EEG-based detection of emotional valence towards a reproducible measurement of emotions

TLDR

Valence detection is framed within the interval scale of the Circumplex Model of emotions. The study proposes a reproducible EEG‑based measurement of emotions, beginning with a binary positive/negative valence classification as an initial step toward finer metric scaling. EEG signals were recorded with an 8‑channel dry electrode cap while participants passively viewed standardized visual stimuli from the Oasis dataset; features were extracted using both theory‑driven hemispheric asymmetry and an automated 12‑band filter bank with CSP, then classified by a shallow ANN and k‑NN. The sample matched the Oasis dataset per SAM, and the ANN achieved 96.1 % within‑subject accuracy while k‑NN reached 80.2 % cross‑subject accuracy.

Abstract

Abstract A methodological contribution to a reproducible Measurement of Emotions for an EEG-based system is proposed. Emotional Valence detection is the suggested use case. Valence detection occurs along the interval scale theorized by the Circumplex Model of emotions. The binary choice, positive valence vs negative valence, represents a first step towards the adoption of a metric scale with a finer resolution. EEG signals were acquired through a 8-channel dry electrode cap. An implicit-more controlled EEG paradigm was employed to elicit emotional valence through the passive view of standardized visual stimuli (i.e., Oasis dataset) in 25 volunteers without depressive disorders. Results from the Self Assessment Manikin questionnaire confirmed the compatibility of the experimental sample with that of Oasis . Two different strategies for feature extraction were compared: (i) based on a-priory knowledge (i.e., Hemispheric Asymmetry Theories), and (ii) automated (i.e., a pipeline of a custom 12-band Filter Bank and Common Spatial Pattern). An average within-subject accuracy of 96.1 %, was obtained by a shallow Artificial Neural Network, while k -Nearest Neighbors allowed to obtain a cross-subject accuracy equal to 80.2%.