Quantitative Personality Predictions from a Brief EEG Recording

Abstract

The assessment of personality is crucial not only for scientific inquiries but also for real-world applications such as personnel selection. However, most existing ways to quantify personality traits rely on self-reported scales, which are susceptible to biases such as self-presentational concerns. In this study, we propose and evaluate a novel implicit measure of personality that uses machine learning (ML) algorithms to predict an individual's levels in the Big Five personality traits from 5 minutes of electroencephalography (EEG) recordings. Results from a large test sample of 196 volunteers indicated that the personality scores derived from the proposed measure converged significantly with a commonly used questionnaire, predicted behavioral indices and psychological adjustment in a manner similar to self-reported scores, and were relatively stable across time. These evaluations suggest that the proposed measure can serve as a viable alternative to conventional personality questionnaires in practice.

The Big Five personality traits and CNS arousal in the resting state

“…Lastly, it should be noted that the present study sought to answer the question of whether CNS arousal but not the EEG, in general, is predictive for basic personality traits. Stronger associations may be derived by the application of machine learning models trained on the EEG to directly predict human personality (for an example see Li et al, 2019).…”

Measurement of High-School Students’ Trait Math Anxiety Using Neurophysiological Recordings During Math Exam

“…To conduct an overall evaluation of the feasibility of implementing a predictive model of MA by using neurophysiological signals, regression analyses were performed, using the self-reported MA scores (MLA, MEA, and MA total) as dependent variables and the 1-minute based neurophysiological data as independent variables. A leave-one-out cross-validation (LOOCV) strategy as used in previous studies [51]- [53] was applied. Specifically, the predicted MA scores of each participant was obtained by regression models based on the data from the other participants.…”

Design and implementation of an EEG-based recognition mechanism for the openness trait of the Big Five

“…One feasible solution is to use electroencephalograph (EEG), which is wearable, relatively inexpensive, and high-temporal. By reason of the connection between personality traits and emotional experience, most EEG-based studies of the Big Five focused on task-state EEG signals (De Pascalis et al, 2004 ; Speed et al, 2015 ; Suzuki et al, 2019 ; Li et al, 2020a , b ). Accordingly, among these works, emotional-related materials (e.g., emotional videos and words) were used as a stimulus for all the Big Five traits (De Pascalis et al, 2004 ; Speed et al, 2015 ; Suzuki et al, 2019 ; Li et al, 2020a , b ).…”

“…By reason of the connection between personality traits and emotional experience, most EEG-based studies of the Big Five focused on task-state EEG signals (De Pascalis et al, 2004 ; Speed et al, 2015 ; Suzuki et al, 2019 ; Li et al, 2020a , b ). Accordingly, among these works, emotional-related materials (e.g., emotional videos and words) were used as a stimulus for all the Big Five traits (De Pascalis et al, 2004 ; Speed et al, 2015 ; Suzuki et al, 2019 ; Li et al, 2020a , b ). However, as mentioned above, openness had its particularity, that is, it was more connected with intelligence and cognitive ability than with emotional factors (DeYoung et al, 2005 ; Llúıs-Font, 2005 ), which resulted in inconsistent statistical results in emotional-related studies (De Pascalis et al, 2004 ; Zhao et al, 2017 ).…”