Resting State EEG for Personality Traits Classification

Personality classification is instrumental in gaining a comprehensive understanding of human behavior and individual differences. The pandemic has brought substantial transformations in lifestyle and difficulties, thereby rein-forcing the necessity for personality evaluation. Personality classification facilitates in comprehending individuals’ cognitive and emotional responses to stressful circumstances, as well as their potential implications for mental well-being, adaptability in the workforce, effective communication, and public health communication. Resting state EEG analysis offers a realistic evaluation of brain function and connectivity by capturing the inherent brain activity and enabling us to grasp the underlying neural processes communication. Patterns and features discerned from the analysis of resting state EEG data have the potential to serve as biomarkers for personality assessment. These biomarkers, in conjunction with the capabilities of machine learning, can prove valuable in developing automated personality classifiers with enhanced precision. To explore the feasibility of personality categorization from resting state EEG, power spectral characteristics derived from EEG and self-reported assessments (NEO-FFI scores) are fed as an input to the Support Vector Machine (SVM) classifier. The preliminary results have demonstrated encouraging results and substantiated our assertion that personality traits can be assessed from resting state EEG data. Based on our findings, it is feasible to classify personality traits in accordance with the Big Five model with an approximate accuracy of 70%.