Affective Air Quality Dataset: Personal Chemical Emissions from Emotional Videos

2025-09-19

AI Summary

Existing emotion sensing technologies face significant challenges regarding user privacy and physical comfort, particularly due to intrusive physiological monitoring or camera-based behavioral analysis. Method: This work proposes a novel, non-contact paradigm for emotion recognition based on individual chemical emissions—specifically volatile organic compounds (VOCs) in breath and body odor—using gas sensor arrays. We introduce the first publicly available Affective Air Quality (AAQ) dataset, comprising four-channel gas sensor measurements from 23 participants exposed to emotion-eliciting films, synchronized with subjective affect ratings and privacy perception interviews. We design dual-distance (wearable and desktop) gas-sensing configurations and integrate chemical signal acquisition into affective computing pipelines, accompanied by formal privacy impact assessment. Contribution/Results: Statistical analysis confirms significant associations between VOC emission patterns and emotional states (e.g., pleasure, stress). Preliminary classification models achieve distinguishable performance across emotion categories. This study establishes a low-intrusion, privacy-preserving framework and provides a foundational benchmark dataset for chemical-signal-based affective computing.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Emotional Intelligence
• Computer Vision: Bias, Fairness & Privacy

Application Category

• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Inspired by the role of chemosignals in conveying emotional states, this paper introduces the Affective Air Quality (AAQ) dataset, a novel dataset collected to explore the potential of volatile odor compound and gas sensor data for non-contact emotion detection. This dataset bridges the gap between the realms of breath & body odor emission (personal chemical emissions) analysis and established practices in affective computing. Comprising 4-channel gas sensor data from 23 participants at two distances from the body (wearable and desktop), alongside emotional ratings elicited by targeted movie clips, the dataset encapsulates initial groundwork to analyze the correlation between personal chemical emissions and varied emotional responses. The AAQ dataset also provides insights drawn from exit interviews, thereby painting a holistic picture of perceptions regarding air quality monitoring and its implications for privacy. By offering this dataset alongside preliminary attempts at emotion recognition models based on it to the broader research community, we seek to advance the development of odor-based affect recognition models that prioritize user privacy and comfort.

Problem

• Exploring volatile compounds for non-contact emotion detection
• Bridging personal chemical emissions with affective computing
• Developing privacy-conscious odor-based affect recognition models

Innovation

• Multi-channel gas sensor data collection system
• Wearable and desktop distance measurement setup
• Odor-based emotion recognition models prioritizing privacy