GameVibe: A Multimodal Affective Game Corpus

TL;DR

GameVibe is a new multimodal affective game corpus with diverse gameplay videos and affect annotations, designed to support affective computing research involving audiovisual stimuli and viewer engagement analysis.

Contribution

It introduces a high-quality, diverse multimodal dataset of gameplay videos with affect annotations, filling a gap in available resources for affective computing research.

Findings

High inter-annotator agreement demonstrated reliability

Diverse set of 30 games enhances generalizability

Rich multimodal data supports advanced affective analysis

Abstract

As online video and streaming platforms continue to grow, affective computing research has undergone a shift towards more complex studies involving multiple modalities. However, there is still a lack of readily available datasets with high-quality audiovisual stimuli. In this paper, we present GameVibe, a novel affect corpus which consists of multimodal audiovisual stimuli, including in-game behavioural observations and third-person affect traces for viewer engagement. The corpus consists of videos from a diverse set of publicly available gameplay sessions across 30 games, with particular attention to ensure high-quality stimuli with good audiovisual and gameplay diversity. Furthermore, we present an analysis on the reliability of the annotators in terms of inter-annotator agreement.