Subject-Specific Feature Identification of Arousal and Valence Based on EEG

Emotions play a critical role in shaping our daily experiences by influencing decision-making, perception, learning, thinking, and behavior. Electroencephalographic (EEG) recordings are commonly utilized to measure brain activity, offering valuable insights into emotional states and allowing researchers to gain deeper understanding of the mechanisms underlying affective processes. The goals of this study are to establish a protocol using validated stimuli from literature to evaluate the effectiveness of EEG signals on an individual level for classifying arousal and valence of elicited stimuli and to identify the most effective feature space, brain regions, and signal frequencies for this purpose. To this extent, specific experimental procedures were employed to elicit four emotions, and standardized preprocessing, feature extraction, selection, and classification processes across subjects were applied to evaluate affective decoding. Classification of arousal and valence levels as binary tasks achieved highest accuracy when utilizing frequency domain features, with 80.1% for arousal and 74.8% for valence. Frequency domain features proved particularly effective in distinguishing varying levels of arousal and valence. The frontal and central cortices emerged as crucial in cognitive processing related to emotion, with higher EEG frequency bands closely associated with emotion processing. Nonetheless, the delta band also showed significance in classification and warrants further exploration, particularly regarding arousal. The study refines EEG-based arousal and valence classification, highlighting optimal feature space, brain regions, and frequency bands, thereby advancing understanding of affective processes.