Detection of Consumer Preferences Using EEG Signals

Abstract

In this study, a liking estimation system based on electroencephalogram (EEG) signals is developed for neuromarketing applications. The determination of the degree of appreciation of a product by consumers has become an important research topic using machine learning methods. Biological data is recorded while viewing product pictures or videos, then processed by signal processing methods. In this study, 32 channel EEG signals are recorded from subjects who watched two different car advertisement videos and the liking status is determined. After watching the advertisement videos, the participants were asked to vote for the rating of the different images (front view, dashboard, side view, rear view, taillight, logo and grille) of the products. The signals corresponding to these different video regions from the EEG recordings were segmented and analyzed by the Empirical Mode Decomposition (EMD) and Ensemble Empirical Mode Decomposition (EEMD). The statistical features were extracted from Intrinsic Mode Functions (IMF) and the liking status classifications were performed. The classification performance of EMD- and EEMD-based methods are 93.4% and 97.8% respectively on Brand1, and 93.5% and 97.4% respectively on Brand2. In addition, the classification accuracy on both brands combined are 85.1% and 85.7% respectively. The promising results obtained using Support Vector Machines (SVM) show that the proposed EEG-based method may be used in neuromarketing studies.

Keywords

• EEG
• EEMD
• Empirical mode decomposition
• Liking status detection
• Neuromarketing

References

1. W. Gordon, “The Darkroom of the Mind: What Does Neuropsychology Now Tell Us About Brands?,” Journal of Consumer Behaviour, vol. 1, pp. 280-292, February 2002.
2. P. Aytekin and A. Kahraman, “Pazarlamada yeni bir araştırma yaklaşımı: Nöropazarlama (A New research approach in marketing: Neuromarketing),” Journal of Management, Marketing&Logistics – JMML, vol. 1, pp. 48-62, 2014.
3. N Lee, A. J. Broderick, and L. Chanberlain, “What is neuromarketing? A discussion and agenda for future research,” International Journal of Psychophysiology, vol. 63, no. 2, pp. 199-204, 2007.
4. M. Tanida, M. Okabe, K. Tagai, and K. Sakatani, “Evaluation of Pleasure-Displeasure Induced by Use of Lipsticks with Near-Infrared Spectroscopy (NIRS): Usefulness of 2-Channel NIRS in Neuromarketing,” in Oxygen Transport to Tissue XXXIX. Advances in Experimental Medicine and Biology, H. Halpern, J. LaManna, D. Harrison, and B. Epel, Ed. Cham: Springer, 2017, vol. 977.
5. R. Chark, “Neuromarketing,” in Innovative Research Methodologies in Management, L. Moutinho and M. Sokele, Ed. Cham: Palgrave Macmillan, 2018.
6. M. Soleymani, M. Pantic, and T. Pun, “Multimodal emotion recognition in response to videos,” IEEE Trans Affect Comput, vol. 3, pp. 211–223, 2012, DOI: (10.1109/T-AFFC.2011.37).
7. B. Knutson, S. Rick, E. G. Wimmer, D. Prelec, and G. Loewenstein, “Neural predictors of purchases,” Neuron, vol. 53, pp. 147–156, 2007.
8. N. K. Rami, W. Chelsea, K. Sarath, L. Jordan, and E. K. Barbara, “Consumer neuroscience: Assessing the brain response to marketing stimuli using electroencephalogram (EEG) and eye tracking,” Expert Systems with Applications, vol. 40, pp. 3803-3812, 2013.

9. https://imotions.com/biosensor/electroencephalography-eeg/. Accessed 28 September 2020.
10. J. Mc. Names, T. Thong., and M. Aboy, “Impulse Rejection Filters for Artifact Removal in Spectral Analysis of Biomedical Signals,” in IEEE Annual International Conference on EBMC, vol. 1, pp. 145-148, 2004.
11. N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, H. H. Shih, Q. Zheng, N. C. Yen, C. C. Tung, and H. H. Liu, “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,” Proc R Soc A Math Phys Eng Sci, vol. 454, pp. 903–995. 1998, DOI: (10.1098/rspa.1998.0193).
12. P. Özel, A. Akan, and B. Yılmaz, “Emotional State Analysis from EEG signals via Noise-Assisted Multivariate Empirical Mode Decomposition Method,” in 10th International Conference on Electrical and Electronics Engineering, Bursa, Türkiye, November 30 - December 02, 2017.
13. G. Rilling and P. Flandrin, “One or two frequencies? The empirical mode decomposition answers,” IEEE Trans Signal Process, vol. 56, pp. 85–95, 2008.
14. A. Mert and A. Akan, “Emotion recognition from EEG signals by using multivariate empirical mode decomposition,” Pattern Analysis and Applications, vol. 21, pp. 81-89, 2018.
15. A. Mert, F. Onay and A. Akan, “Empirical Mode Decomposition Based Feature Extraction for Intelligent Emotion Recognition,” in International Conference on Engineering Technologies (ICENTE), Konya, Türkiye, December 07 – December 09, 2017.
16. A. Mert and A. Akan, “Detrended fluctuation thresholding for empirical mode decomposition based denoising,” Digital Signal Processing , vol. 32, pp. 48–56, 2014.
17. B. Sharma and S. Kaur, “Distinction between EMD & EEMD Algorithm for Pitch Detection in Speech Processing,” International Journal of Engineering Trends and Technology (IJETT), vol. 7, no.3, 2014.
18. M. Murugappan, R. Nagarajan and S. Yaacob, “EEG Sinyalleri Kullanarak İnsan Duygularını Sınıflandırmak için Mekansal Filtreleme ve Dalgacık Dönüşümünü Birleştirmek,” Tıbbi ve Biyoloji Mühendisliği Dergisi, vol. 31, no. 1, pp. 45-51, 2011.
19. M. Robnik-Sikonja and I. Kononenko, “Theoretical and empirical analysis of ReliefF and RReliefF,” Machine Learning, vol. 53, pp. 23–69, 2003