GameVibe: a multimodal affective game corpus

2024-06-17

Scientific Data

AI Summary

Current multimodal affective computing lacks high-quality, game-specific audiovisual stimuli datasets. Method: This study introduces GameVibe—the first multimodal affective corpus explicitly designed for gaming contexts—comprising high-fidelity gameplay videos from 30 representative games, fine-grained player behavioral logs, and continuous affect annotations from third-party viewers. It innovatively integrates in-game behavior, audiovisual content, and cross-perspective affective responses, employing a systematic audio-video-gameplay tridimensional diversity sampling strategy. Annotation consistency is rigorously quantified using Krippendorff’s Alpha (α > 0.8). Contribution/Results: GameVibe is publicly released and covers major genres—including RPG, FPS, and simulation—establishing the first benchmark resource and methodological paradigm for AIGC-driven affective interaction modeling and immersive experience research.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Computer Vision: Multi-modal Vision

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience

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.

Problem

• Lack of high-quality multimodal affective datasets
• Need diverse audiovisual stimuli for gaming research
• Assessing annotator reliability for affective traces

Innovation

• Multimodal audiovisual stimuli dataset
• In-game behavioral observations included
• High-quality diverse gameplay videos