Mapping Emotions in the Brain: A Bi-Hemispheric Neural Model with Explainable Deep Learning

2025-07-16

AI Summary

Existing bilateral-hemisphere EEG emotion recognition models suffer from insufficient interpretability in affective computing and cognitive modeling. Method: We propose an interpretability-enhancement framework tailored to a dual-pathway neural architecture: (i) a two-branch RNN model simulating parallel left- and right-hemisphere processing, trained on the EmoNeuroDB dataset acquired under VR-based emotional elicitation; (ii) a modified LIME algorithm enabling fine-grained attribution decomposition per electrode channel and emotion class; and (iii) symmetric-electrode correlation analysis to quantify hemispheric lateralization effects. Contribution/Results: This work is the first to systematically uncover emotion-specific neural lateralization patterns—e.g., left-frontal bias for joy and right-posterior bias for sadness—whose consistency with established neuroscientific findings substantially improves mechanistic interpretability and cross-domain credibility of EEG-based emotion models.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Recent advances have shown promise in emotion recognition from electroencephalogram (EEG) signals by employing bi-hemispheric neural architectures that incorporate neuroscientific priors into deep learning models. However, interpretability remains a significant limitation for their application in sensitive fields such as affective computing and cognitive modeling. In this work, we introduce a post-hoc interpretability framework tailored to dual-stream EEG classifiers, extending the Local Interpretable Model-Agnostic Explanations (LIME) approach to accommodate structured, bi-hemispheric inputs. Our method adapts LIME to handle structured two-branch inputs corresponding to left and right-hemisphere EEG channel groups. It decomposes prediction relevance into per-channel contributions across hemispheres and emotional classes. We apply this framework to a previously validated dual-branch recurrent neural network trained on EmoNeuroDB, a dataset of EEG recordings captured during a VR-based emotion elicitation task. The resulting explanations reveal emotion-specific hemispheric activation patterns consistent with known neurophysiological phenomena, such as frontal lateralization in joy and posterior asymmetry in sadness. Furthermore, we aggregate local explanations across samples to derive global channel importance profiles, enabling a neurophysiologically grounded interpretation of the model's decisions. Correlation analysis between symmetric electrodes further highlights the model's emotion-dependent lateralization behavior, supporting the functional asymmetries reported in affective neuroscience.

Problem

• Enhancing interpretability of bi-hemispheric EEG emotion recognition models
• Explaining emotion-specific hemispheric activation patterns in deep learning
• Validating neural model decisions with neurophysiological emotion asymmetry

Innovation

• Bi-hemispheric deep learning for EEG emotion recognition
• Post-hoc interpretability framework for dual-stream classifiers
• LIME adaptation for structured two-branch EEG inputs