Classification of Neuroticism using Psychophysiological Signals During Speaking Task based on Two Different Baseline Measurements
Keywords:Neuroticism, Electroencephalography (EEG), Heart rate, Skin conductance, Respiration rate, SVM, Classification
Biosignals from psychophysiological changes can be measured as electroencephalography (EEG), heart rate, skin conductance, and respiration rate, to name a few. They have been used in many research areas including human personality. Neuroticism, one of the five major traits underlie personality, reflects stable tendency towards experiencing negative emotions. An understanding of how neuroticism influences responses to psychological distress may shed a light upon individual differences in emotion self-regulation. To study the causal relationship between neuroticism and psychophysiological signals, a selection of appropriate baseline signals as a reference signal is essential to compare to current experimental signals of interest. Thus, we present classification of neuroticism using psychophysiological signals obtained during a speaking task based on two different baseline measurements (eyes closed and eyes open). Eight healthy male participants consisting of four neurotic and four emotionally stable subjects were recruited based on Eysenck Personality Inventory (EPI) and Big Five Inventory (BFI) scoring system. Four features including mean EEG beta power, heart rate, skin conductance, and respiration rate were used for the classification using a Support Vector Machine (SVM). The results showed higher classification accuracy achieved with eyes open as the baseline (62.5%) as compared to eyes closed as the baseline (37.5%), during speaking task. This indicate the importance of selecting appropriate baseline in analysis involving EEG and physiological signals.
How to Cite
Open access licenses
Open Access is by licensing the content with a Creative Commons (CC) license.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.