Valence-arousal evaluation using physiological signals in an emotion recall paradigm

TLDR

The valence‑arousal space is partitioned into negatively excited, positively excited, and calm‑neutral states. The study aims to assess human emotions using peripheral and EEG physiological signals. An emotion‑recall protocol collected peripheral and EEG data, and pattern‑classification models were trained to distinguish the three valence‑arousal states, with two classifiers evaluated on peripheral, EEG, and EEG‑with‑feature‑selection feature sets. Results show that EEG signals outperform peripheral signals in assessing valence and arousal during emotion recall.

Abstract

The work presented in this paper aims at assessing human emotions using peripheral as well as electroencephalographic (EEG) physiological signals. Three specific areas of the valence-arousal emotional space are defined, corresponding to negatively excited, positively excited, and calm-neutral states. An acquisition protocol based on the recall of past emotional events has been designed to acquire data from both peripheral and EEG signals. Pattern classification is used to distinguish between the three areas of the valence-arousal space. The performance of two classifiers has been evaluated on different features sets: peripheral data, EEG data, and EEG data with prior feature selection. Comparison of results obtained using either peripheral or EEG signals confirms the interest of using EEG's to assess valence and arousal in emotion recall conditions.