Cnn classifies extraversion from brief eeg segments efficiently
CNN-based classifier for subject-independent MBTI Extraversion/Introversion preference classification from short-time EEG signals
Machine Learning
Summary
This study looks at whether short bursts of brain activity data (EEG) can tell if someone is more outgoing or reserved, based on a common personality test. The authors tested three different computer models to see which could best guess this personality trait without needing extra complicated data processing. They found their new model, SSCNet, was the most accurate and fastest at learning from the EEG data. This means simple brain data might reveal something about personality, and it also shows how important it is to test models on new people and keep them efficient.
What this means in practice
- •For neurotechnology developers: Create lightweight EEG-based tools that infer personality traits for personalized user experiences using short brain signal recordings.$Commercial implications: Enables new brain-computer interface products that adapt to user personality traits detected quickly and efficiently from EEG data.
- •For mental health app developers: Incorporate fast EEG signal analysis to help tailor mental wellness programs based on inferred extraversion or introversion tendencies.
Tested on one dataset.
Authors
Filip Postepski, Grzegorz M. Wojcik
Abstract
This study examines whether short, minimally preprocessed EEG segments contain sufficient information to distinguish between individuals classified as extraverted or introverted according to the Myers--Briggs Type Indicator (MBTI). EEG recordings from 50 participants were divided into 4-s segments and analyzed using a subject-independent nested 5-fold cross-validation procedure to compare EEGNet, EEGProgress, and a newly proposed compact convolutional architecture, SSCNet. SSCNet achieved the highest mean accuracy (0.6481), AUC (0.7063), and F1-score (0.6276). The proposed architecture also showed the lowest variability across folds. SSCNet demonstrated the best computational efficiency, with the shortest median training epoch time and the highest training throughput despite having a similar number of trainable parameters to EEGProgress. The results suggest that MBTI Extraversion--Introversion preferences may be moderately predictable from short time-domain EEG segments without manual spectral feature extraction, while highlighting the importance of subject-independent validation and computationally efficient model design.