE 2013 Conference on Computational Intelligence in Games (In Press). CIG, 2013
Towards a Player Age Mode – PDF
This paper proposes a Player Age (PA) model with the potential to be generalized to many different games. The model offers insight into the relationship between age and play style. Game developers can use the PA model to gain a better understanding of their target audience, and to optimize adaptive game features (i.e., AI, targeted marketing). In order to become generically applicable, the PA model is based on the literature on life-span developments in physiology and psychology. The PA model states that player age is a linear function of four factors: Speed of Play (-), Performance (-), Preference (+/-), and Time Played (+/-). The model is validated on a data set from Battlefield 3 (FPS). It explains 33.7% of the variance in age (range: 12-65 years) with a standard error of 6.743. To determine the generic quality of the PA model, future work will validate it on games of other genres.
CITATION: S. Tekofsky, P. Spronck, M. Goudbeek, and J. Broersen. Towards a Player Age Model. In Proceedings of the Ninth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-13) (In Press). AAAI, 2013