Emotion and Mood Recognition

Embracing naturalistic paradigms: substituting GPT predictions for human judgments

This study evaluates GPT's ability to predict human affective judgments in narratives and finds it correlates with human ratings and neural activity inferences.

Spatiotemporal dynamics and substates underlie emotional signalling in facial movements

This paper analyzes spatiotemporal patterns in facial movements to identify emotion-specific dynamics and substates across non-verbal expressions and emotive speech.

Biologically Inspired Deep Neural Network Models for Visual Emotion Processing

This paper introduces a biologically inspired deep neural network model for visual emotion processing and shows it accurately predicts human emotion ratings and aligns with amygdala activity.

Improving Emotion Classification by Combining fNIRS-Derived Hemodynamic Responses with Peripheral Physiological Signals

This study combines fNIRS and peripheral physiological signals to improve arousal and valence classification, achieving F1 scores of 0.73 and 0.64 respectively.

Exploring the Neural Basis and Validity of Ordinal Emotion Representation through EEG

This study investigates the neural basis and validity of ordinal emotion representation using EEG data, showing it better captures emotional experiences than interval scales.

Emo-FilM: A multimodal dataset for affective neuroscience using naturalistic stimuli

The paper introduces Emo-FilM, a multimodal dataset combining fMRI, physiological recordings, and detailed emotion annotations from films to study emotion processing.

The Effect of Evaluating Self's Emotions on Frontal Alpha Asymmetry

This study shows that rating emotions during EEG measurements reduces frontal alpha asymmetry, suggesting evaluations amplify emotional brain activity.

Consistent movement of viewers' facial keypoints while watching emotionally evocative videos

The paper introduces a new metric for measuring consistent facial muscle movement across subjects using facial keypoint tracking, showing high correlation with direct FACS-based measurements.

Electrophysiological Representations of Multivariate Human Emotion Experience

This study identifies EEG representations of multivariate emotion experience using inter-situation RSA, finding significant correlations in Alpha and Beta bands over frontal and parietal-occipital regions.

Classification of Multiple Emotional States from Facial Expressions in Mice using a Deep Learning-Based Image Analysis

This paper develops a deep learning tool to classify three emotional states from mouse facial expressions and demonstrates its accuracy using Gradient-weighted Class Activation Mapping.

Quantifying dynamic facial expressions under naturalistic conditions

The paper quantifies dynamic facial expressions under naturalistic conditions and identifies distinct spatiotemporal states that vary between individuals with melancholic depression.

A Generalizable Speech Emotion Recognition Model Reveals Depression and Remission

This paper develops a speech emotion recognition model trained on non-clinical data to detect depression and remission in clinical speech, achieving an AUC of 0.71.

Classification of complex emotions using EEG and virtual environment: proof of concept and therapeutic implication

This paper classifies two complex emotions, tenderness and anguish, using EEG features from a virtual environment experiment, achieving 79.3% accuracy with random cross-validation.

Reliability of web-based affective auditory stimulus presentation

This study evaluates the reliability of affective auditory stimuli presented online, finding good test-retest reliability and internal consistency comparable to in-lab settings.

Cross-Subject EEG-Based Emotion Recognition through Neural Networks with Stratified Normalization

This study introduces stratified normalization for cross-subject EEG emotion classification, achieving higher accuracy than batch normalization.

Subject-independent decoding of affective states using functional near-infrared spectroscopy

This paper demonstrates subject-independent affective state decoding using fNIRS signals, achieving significant classification accuracies for positive, negative, and neutral emotional states.

Quantitative Personality Predictions from a Brief EEG Recording

This study uses machine learning to predict Big Five personality traits from 5 minutes of EEG data, showing convergence with self-reported scores and stability over time.

Quantification of anticipation of excitement with three-axial model of emotion with EEG

The paper introduces a three-axial model of emotion to quantify anticipatory excitement using EEG data from participants viewing emotional stimuli.

Exploring Deep Physiological Models for Nociceptive Pain Recognition

This paper uses deep learning to classify nociceptive pain levels from physiological signals, achieving higher accuracy than traditional feature-based methods.