Reproducible Physiological Features in Affective Computing: A Preliminary Analysis on Arousal Modeling

2025-08-14

AI Summary

In affective computing, establishing reliable and reproducible associations between subjective emotional states and objective physiological markers remains challenging. This study focuses on arousal modeling, extracting 164 physiological features from electrocardiogram (ECG) and electrodermal activity (EDA) signals in the CASER dataset. We apply T-Rex (Terminating-Random Experiments), a rigorous variable-selection framework that controls the false discovery rate, to identify replicable feature–arousal associations. Across 30 participants, only two EDA-derived features—namely, skin conductance response (SCR) amplitude and recovery slope—consistently exhibited significant associations with continuous self-reported arousal (100% validation accuracy), underscoring the necessity of high-stringency evaluation. To our knowledge, this is the first work to introduce T-Rex to affective physiological modeling, yielding a transparent, interpretable, and highly reproducible feature-selection paradigm. The approach advances methodological rigor for trustworthy affective computing, particularly in safety-critical applications.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Machine Learning: Dimensionality Reduction/Feature Selection

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

In Affective Computing, a key challenge lies in reliably linking subjective emotional experiences with objective physiological markers. This preliminary study addresses the issue of reproducibility by identifying physiological features from cardiovascular and electrodermal signals that are associated with continuous self-reports of arousal levels. Using the Continuously Annotated Signal of Emotion dataset, we analyzed 164 features extracted from cardiac and electrodermal signals of 30 participants exposed to short emotion-evoking videos. Feature selection was performed using the Terminating-Random Experiments (T-Rex) method, which performs variable selection systematically controlling a user-defined target False Discovery Rate. Remarkably, among all candidate features, only two electrodermal-derived features exhibited reproducible and statistically significant associations with arousal, achieving a 100% confirmation rate. These results highlight the necessity of rigorous reproducibility assessments in physiological features selection, an aspect often overlooked in Affective Computing. Our approach is particularly promising for applications in safety-critical environments requiring trustworthy and reliable white box models, such as mental disorder recognition and human-robot interaction systems.

Problem

• Identifying reproducible physiological features for arousal modeling
• Linking subjective emotions with objective physiological markers
• Ensuring feature reproducibility in Affective Computing applications

Innovation

• Identify reproducible physiological arousal features
• Use T-Rex for controlled feature selection
• Focus on electrodermal-derived reliable markers