What does touch tell us about emotions in touchscreen-based gameplay?

Abstract

Nowadays, more and more people play games on touch-screen mobile phones. This phenomenon raises a very interesting question: does touch behaviour reflect the player’s emotional state? If possible, this would not only be a valuable evaluation indicator for game designers, but also for real-time personalization of the game experience. Psychology studies on acted touch behaviour show the existence of discriminative affective profiles. In this paper, finger-stroke features during gameplay on an iPod were extracted and their discriminative power analysed. Based on touch-behaviour, machine learning algorithms were used to build systems for automatically discriminating between four emotional states (Excited, Relaxed, Frustrated, Bored), two levels of arousal and two levels of valence. The results were very interesting reaching between 69% and 77% of correct discrimination between the four emotional states. Higher results (~89%) were obtained for discriminating between two levels of arousal and two levels of valence.