Measuring Enjoyment in Games Through Electroencephalogram (EEG) Signal Analysis

Awareness is growing that neuroscientific knowledge can offer a significant contribution to improve education. This paper reports the research work we are conducting in investigating the in-game player's enjoyment state through a simple commercial electroencephalogram. In particular, we focus on three consequential research questions: is it possible to statistically distinguish a flow from a boredom condition? Which wavelengths are significant for such a classification? Can different levels of boredom and flow be identified? This work gives initial positive answers. Results, even if limited because of the small size of the test, are promising and enable further research. New, more extensive experiments are needed to better interpret some results of the wave spectrum analysis, also exploiting a better characterization of the actual activities and conditions of the user during the tests. Support Vector Machine (SVM) classification achieved significant accuracy results in the 2-level analysis case, in particular with personalized training (81% average accuracy).