Playing With Networks

Video gaming behavior may offer information about the players and the widespread diffusion of this form of entertainment produces a staggering amount of data about gaming behaviors. The aim of the current study was to investigate the possibility to use the information about the way the player acts and reacts in a competitive video game to assess personality traits inside the HEXACO space. Deep learning was used to train deep neural networks that classified a sample of players (N = 41) with different personality traits by how they play in a Massive Online Battle Arena (MOBA) video game. Results suggested that the likelihood of correctly identifying the player’s trait level was above chance for five out of the six personality dimensions, but there is a medium to high margin of error in the classification. These findings provide interesting suggestions to set the premises for future studies to test the feasibility of this alternative assessment tool.