From Pixels to Affect: A Study on Games and Player Experience
This work addresses the problem of affect prediction for affective computing, with potential applications in gaming and beyond, though it is incremental as it applies existing deep learning methods to a new domain.
The paper tackled predicting player arousal from gameplay video using deep convolutional neural networks, achieving over 78% average accuracy and up to 98% best accuracy in classifying high vs low arousal levels on a dataset of 50 videos.
Is it possible to predict the affect of a user just by observing her behavioral interaction through a video? How can we, for instance, predict a user's arousal in games by merely looking at the screen during play? In this paper we address these questions by employing three dissimilar deep convolutional neural network architectures in our attempt to learn the underlying mapping between video streams of gameplay and the player's arousal. We test the algorithms in an annotated dataset of 50 gameplay videos of a survival shooter game and evaluate the deep learned models' capacity to classify high vs low arousal levels. Our key findings with the demanding leave-one-video-out validation method reveal accuracies of over 78% on average and 98% at best. While this study focuses on games and player experience as a test domain, the findings and methodology are directly relevant to any affective computing area, introducing a general and user-agnostic approach for modeling affect.