Classification of “Like” and “Dislike” Decisions From EEG and fNIRS Signals Using a LSTM Based Deep Learning Network

Abstract

Neuromarketing is an innovative discipline that combines neuroscience with marketing and refers to analyzing physiological and brain signals to obtain insight into consumer behavior. The field's potential for reducing the uncertainty that has previously hindered marketing efforts to explain consumer behavior has accelerated growth within the area. Most recently, artificial intelligence (AI) has driven neuromarketing research forward by enabling researchers to conduct tests more effectively because AI assists in revealing patterns that were previously hard to detect. In this paper, deep learning is applied by employing a particular type of recurrent neural network called long short-term memory (LSTM) to recognize subject preferences from combined electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals.