Related Experiment Video
Updated: Dec 22, 2025
08:31
Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
Published on: July 31, 2016
14.3K
Automatic Recognition of Personality Profiles Using EEG Functional Connectivity During Emotional Processing
Manousos A Klados1,2, Panagiota Konstantinidi2,3, Rosalia Dacosta-Aguayo4
1Department of Psychology, University of Sheffield, International Faculty, CITY College, Thessaloniki 54453, Greece.
Brain Sciences
|May 8, 2020
Summary
This study accurately predicts personality traits using electroencephalogram (EEG) data during emotion processing. Machine learning models achieved high accuracy in identifying individual personality profiles from brain activity.
Area of Science:
- Neuroscience and Cognitive Science
- Human-Computer Interaction (HCI)
- Machine Learning Applications
Background:
- Personality recognition is key for personalized and realistic human-computer interaction.
- Understanding the neurobiological basis of personality requires analyzing brain activity.
- Previous attempts using resting-state electroencephalogram (EEG) showed limited success in personality prediction.
Purpose of the Study:
- To develop an automated method for personality recognition using EEG signals.
- To investigate the efficacy of EEG data acquired during emotion processing for personality profiling.
- To combine neuroscientific data with machine learning for enhanced user experience in HCI.
Main Methods:
- Utilized the AMIGOS dataset comprising EEG recordings from 37 healthy participants during emotion processing.
- Extracted brain network and graph theoretical parameters from cleaned EEG signals.
- Employed k-means for dichotomizing personality trait scores, feature selection for identifying key features, and Support Vector Machines (SVM) for classification.
Main Results:
- Achieved high classification accuracies for major personality traits: 83.8% for extraversion, 86.5% for agreeableness, 83.8% for conscientiousness, and 83.8% for neuroticism.
- Demonstrated a classification accuracy of 73% for openness.
- Successfully identified distinct personality profiles from EEG data with significant accuracy.
Conclusions:
- EEG recordings during emotion processing are effective for automated personality recognition.
- Machine learning techniques, particularly SVM, can accurately classify personality traits based on neurophysiological data.
- This approach holds promise for creating more adaptive and user-friendly HCI applications by understanding user personality.
