No abstract

Believable artificial opponents, for example, believable virtual drivers, are fundamental to engage players and make (car racing) video games more entertaining. This paper lays the foundations for the design of believable virtual drivers by proposing a methodology for profiling players using the open racing car simulator. Data collected from 125 players about their driving behaviors and personality traits give insights into how personality traits should model the behavior of believable virtual drivers. The data analysis was conducted using a correlation analysis and the J48 decision tree algorithm. Empirical evidence shows that goal-oriented driving behaviors can be used to determine personality traits of players. In addition, this work also (i) gives preliminary insights into the relationship between the driving behavior and personality of racing game players and actual car drivers; and (ii) presents evidence of the relevance of gender as a predictor of personality traits of racing game players.