Related Experiment Video
Updated: Jul 25, 2025
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
3.9K
Personality-Based Emotion Recognition Using EEG Signals with a CNN-LSTM Network.
Mohammad Saleh Khajeh Hosseini1, Seyed Mohammad Firoozabadi2, Kambiz Badie3
1Department of Biomedical Engineering, Science and Research Branche, Islamic Azad University, Tehran 14778-93855, Iran.
Brain Sciences
|June 28, 2023
Summary
Integrating personality traits into electroencephalography (EEG) analysis significantly improves emotion recognition accuracy. This novel deep learning approach achieved 93.97% accuracy by combining convolutional neural networks and long short-term memory networks.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Psychology
Background:
- Accurate emotion detection is crucial for healthcare, psychology, and human-computer interaction.
- Integrating personality traits can enhance emotion recognition applications.
- Existing methods often overlook the influence of personality on emotional responses.
Purpose of the Study:
- To develop a novel deep learning model for emotion recognition using electroencephalography (EEG) signals.
- To investigate the impact of incorporating Big Five personality traits into emotion recognition.
- To enhance the accuracy and utility of emotion recognition systems.
Main Methods:
- Recruited 60 participants and collected EEG data during emotional stimuli presentation.
- Utilized a pre-trained Convolutional Neural Network (CNN) for emotion-related EEG feature extraction.
- Employed a Long Short-Term Memory (LSTM) network to extract Big Five personality traits from EEG data.
- Integrated extracted features into a novel network for predicting arousal and valence dimensions of emotional states.
Main Results:
- The model accurately predicted personality traits from EEG data.
- The proposed classifier achieved a high accuracy of 93.97% in emotion recognition.
- The integration of personality traits significantly improved emotion recognition performance compared to common classifiers.
Conclusions:
- Incorporating Big Five personality traits as features enhances deep learning-based emotion recognition accuracy.
- The developed model demonstrates the potential of combining EEG, personality traits, and deep learning for advanced emotion analysis.
- This approach holds promise for more personalized and effective applications in healthcare and human-computer interaction.
