Personality cannot be predicted from the power of resting state EEG

TL;DR

This study investigated whether resting state EEG data can predict personality traits and found that it cannot reliably do so, suggesting the method is too noisy for accurate personality decoding.

Contribution

The paper provides evidence that resting state EEG power spectra do not predict personality traits, challenging previous assumptions about EEG's predictive capabilities for personality.

Findings

Personality traits cannot be predicted from resting state EEG.

EEG data successfully classified eyes open/closed and gender.

Resting state EEG power spectra are too noisy for personality prediction.

Abstract

In the present study we asked whether it is possible to decode personality traits from resting state EEG data. EEG was recorded from a large sample of subjects (N = 309) who had answered questionnaires measuring personality trait scores of the 5 dimensions as well as the 10 subordinate aspects of the Big Five. Machine learning algorithms were used to build a classifier to predict each personality trait from power spectra of the resting state EEG data. The results indicate that the five dimensions as well as their subordinate aspects could not be predicted from the resting state EEG data. Finally, to demonstrate that this result is not due to systematic algorithmic or implementation mistakes the same methods were used to successfully classify whether the subject had eyes open or eyes closed and whether the subject was male or female. These results indicate that the extraction of personality traits from the power spectra of resting state EEG is extremely noisy, if possible at all.