Psychophisiological Reactions to Advertising Video Materials and the Possibility of Neuroprediction of Commercial Success Based on Them

This master's thesis investigates the relationship between psychophysiological reactions to advertising video materials and their commercial success, focusing on the potential for neuroprediction. Utilizing advanced techniques in electroencephalography (EEG), heart rate variability (HRV), skin conductance response (SCR), and facial electromyography (EMG), the study aimed to uncover the neural and physiological patterns underlying consumer engagement and decision-making processes. Despite the detailed analysis of traditional psychophysiological metrics, such as EEG, HRV, SCR, and facial EMG, most measures did not exhibit strong correlations with the commercial success of the advertisements. This may be attributed to the inherent complexity of brain responses and individual differences among participants. However, machine learning models, particularly convolutional neural networks (CNNs), trained on the comprehensive psychophysiological data significantly outperformed traditional methods, achieving a prediction success rate of 72%. These findings highlight the potential of integrating machine learning techniques in neuromarketing to enhance the predictive accuracy of advertising effectiveness. The study underscores the importance of using sophisticated analytical approaches to account for the multifaceted nature of consumer responses and suggests directions for future research, including the consideration of additional variables such as blogger trustworthiness and audience history. This research contributes to the evolving field of neuromarketing by providing actionable insights that could optimize advertising strategies and improve their impact on consumer behavior.