EEG-based classification of positive and negative affective states

Abstract

This study aimed to identify the neurophysiological correlates of two primary aroused affective states related to positive and negative emotions, and to create a classification model for each second of data. General and individualized models were built on the EEG data recorded from 98 participants while watching two contrasting ~20 min videos – one to elicit a negative affective state, and the other to induce positive affect. The final models were cross-validated on an additional 63 participants and the classifiers achieved similar results. The classifiers’ generalization capability was further estimated in a related study where 63 participants returned to watch videos that incorporated narratives with varying levels of fairness, justice, and character identification.