Is Mate Preference Recognizable Based on Electroencephalogram Signals? Machine Learning Applied to Initial Romantic Attraction

• Published in: Frontiers in neuroscience Vol. 16; p. 830820
• Main Authors: Yuan, Guangjie, He, Wenguang, Liu, Guangyuan
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 11.02.2022; Frontiers Media S.A
• Subjects: aesthetic preference; Algorithms; Classification; Consciousness; EEG; Electroencephalography; Emotions; Experiments; frequency band; hemispheric asymmetries; Hemispheric laterality; Learning algorithms; Machine learning; mate choice; Mate selection; Neuroscience; physiological signals; Physiology; Preferences; Theta rhythms; physiological signals; aesthetic preference; hemispheric asymmetries; mate choice; frequency band
• ISSN: 1662-4548; 1662-453X; 1662-453X
• DOI: 10.3389/fnins.2022.830820

Initial romantic attraction (IRA) refers to a series of positive reactions toward potential ideal partners based on individual preferences; its evolutionary value lies in facilitating mate selection. Although the EEG activities associated with IRA have been preliminarily understood; however, it remains unclear whether IRA can be recognized based on EEG activity. To clarify this, we simulated a dating platform similar to Tinder. Participants were asked to imagine that they were using the simulated dating platform to choose the ideal potential partner. Their brain electrical signals were recorded as they viewed photos of each potential partner and simultaneously assessed their initial romantic attraction in that potential partner through self-reported scale responses. Thereafter, the preprocessed EEG signals were decomposed into power-related features of different frequency bands using a wavelet transform approach. In addition to the power spectral features, feature extraction also accounted for the physiological parameters related to hemispheric asymmetries. Classification was performed by employing a random forest classifier, and the signals were divided into two categories: IRA engendered and IRA un-engendered. Based on the results of the 10-fold cross-validation, the best classification accuracy 85.2% (SD = 0.02) was achieved using feature vectors, mainly including the asymmetry features in alpha (8-13 Hz), beta (13-30 Hz), and theta (4-8 Hz) rhythms. The results of this study provide early evidence for EEG-based mate preference recognition and pave the way for the development of EEG-based romantic-matching systems.