The Prediction Value of EEG in Neuromarketing: Advertising Videos and Consumer Engagement

Abstract

Introduction

Neuromarketing techniques can improve the prediction of consumer behavior by measuring implicit physiological consumer responses unobservable through traditional methods. Neural measures have the potential as unbiased predictors, overcoming the limitations of subjective measures used in marketing research [1]. Many findings attempt to predict preference based on various features of the EEG signal. Alpha frequency suppression is a recognized indicator of mental activity and engagement, e.g., when paying close attention to any kind of stimulus [2]. EEG shows promise for predicting consumer response, but its contribution to preference prediction beyond traditional measures requires further research.

Methods

A total of 40 university students will be recruited for the study. In a within-subjects design, participants will be presented with a set of video ads from a video advertisement database with performance metrics selected from the Golden Drum advertising festival. Video ads will be divided into two major groups depending on whether they have received an award at the festival or not and further divided into groups based on the year of production and content. The videos will be displayed on a computer screen, and the participants' EEG oscillations will be recorded simultaneously to measure the neural correlates of the engagement with presented audiovisual stimuli. Engagement with each video will be rated using a 5-point Likert scale. We presume to see a difference in engagement between selected groups of videos. EEG data will be pre-processed and frequency analyses will be performed to calculate power change in alpha frequency for each subject. A multiple regression analysis will be conducted to evaluate the predictive value of different models. Additional analysis will be performed on subgroups.

Expected Results and Discussion

It is expected that the awarded videos will lead to higher levels of engagement, as measured by both EEG and self-reported responses. We expect the relative power change in the alpha frequency band will be greater for winning videos than for non-winning videos compared to the average alpha power across all videos. This interdisciplinary study's results will add valuable insights to the growing research on consumer neuroscience and examine the impact of audiovisual stimuli on engagement and associated neural processes.

References

[1] A. Hakim and D. J. Levy, "A gateway to consumers' minds: Achievements, caveats, and prospects of electroencephalography-based prediction in neuromarketing," WIREs Cognitive Science, vol. 10, no. 2, article e1485, 2019, doi: 10.1002/wcs.1485

[2] G. Pfurtscheller and A. Aranibar, "Event-related cortical desynchronization detected by power measurements of scalp EEG," Electroencephalography and Clinical Neurophysiology, vol. 42, no. 6, pp. 817-826, 1977, doi: 10.1016/0013-4694(77)90235-8