Attentional Bias Pattern Recognition in Spiking Neural Networks from Spatio-Temporal EEG Data
- 328 Downloads
When facing with different marketing product features, consumers are unaware of the important role of external stimuli on their decision-making behaviour. Neuromarketing background suggested that consumers might be seduced by the attentional bias which can direct their decision. This study aims at modelling and visualisation of the brain activity patterns generated by marketing product features with respect to the spatio-temporal relationships between the continuous EEG data streams. This research utilises brain-like Spiking Neural Network (SNN) models for analysing spatio-temporal brain patterns generated by attentional bias. The model was applied to Electroencephalogram (EEG) data for investigating the effectiveness of attentional bias on consumer preference towards marketing stimuli. Our experimental results have shown that consumers were more likely to get distracted by product features that are related to their subconscious preferences. This paper proofs that consumers pay the highest attention to non-target stimuli when they were presented with attractive features. This study provided a proof of principle for the role of attentional bias on concern-related human preferences. It represents knowledge discovery in the prediction of consumer preferences in the field of neuromarketing. The SNN-based models performed superior not only in achieving a higher classification of EEG data related to different stimuli in comparison with traditional methods, but it most importantly enables a better interpretation and understanding of underpinning brain functions against marketing stimuli.
KeywordsNeuromarketing Attentional bias Consumer preferences Decision making NeuCube Spiking neural networks Spatio-temporal brain data
This study is supported by Knowledge Engineering and Discovery Research Institute (KEDR), Auckland University of Technology (AUT), New Zealand.
Compliance with Ethical Standards
The contents of this study are the authors’ original work and the manuscript has not been published or submitted for publication elsewhere. Also we declare there was no disclosure of any financial support, conflict of interest to be made.
The EEG data was collected from human participants. Prior to EEG data collection, ethical approval was granted by Ethics Committee of Auckland University of Technology (AUTEC) New Zealand, and informed consent was signed by every single subjects.
- 2.Nazari M, Doborjeh ZG, Oghaz TA, Fadardi JS, Yazdi SA. Evaluation of consumers’ preference to the brands of beverage by means of ERP pre-comprehension component. In: Proceedings of the International Conference on Global Economy, Commerce and Service Science (GECSS), Thailand 2014 Jan 9, pp: 294–297.Google Scholar
- 3.Harrison NR, McCann A. The Effect of Colour and Size on Attentional Bias to Alcohol-Related Pictures. Psicol: Int J Methodol Exp Psychol. 2014;35(1):39–48.Google Scholar
- 8.Luijten M, Veltman DJ, Hester R, Smits M, Pepplinkhuizen L, Franken IH. Brain activation associated with attentional bias in smokers is modulated by a dopamine antagonist. Neuro-psychoanalysis. 2012;37(13):2772–9.Google Scholar
- 9.Paugam-Moisy H, Bohte S. Computing with spiking neuron networks. In: Handbook of natural computing 2012 (pp. 335–376). Springer Berlin Heidelberg.Google Scholar
- 12.Modha DS. Introducing a Brain-inspired Computer. IBM Research, accessed at www. Research. ibm. Com/articles/brain-chip. shtml. 2014.Google Scholar
- 14.Yadava M, Kumar P, Saini R, Roy PP, Dogra DP. Analysis of EEG signals and its application to neuromarketing. Multimedia Tools Appl. 2017:1–25.Google Scholar
- 18.Doborjeh ZG, Doborjeh MG, Kasabov N. Efficient recognition of attentional bias using EEG data and the NeuCube evolving spatio-temporal data machine. In: International Conference on Neural Information Processing. Springer International Publishing; 2016. pp. 645–53.Google Scholar
- 19.Kawano H, Seo A, Doborjeh ZG, Kasabov N, Doborjeh MG. Analysis of similarity and differences in brain activities between perception and production of facial expressions using EEG DATA and the NeuCube spiking neural network architecture. In: International Conference on Neural Information Processing. Springer International Publishing; 2016. pp. 221–7.Google Scholar
- 20.Capecci E, Doborjeh ZG, Mammone N, La Foresta F, Morabito FC, Kasabov N. Longitudinal study of Alzheimer’s disease degeneration through EEG data analysis with a NeuCube spiking neural network model. In: Neural Networks (IJCNN), 2016 International Joint Conference on 2016 Jul 24. IEEE. pp. 1360–6.Google Scholar
- 24.García-Larrea L, Lukaszewicz AC, Mauguiére F. Revisiting the oddball paradigm. Non-target vs neutral stimuli and the evaluation of ERP attentional effects. Neuro psychology. 1992;30(8):723–41.Google Scholar
- 25.Kasabov N, Zhou L, Doborjeh MG, Doborjeh ZG, Yang J. New algorithms for encoding, learning and classification of fMRI data in a spiking neural network architecture: a case on modelling and understanding of dynamic cognitive processes. IEEE Trans Cogn Dev Syst. 2016.Google Scholar
- 26.Tu E, Kasabov N, Yang J. Mapping temporal variables into the NeuCube for improved pattern recognition, predictive modelling, and understanding of stream data. IEEE Trans Neural Netw Learn Syst. 2016;15(99):1–13.Google Scholar