Modelling virtual camera behaviour through player gaze

In a three-dimensional virtual environment, aspects such as narrative and interaction largely depend on the placement and animation of the virtual camera. Therefore, virtual camera control plays a critical role in player experience and, thereby, in the overall quality of a computer game. Both game industry and game AI research focus on the development of increasingly sophisticated systems to automate the control of the virtual camera integrating artificial intelligence algorithms within physical simulations. However, in both industry and academia little research has been carried out on the relationship between virtual camera, game-play and player behaviour. We run a game user experiment to shed some light on this relationship and identify relevant differences between camera behaviours through different game sessions, playing behaviours and player gaze patterns. Results show that users can be efficiently profiled in dissimilar clusters according to camera control as part of their game-play behaviour.