Neuromarketing

Abstract

This study explores the use of electroencephalography (EEG) in understanding emotional re sponses to video stimuli, contributing to the field of neuromarketing. Participants viewed 20 video clips categorized into four emotional quadrants: High Valence High Arousal (HVHA), High Valence Low Arousal (HVLA), Low Valence High Arousal (LVHA), and Low Valence Low Arousal (LVLA). EEG data was analyzed for power spectral density, topographic distributions, and frequency band activity to examine neural correlates of valence and arousal. The results demonstrated significant differences in brain activity patterns, with frontal and temporal regions showing heightened engagement during high arousal states. Machine learning models such as Random Forest and CNN were employed for emotion classification, with modest accuracy im provements observed with larger data samples. These findings underscore EEG’s potential in decoding consumer emotions and guiding computational advertising strategies.