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

TL;DR

This study identifies reproducible physiological features linked to arousal in affective computing, emphasizing the importance of rigorous validation for reliable emotion recognition models in safety-critical applications.

Contribution

It introduces a systematic feature selection method demonstrating that only a few electrodermal features are reliably associated with arousal, highlighting reproducibility issues in physiological feature analysis.

Findings

Only two electrodermal features showed reproducible arousal association.

The feature selection method effectively controls false discovery rate.

Reproducibility is crucial for trustworthy affective computing models.

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.