Neurogaming-based Classification of Player Experience Using Consumer-Grade Electroencephalography

A growing body of literature has emerged that demonstrates the potential of neurogaming platforms for interfacing with well-known video games. With the recent convergence of advances in consumer electronics, ubiquitous computing, and wearable sensor technologies real-time monitoring of neurocognitive and affective states can be studied in an objective, timely, and ecologically valid manner. Whilst establishing the optimal relation among frequency bands, task engagement, and arousal states is one of the main goals of neurogaming, a standardized method has yet to be established. Herein we aimed to test classifiers within the same context, group of participants, feature extraction methods, and protocol. Given the emphasis upon neurogaming, the commercial-grade Emotiv EPOC headset was used to collect electroencephalographic (EEG) signals from users as participants experienced various stimulus modalities aimed at assessing cognitive and affective processing. The EEG data were then filtered to get separate frequency bands to train cognitive-affective classifiers with three classification techniques: Support Vector Machines (SVM), Naive Bayes (NB), and kNearest Neighbors (kNN). Results revealed that the NB classifier was the most robust classifier for identifying game-based Death Events. However, the identification of General Gameplay Events is best identified using kNN and the Beta band. From this study’s findings, it is suggested that using a combination of classifiers is preferable over selecting just one classifier.