A Controlled Set-Up Experiment to Establish Personalized Baselines for Real-Life Emotion Recognition

TL;DR

This study develops a personalized baseline method for real-life emotion recognition using physiological sensors, incorporating adaptive stimuli selection and achieving promising accuracy with minimal features.

Contribution

It introduces a novel adaptive stimuli-selection mechanism for personalized emotion recognition experiments, enhancing ground-truth reliability with minimal sensor features.

Findings

Achieved 85% accuracy in emotion prediction.

Few easy-to-implement features are sufficient for reliable recognition.

Adaptive stimuli selection improves personalized baseline establishment.

Abstract

We design, conduct and present the results of a highly personalized baseline emotion recognition experiment, which aims to set reliable ground-truth estimates for the subject's emotional state for real-life prediction under similar conditions using a small number of physiological sensors. We also propose an adaptive stimuli-selection mechanism that would use the user's feedback as guide for future stimuli selection in the controlled-setup experiment and generate optimal ground-truth personalized sessions systematically. Initial results are very promising (85% accuracy) and variable importance analysis shows that only a few features, which are easy-to-implement in portable devices, would suffice to predict the subject's emotional state.