Search Results (2,106)

Post-traumatic stress disorder (PTSD) is a severe condition triggered by traumatic exposure, characterized by symptoms like trauma re-experiencing, avoidance, mood alterations, hypervigilance, and sleep disturbances. While its exact mechanisms remain uncertain, PTSD involves dysregulation across neurobiological systems underlying fear conditioning, threat appraisal, executive control, and stress response. Although research highlights the sympathetic–adreno–medullary (SAM) system and the hypothalamic–pituitary–adrenal (HPA) axis, findings on stress-related mediators remain inconsistent regarding their precise contributions over time. To address this, we propose a hypothetical model viewing PTSD as a multistable system shifting from physiological to pathological steady states. We assume that intense, repeated emotional stress triggers spike activation in the amygdala, driving an amygdala–locus coeruleus loop into a high-activation state via reciprocal excitation, mediated by corticotropin-releasing hormone (CRH) and noradrenaline. This sequentially alters amygdala–hippocampus and prefrontal cortex loops, reinforcing fear expression and impairing extinction. This model is consistent with key features of PTSD, including its higher prevalence among females, increased glucocorticoid receptor sensitivity, the frequently observed hypocortisolism, and the partial efficacy of serotonin and norepinephrine reuptake inhibitor (SNRI) and CRH receptor antagonists. While requiring experimental validation, this framework connects molecular, circuit, and behavioral data to help identify novel interventions for restoring adaptive stress-response dynamics. Full article

Accurate emotion recognition is crucial for enhancing human–computer interaction, and brain–computer interface (BCI) technology offers an efficient means for emotion detection using the EEG signal. However, existing methods face significant challenges due to the inherent inter-individual differences and temporal variability of EEG data. To address these limitations, this paper introduces a multi-source domain adaptive algorithm based on dendrite net (DD-MSDA). The proposed model employs the dendrite network as a shared feature extractor to align feature distributions across multiple source domains, thereby capturing common features among diverse datasets. Experimental validation on cross-subject and cross-session tasks using the SEED and SEED-IV datasets demonstrates that DD-MSDA achieves highly competitive performance, outperforming all compared single-modal EEG-based domain adaptation methods. Moreover, the algorithm demonstrates statistically significant advantages over existing domain adaptation baselines in cross-dataset settings. These results highlight the consistent competitiveness of DD-MSDA across various cross-domain scenarios, and its unsupervised nature underscores its potential for practical online EEG emotion recognition applications. Full article

Facial emotion recognition plays an important role in affective computing and human–computer interaction. Although convolutional neural network (CNN)-based methods have demonstrated remarkable performance, deep features alone may not sufficiently capture subtle geometric deformations and local texture variations, particularly under limited training data and challenging real-world conditions. To address this limitation, this study proposes a hybrid framework that integrates CNN-based deep features with handcrafted geometric and texture features. Specifically, 17 landmark-based angular features extracted from the eyebrows, eyes, nose, and mouth are combined with histogram of oriented gradients (HOG) features extracted from the nose and mouth regions through feature-level concatenation. The proposed method was extensively evaluated on three controlled datasets (JAFFE, CK+, and KDEF) and two large-scale in-the-wild datasets (RAF-DB and AffectNet). Five-fold cross-validation, leave-one-subject-out cross-validation, statistical significance analysis using paired t-tests, computational efficiency analysis, and comparisons with conventional handcrafted methods, standard CNN models, transfer learning-based methods, and recent hybrid feature-fusion methods were performed to comprehensively validate the proposed approach. Experimental results demonstrated consistent improvements across different datasets, evaluation protocols, and CNN backbone networks while maintaining a favorable balance between recognition performance and computational efficiency. These findings demonstrate that handcrafted geometric and local texture features effectively complement CNN-based deep representations, providing a robust and generalizable framework for facial emotion recognition across both controlled and large-scale in-the-wild datasets. Full article

Background/Objectives: Perinatal loss is a profoundly distressing life event associated with grief, depression, anxiety, post-traumatic stress symptoms, and long-term psychosocial challenges among bereaved parents who experience miscarriage, stillbirth, or neonatal death. Although psychotherapeutic interventions are increasingly used to address these adverse outcomes, there is limited synthesis on how characteristics consistent with a patient-centered care perspective are reflected in such interventions and how they may relate to psychosocial well-being. This umbrella review aimed to synthesize evidence on psychotherapeutic interventions following perinatal loss and to examine patient-centered care–related dimensions reported across the included reviews, including therapeutic communication, patient engagement, therapeutic relationships, emotional validation, and meaning-making processes. Methods: An umbrella review was conducted in accordance with the Joanna Briggs Institute methodological guidance. Systematic reviews and meta-analyses published between 2019 and 2025 were identified through searches of PubMed, CINAHL, PsycINFO, and the Cochrane Library from database inception to 31 May 2026. Eligible reviews examined psychotherapeutic, psychosocial, and psychological support interventions designed to improve grief, depression, anxiety, post-traumatic stress symptoms, psychological distress, coping, and psychosocial well-being among bereaved parents following perinatal loss. In accordance with the predefined secondary exploratory objective, a secondary interpretive synthesis examined patient-centered care–related dimensions described within the included reviews. Results: Five systematic reviews and meta-analyses met the inclusion criteria. Interventions included cognitive behavioral therapy, mindfulness-based approaches, bereavement counseling, psychosocial support programs, narrative interventions, supportive counseling, and digitally delivered psychological therapies. Across reviews, psychotherapeutic interventions were generally associated with beneficial effects on grief, depression, anxiety, post-traumatic stress symptoms, and broader indicators of psychosocial well-being. Communication-, support-, and engagement-related characteristics consistent with a patient-centered care perspective, including empathy, therapeutic alliance, individualized support, emotional validation, and continuity of communication, were identified through secondary interpretive synthesis as recurring features of beneficial interventions. Digital modalities, such as internet-based cognitive behavioral therapy and telephone-delivered counseling, were consistently described as supporting accessibility, engagement, and continuity of care. Conclusions: Psychotherapeutic interventions following perinatal loss appear to improve a range of psychosocial outcomes. A patient-centered care perspective may help interpret how communication, emotional validation, patient engagement, and supportive therapeutic relationships are described in relation to psychological adaptation after loss. These dimensions should be understood as interpretive characteristics identified across the included reviews rather than as directly measured mechanisms of intervention effectiveness. Future research should examine communication processes, therapeutic alliance, and patient engagement using validated measures, assess how these factors relate to intervention effectiveness, and support the development of integrated, patient-centered models of perinatal bereavement care. Full article

Background: Depression is among the most prevalent psychiatric conditions and markedly disrupts everyday functioning. Its origins are multifactorial, with biological, psychological, and contextual influences jointly shaping the course of recovery and the response to treatment. Personality has been proposed as a relatively stable factor that may reflect developmental influences on emotional and cognitive functioning and may be associated with long-term clinical outcomes in depression. The present study aimed to examine the association between implicit personality characteristics in women hospitalized for depressive disorder and their long-term psychosocial functioning, using a performance-based measure of personality (the Rorschach Inkblot Method, RIM). Subjects and Methods: At baseline (T1), 58 women hospitalized for depressive disorder completed the Beck Depression Inventory (BDI-II) and the Rorschach Inkblot Method (RIM); Rorschach protocols were scored using the Ego Impairment Index—second revision (EII-2), a behaviorally derived index spanning perceptual accuracy, executive integrity, and social cognition. Demographic and clinical information was abstracted from medical records, and an independent rating of functioning was obtained with the Global Assessment of Functioning scale (GAF). Four years later (T2), patients were re-administered the BDI-II and the GAF, and major life events occurring during the follow-up interval were quantified with the Social Readjustment Rating Scale (SRRS). Results: Baseline implicit personality organization showed a significant association with psychosocial functioning four years after the index hospitalization. Among the variables examined, personality structure at admission outperformed both initial depressive symptom severity and the burden of intervening life events in predicting later functional status. In particular, EII-2 accounted for an additional 10.3% of the variance (ΔR² = 0.103, p < 0.05) over and above age, chronicity, stress, and depressive symptom severity when predicting four-year GAF-rated functioning. Among the predictors examined, age was the most influential variable in the final model (β = 0.442), indicating that demographic factors carry substantial weight alongside personality functioning in shaping long-term outcomes. Conclusions: Our findings are consistent with the view that a patient’s personality may influence the course of recovery and suggest that personality-level factors deserve attention when planning care for this clinically complex disorder. The present results indicate that implicit cognitive–perceptual features—assessed through performance-based methods that bypass conscious self-report—may be associated with long-term psychosocial functioning in women hospitalized for depression. These findings suggest that performance-based personality assessment deserves further study as a potential prognostic aid, although replication in larger and more diverse samples is needed before clinical application. Full article

This study addresses a limitation of the assumption in Kansei Engineering (KE) that morphological features contribute equally to affective evaluation by developing a KE framework based on the Feature Integration Theory (FIT). Specifically, eye-tracking data based on Areas of Interest (AOI) are used to calculate the coefficient of variation (CV) of fixation duration between stimuli, which is then applied to rescale morphological features before modeling. In practice, ten Ming-style chairs were encoded with 30 morphological features, and Kansei ratings were collected from 389 participants, along with eye-tracking data from 30 participants. Accordingly, six Partial Least Squares (PLS) models constructed based on the rescaled features demonstrated robust performance (Q² = 0.544–0.885), supported by LOOCV, bootstrap, and permutation tests, with external validation further confirming their generalizability. Notably, the results revealed a dissociation between fixation distribution and dispersion-based scaling, indicating that stable gaze concentration does not translate into higher predictive contributions in Kansei responses. This framework provides a repeatable method for incorporating visual attention variability into feature-based KE for product evaluation. Full article

In this paper we study how external affective information should be integrated into a compact transformer-based text classifier. Rather than treating affective features as signals to be appended directly to the representation, we examine whether their contribution should be controlled through lightweight fusion mechanisms. The comparison focuses on scalar-gated fusion versus plain concatenation, using DistilBERT as the textual backbone and four affective resources: the NRC VAD Lexicon, VAD-BERT, Ekman-style emotion scores, and SenticNet. The evaluation is conducted on two English corpora with different label structures: a seven-class MentalHealth dataset and the fine-grained GoEmotions benchmark. Across both corpora, scalar gating consistently matches or outperforms concatenation in terms of Macro-F1. On MentalHealth, scalar gating improves all directly comparable configurations. On GoEmotions, it achieves the best overall Macro-F1 and improves most matched comparisons. Beyond static feature integration, we introduce affective flow (EmoFlow) representations derived from VAD-BERT, which model the evolution of valence, arousal, and dominance across segments of a text. These dynamic representations do not surpass the strongest static lexical resources in absolute performance, but they provide consistent improvements within the VAD-BERT family, particularly when combined with scalar gating or cross-attention. Our contribution is twofold. First, we show that a lightweight scalar gate provides an effective and interpretable mechanism for adaptively integrating low-dimensional affective side information into transformer-based classifiers. Second, we introduce affective flow representations that explicitly model how affect evolves within a document, enabling the analysis of both adaptive resource selection and intra-document affective dynamics. Together, these results suggest that the key issue is not only which affective resources to use, but also when and how they should influence the model. Full article

This study compares the effectiveness of two approaches to speech emotion recognition for three affective states in Polish: sad, neutral, and happy. Both a set of acoustic features—capturing prosodic, phonatory, temporal, spectral, and cepstral properties—and representations learned by self-supervised models (wav2vec 2.0 and WavLM) were analyzed. Experiments were conducted on the nEMO corpus, comprising 2327 recordings from nine speakers, using a rigorous leave-one-subject-out protocol to evaluate cross-speaker generalization. In the feature-based approach, 107 acoustic features were used, and classification was performed with logistic regression and, additionally, SVM variants. In the deep learning approach, the wav2vec2-base and WavLM-base models were fine-tuned for the three-class task. The best results were achieved by the self-supervised models: WavLM reached a global balanced accuracy of 0.727 and a macro-F1 score of 0.710, while wav2vec 2.0 achieved 0.722 and 0.695, respectively. Both outperformed the feature-based approach (BAcc = 0.627, macro-F1 = 0.584). Confusion matrix analysis showed that the greatest difficulty lies in distinguishing the neutral class from the sad and happy classes, whereas sad and happy classes are more clearly separable. Feature utility analysis (SFS under the LOSO protocol) indicated the significant role of cepstral features (MFCCs and their derivatives), complemented by selected prosodic and temporal features. An additional comparison of SVM classifiers suggested that the main limitation of this approach lies in the signal representation itself rather than solely in the choice of classifier. Explainability analyses of the deep models, using layer-wise probing and integrated gradients, showed that affective information is best represented in intermediate layers, and that model decisions rely on locally salient segments of the signal. Furthermore, a speaker adaptation experiment demonstrated that personalization significantly improves classification performance, highlighting the potential of such methods for long-term monitoring of affective expression changes in the same individual. Full article

Background/Objectives: Children with autism spectrum disorder (ASD) often exhibit differences in attention regulation and visual behavior. However, many ASD eye-tracking datasets lack reliable moment-to-moment behavioral or emotional annotations, limiting the direct application of supervised learning approaches. To address this challenge, this study proposes an interpretable gaze-based unsupervised framework for discovering behavioral pseudo-zones from unlabeled ASD eye-tracking data. Methods: Raw gaze recordings from ASD participants were segmented into fixed temporal windows and represented using interpretable gaze features, including gaze dispersion, fixation duration, tracking quality, motion ratio, pupil size, and gaze velocity measures. Multiple clustering models and alternative temporal window sizes were systematically compared, including K-means, Gaussian Mixture Modeling (GMM), Agglomerative Clustering, and HDBSCAN. Results: Among the evaluated configurations, the combination of 1000 ms windows with K-means clustering (k = 4) was retained as the final exploratory configuration. Although alternative solutions achieved slightly stronger internal validation metrics, the selected configuration provided a more interpretable four-zone structure while maintaining acceptable clustering quality. The final retained solution produced four interpretable behavioral pseudo-zones with statistically significant differences across all extracted gaze features according to the Kruskal–Wallis test (p < 0.05). A PCA projection further supported the exploratory structure of the discovered pseudo-zones, with the first two principal components explaining 72.3% of the total variance. Conclusions: The findings demonstrate that unlabeled ASD gaze data can be organized into interpretable behavioral pseudo-zones using an unsupervised and transparent feature-based framework. This work contributes a data-driven and interpretable framework for future gaze-based behavioral analysis and autism-related AI research. Full article

Background/Objectives: Social skills deficits are increasingly recognized as clinically relevant correlates of suicidal behavior in adolescents. Goldstein’s Aggression Replacement Training (ART) provides a structured framework for assessing discrete prosocial and emotional skills, but its relationship with suicidality in psychiatric inpatients has not been systematically examined. This paper investigated whether self-rated ART social skills items differentiate adolescents with and without a history of suicide attempt as well as whether machine learning (ML) models can identify interpersonal profiles associated with SA. Methods: In this cross-sectional study, 162 psychiatric inpatients aged 11–17 years (72% female) were assessed at admission. Social skills were measured using the 50-item Skillstreaming component of ART, which is grouped into six domains (basic, advanced, emotional, alternatives to aggression, stress management, planning). Machine learning models (logistic regression, random forest, XGBoost, SVM, k-NN, Gaussian Naive Bayes) were trained on item-level features using repeated nested cross-validation with a held-out test set providing an unbiased estimate of generalization. Results: One item—Helping Others—remained significant after Holm correction (adjusted p = 0.042) with higher scores among adolescents with a history of SA. Seven additional prosocial items reached nominal significance (raw p < 0.05) but did not survive correction. Across ML models, discrimination was modest (cross-validated ROC-AUC 0.59–0.66) with Gaussian Naive Bayes performing best (ROC-AUC 0.66). Held-out test set performance was lower (ROC-AUC 0.46, 95% CI 0.26–0.69). SHAP analysis localized the model’s signal to a coherent cluster of prosocial and empathic communication items with higher self-reported prosociality paradoxically associated with SA history. Conclusions: In this inpatient cohort, self-rated social skills carried a small but coherent discriminative signal for prior suicide attempt, which was concentrated in outward-directed prosocial behaviors rather than global interpersonal functioning. The counterintuitive directionality—higher prosocial self-ratings among attempters—aligns with developmental frameworks describing compliant, hyper-responsible, or self-silencing interpersonal styles. While predictive performance was modest and sample size limits generalizability, item-level ART assessment may generate hypotheses about interpersonal risk phenotypes in this specific population of predominantly female adolescent inpatients. Only one item survived correction for multiple comparisons, and all findings should be interpreted as exploratory and hypothesis generating. Full article

An animal’s emotion is regarded as a critical indicator for assessing its welfare. At present, most canine emotion recognition models rely on static images, which leads to insufficient modeling of spatiotemporal features and low accuracy. To address this limitation, this study proposed a 3D ResESAM model based on 3D ResNet50, which is a pre-trained model on the Kinetics dataset. Specifically, the Enhanced Sequential Attention Module (ESAM) is integrated into the backbone to improve the capability of extracting and enhancing spatiotemporal features, and YOLO (You Only Look Once) was employed to detect and crop canine facial regions to reduce interference from complex backgrounds (e.g., furniture, humans, or other animals). To evaluate the effectiveness of 3D ResESAM, a canine emotion dataset named Dog-Face was constructed, which contains four emotions: happiness, sadness, anger, and calmness. Experimental results demonstrate that the proposed 3D ResESAM achieves an accuracy of 0.9239, representing a 3.25% improvement over the baseline 3D ResNet50. Furthermore, compared with other models such as C3D and R(2 + 1)D, whose accuracies are just 0.5215 and 0.8570, respectively, from different attention mechanism perspectives, the proposed model outperforms not only the baseline model without ESAM but also models incorporating other attention modules such as ECA and CBAM, with average accuracies being 0.8972 and 0.9103, respectively. In addition, cross-domain experiments are conducted on a human emotion dataset. The results show that 3D ResESAM achieves an average accuracy improvement of 2.39% over 3D ResNet50, demonstrating its significantly superior performance, effectiveness and potential in real-world applications. Full article

Immersive audio and vibroacoustic stimulation have gained increasing attention as non-invasive approaches for modulating human emotional and physiological states. The SonikB3D platform was previously introduced as a multisensory system combining immersive 3D audio, vibroacoustic stimulation, and physiological monitoring. Building upon this prior work, the present study advances the platform through a refined experimental protocol and a data-driven framework for the automatic assessment of relaxation using multimodal biosignals. A controlled pilot study was conducted with 20 participants exposed to 3D sound and vibroacoustic stimulation delivered through a massage table equipped with integrated transducers. Although the SonikB3D platform supports multiple stimulation scenarios, the present study focuses on a single controlled condition combining binaural 3D audio (binaural beats plus music) and vibroacoustic stimulation in order to ensure methodological consistency for multimodal modelling. Physiological responses were continuously recorded using a synchronized setup including electroencephalography (EEG), photoplethysmography (PPG), and electrodermal activity (EDA). Subjective emotional self-assessment questionnaires were collected before and after exposure to provide a multidimensional characterization of participant responses. Results show a statistically significant increase in self-reported relaxation (paired t-test = 3.05, p = 0.01), corresponding to an average 8% improvement in normalized relaxation scores. To support objective assessment, multimodal physiological features associated with autonomic and emotional regulation were extracted and used to develop a two-stage machine learning pipeline. The proposed model, combining a window-level Random Forest classifier with session-level aggregation, achieved an accuracy of 80% and an F1-score of 0.857 in classifying relaxation-related states. These findings provide preliminary evidence that combined 3D audio and vibroacoustic stimulation can produce measurable changes in subjective and physiological indicators of relaxation, while demonstrating the feasibility of automatic relaxation state inference from multimodal biosignals. Although exploratory due to the limited sample size and the absence of unimodal control conditions, this work contributes a data-driven methodology for studying human responses to multisensory sound and vibration metrics. Full article

Electroencephalography (EEG) is closely related to neural activity underlying emotional states. It has become an important input modality for emotion recognition in affective computing. However, many existing studies rely on complex experimental paradigms and full-channel EEG signals. They often construct high-dimensional features for discrete emotion classification and pay less attention to continuous emotional dynamics. To address these issues, this study uses six frontal EEG channels, including Fp1, Fp2, AF3, AF4, F7, and F8. These channels are relatively easy to acquire and are closely associated with emotional activity. A frontal hemispheric relation-aware temporal convolutional network (FHR-TCN) is proposed for continuous emotion regression and discrete emotion classification. Experiments on MAHNOB-HCI and DEAP evaluated FHR-TCN for continuous emotion regression and discrete emotion classification, respectively. Under the reported protocols, FHR-TCN achieved higher average scores than the evaluated baselines. It also showed lower parameter counts, MACs, and GPU inference latency than GRU. These findings support further deployment-oriented evaluation under limited-channel conditions. Full article

Synchrony refers to similarity in movement between different actors such as dancing, clapping, or singing together. Prior research demonstrates that synchrony often elicits emotions that may be characterized as aesthetic or self-transcendent (e.g., awe, connectedness). Our research situated the concept of synchrony in media contexts, examining viewers’ affective responses to videos featuring synchronous movement. Study 1 employed an experiment, showing that synchronized videos elicited greater awe, with awe associated with a host of prosocial outcomes reflecting connectedness and motivations to do good. Study 2 employed content analytic procedures to examine how the synchrony present in a large sample of YouTube videos was associated with user comments reflecting self-transcendent emotions, and how these emotions were associated with the salience of moral foundations. The results showed that synchrony was associated with greater feelings of awe, admiration, and elevation. Further, comments reflecting self-transcendence were associated with the salience of moral foundations, and particularly the foundation of care. Full article

Implicit-emotional expressions are common in college students’ social media posts, where literal meanings may contradict underlying emotions. Bidirectional Encoder Representations from Transformers (BERT)-based models face two coupled challenges in this setting: feature confusion between semantic content and expression style, and coarse-grained feature fusion. We propose CSD-IFRN (Content–Style Disentanglement with Conditional Fusion for Implicit Emotion Recognition Network), which disentangles content and style using dual non-shared BERT encoders, combines gradient-reversal adversarial training with a content–style orthogonality regularizer (L_orth), and applies conditional layer normalization (CLN) for adaptive fusion. On a dedicated dataset of 11,154 triple-annotated texts, averaged over five random seeds, CSD-IFRN achieves 88.58% accuracy and 88.43% macro-F1, improving over BERT-base-chinese by 6.99 points and over the strongest SOTA baseline by 2.61 points. The main gains remain significant after Holm correction (p < 0.01) and also hold on a public benchmark. A frozen style probe trained on content features falls to 50.40% balanced accuracy, close to chance level, supporting effective disentanglement. Among fusion strategies, CLN achieves the best accuracy with low seed-to-seed variance. These results suggest that CSD-IFRN can provide an auxiliary signal for university mental-health monitoring, rather than a clinical diagnostic tool. Full article