Search Results (1,369)

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

This study investigated the relationship between fixation-frequency-based Shannon entropy and dwell-time-based entropy across two different visual task domains: emotional evaluation of automotive exterior designs and safety-critical monitoring of nuclear power plant emergency scenarios. Although gaze entropy has been widely used to explain emotional responses, task performance, and situation awareness, the relationship between entropy measures derived from fixation counts and fixation durations remains insufficiently examined. Eye-tracking data were analyzed from two experiments with different attentional characteristics. In the emotional visual task, 10 participants evaluated three automotive design images. In the safety-critical task, 20 participants performed four nuclear power plant emergency monitoring scenarios. Shannon entropy and dwell-time entropy were calculated using fixation count and fixation duration distributions across Areas of Interest, respectively. Pearson correlation and simple regression analyses were conducted within each task domain. The results showed strong positive associations between Shannon entropy and dwell-time entropy in both domains. The emotional task showed a correlation of r = 0.844, while the safety-critical task showed a correlation of r = 0.890. These findings suggest that fixation-frequency-based and dwell-time-based entropy measures exhibit substantial overlap across different visual task contexts. However, the observed associations may partly reflect mathematical dependency between fixation frequency and cumulative dwell-time, and the findings should be interpreted as exploratory evidence rather than proof of metric interchangeability. The study highlights that gaze entropy metrics should be interpreted in relation to task-dependent attentional contexts. Higher entropy may be associated with exploratory visual attention in emotional evaluation, whereas lower entropy may be associated with focused monitoring in safety-critical tasks. Full article

This paper examines whether the persistent difficulty in addressing the eco-social crisis may partly stem from an inadequate representation of human decision-making within mainstream economic models. Although pro-environmental behaviors (PEBs) and sustainable consumption are increasingly recognized as essential for sustainability transitions, neoclassical economics still largely relies on the homo oeconomicus paradigm, which assumes fully rational and utility-maximizing decision-making. Building on contributions from psychology, behavioral economics, neuroscience, and sustainability studies, this integrative narrative review examines how cognitive biases challenge the foundational assumptions of homo oeconomicus and explores the potential role of emotional intelligence in sustainability-related decision-making. Adopting the integrative narrative review approach, this paper integrates literature on (1) cognitive biases and bounded rationality; (2) emotional intelligence and judgment bias; and (3) emotional intelligence, pro-environmental behaviors, and sustainable consumption. The evidence reviewed suggests that sustainability-related decisions are strongly shaped by cognitive and emotional processes operating under uncertainty and socially embedded consumption patterns. Within this framework, EI may represent a psychological resource capable of influence of cognitive biases by supporting emotional regulation, impulse control, self-awareness, and long-term orientation. Overall, the paper proposes a conceptual framework linking cognitive biases, emotional intelligence, and sustainable behavior beyond the traditional homo oeconomicus paradigm. Full article

(1) Background. Substance use disorders are frequently associated with difficulties in emotion regulation and the use of ineffective coping strategies. (2) Methods. A total of 201 participants undergoing specialized treatment for substance use disorders in Romania completed the Difficulties in Emotion Regulation Scale (DERS) and the Strategic Approach to Coping Scale (SACS). Statistical analyses included independent samples t-tests, Pearson correlations, path analysis, and linear regression. (3) Results. Participants with more severe substance use (history of hospitalization, detoxification treatment, and polysubstance use) exhibited significantly higher levels of emotion regulation difficulties. The latent factor DIFFICULTY was predicted by two correlated SACS predictors: Assertive Action (AA) and Antisocial Action (AS). Substance type differentially influenced DERS dimensions. The strongest correlation with the total DERS score was observed for antisocial action. (4) Conclusions. Emotion regulation and coping optimization are key targets in the treatment of substance use disorders, reflecting persistent difficulties in effectively managing emotions despite cognitive awareness. Social support may function as both an adaptive and maladaptive mechanism in this clinical context. Full article

With the rapid development of social media and online interactive platforms, online public opinion has become a vital information source for public emotional expression, social risk perception, and decision support. However, public opinion texts are typically characterized by short length, obscure semantics, complex emotional expressions, and strong context dependence, making it difficult for traditional lexicon-based or shallow neural network methods to achieve stable and robust performance in sentiment discrimination tasks. To address these issues, this paper proposes BERT-BiLSTM-MHSA-Capsule (BBMC), hereafter referred to as BBMC, an online public opinion sentiment analysis model based on multi-level semantic feature fusion. The model first utilizes the pretrained language model BERT to extract dynamic semantic representations with context-aware capabilities; subsequently, a Bidirectional Long Short-Term Memory (BiLSTM) network is employed to model the bidirectional temporal dependencies within the texts, while a Multi-Head Self-Attention (MHSA) mechanism is introduced to achieve adaptive focusing on key emotional information. Building upon this, a three-layer cascaded capsule network is constructed to achieve structured modeling of high-order emotional attributes through vector neurons and dynamic routing mechanisms, effectively mitigating the loss of spatial feature information caused by traditional pooling and fully connected structures. Experimental results on a manually annotated online public opinion dataset show that BBMC achieves better performance than the evaluated baseline models in terms of accuracy, recall, and F1-score. These results indicate the empirical effectiveness of the proposed task-oriented feature-integration strategy and capsule-based classification head for online public opinion sentiment analysis. Full article

Background: Genetic testing is increasingly part of the diagnostic pathway of congenital hearing loss (CHL), clarifying etiology and supporting clinical management. However, its psychosocial impact, especially differences between syndromic and non-syndromic conditions, remains underexplored. Objectives: This study evaluated the differential psychological impact of genetic diagnosis in syndromic versus non-syndromic pediatric patients, its relationship with clinical and rehabilitative variables, and the role of post-diagnostic psychological assessment. Methods: A cross-sectional post-diagnosis survey was conducted in families of children with genetically confirmed syndromic (Usher syndrome, n = 21) and non-syndromic (GJB2-related, n = 21) CHL; a total of 37 families responded. Parental empowerment was assessed using an Italian translated version of the Genetic Counseling Outcome Scale (GCOS-24). In an exploratory analysis, GCOS-24 items were grouped into three author-derived domains (understanding/awareness, emotional experience, and informational support) based on semantic content, not validated psychometrically. Results: No significant differences in GCOS-24 scores emerged between groups, nor in relation to clinical variables like hearing loss severity, auditory outcomes, or rehabilitative interventions. Genetic diagnosis occurred later in the syndromic group. Qualitative observations suggested parental empowerment varied with timing of diagnosis, clarity of information, and therapeutic alliance quality. Conclusions: Overall, these results highlight the importance of integrating psychological support and structured communication into clinical pathways to support families and patients in understanding and adapting to the diagnosis over time. Further longitudinal studies are needed to clarify the evolving psychosocial impact of genetic diagnosis in CHL. Full article

Early clinical exposure (ECE) has been associated with increased confidence, professionalism, and career exploration in undergraduate medical education. Student-run free clinics (SRFCs), such as the Health Outreach Project (HOP) at Drexel University College of Medicine, provide opportunities for preclinical students to engage in patient care and community outreach. This qualitative study explored medical students’ perceptions of participation in HOP. Fourteen third- and fourth-year medical students with prior HOP experience participated in four semi-structured focus groups conducted virtually over Zoom. Data were analyzed using an inductive thematic analysis approach. Four major themes emerged: (1) early clinical exposure and clinical skills development, (2) community engagement and patient-centered perspectives, (3) professional identity formation and career exploration, and (4) opportunities, limitations, and emotional challenges of outreach work. Participants described HOP as an important source of authentic clinical exposure that increased confidence in patient interactions and broadened awareness of social determinants of health and underserved populations. Students also reflected on the influence of HOP on professional identity formation, career interests, and perspectives on patient-centered care, while acknowledging frustrations related to systemic barriers and limited resources. These findings suggest that students perceive SRFCs as valuable experiential learning environments that support clinical preparedness and professional development early in medical training. Full article

Transition to higher education represents a critical period marked by academic, emotional, and social challenges that can affect students’ well-being. Although social and emotional competence (SEC) and self-care practices have been identified as protective factors of well-being, there is a gap in understanding how these concepts intersect within higher education. In an exploratory sequential mixed-methods study, we first explored the main challenges perceived by higher education students in adapting to university and which SEC and self-care practices they perceived as most relevant to promoting their personal and academic well-being. Building on these insights, we then investigated the mediating role of self-care practices in the relationship between students’ SEC and their well-being. In the first stage of the study, 16 higher education students (81.3% female, M = 22.19 years) participated in semi-structured interviews; additionally, 204 higher education students (77.9% female, M = 22.10 years) responded to an online survey. Qualitative findings suggested that the most significant challenges in the adaptation to university were of a social and emotional nature, related to emotional challenges, interpersonal relationships, and personal organization. To overcome these, students primarily valued intrapersonal competencies such as self-awareness and self-regulation. Participants predominantly described using personal self-care practices, focusing on psychological and emotional care. Generalized linear model-based mediation analysis sustained that both personal and academic self-care practices mediated SEC effects on students’ personal well-being. However, only academic self-care practices mediated SEC effects on their academic well-being. Self-regulation competencies had the strongest effect on students’ personal and academic well-being, providing quantitative support for the prominence attributed to this competency by students during the qualitative phase. This research contributes to a strengthened theoretical understanding of the interplay between higher education students’ SEC, self-care practices, and well-being, offering new empirical evidence on how these relate. Full article

Change point detection in dynamic social graphs aims to identify significant transitions in evolving interaction patterns. The task is particularly challenging due to sparse and noisy interactions and frequent user turnover, while the existing methods largely overlook the semantic and emotional signals in user-generated content by focusing primarily on structural changes. To address these limitations, this paper proposes ECPD-SG, an emotion-aware contrastive prototype learning algorithm for unsupervised change point detection in dynamic social graphs. ECPD-SG constructs emotion-aware graph snapshots by integrating textual and affective features into node representations and recalibrating interaction weights through emotion-aware attention. It then summarizes temporal node representations into adaptive prototypes and models their evolution using optimal-transport-based alignment and contrastive learning. Change points are detected from prototype-level shift scores with an adaptive CUSUM decision rule. Experiments on real-world dynamic social graph datasets show that ECPD-SG achieves competitive or superior performance over representative baselines, while ablation and sensitivity analyses verify the effectiveness of its key components. Full article

For autonomous maritime perception and situational awareness, the end-to-end multi-object tracking paradigm has achieved complete learning, from image sequences to tracking results, reducing the reliance on manually designed association rules and holding great potential. However, in maritime radar video multi-object tracking, due to the limited visual features of targets and significant feature variations under long-term tracking, problems such as identity switching are prone to occur, making it difficult to directly apply existing end-to-end approaches. To solve these problems, this paper proposes a trajectory-aware end-to-end multi-object tracking method. The real-time trajectory of the targets contains temporal context information. This work uses it as prior knowledge to enhance visual feature encoding and compensate for the shortcomings of single-frame visual features. Specifically, the trajectory feature is encoded by the trajectory encoder module while, simultaneously, the visual features are encoded through the backbone and the visual feature encoder module. Then, in the frame-trajectory cross-modal attention module, the trajectory feature encoding is used to reconstruct the visual feature encoding with cross-attention, dynamically enhancing the features related to the target identity. Experiments on actual collected maritime radar video data show that the proposed method is effective, achieving improvements in several key indicators. Full article

Arabic multi-label emotion detection (MLED) in social media remains challenging because dialectal variation, implicit affective cues, and polarity-opposed emotions may occur within the same post. Existing Arabic MLED studies have mainly emphasized thresholded predictive performance, with limited attention to whether model confidence remains reliable under emotionally conflicting conditions. In this study, we propose CONCORD-Emo (CONflict-aware Compositional Representation for Emotion Detection), a reliability-aware framework for Arabic MLED. The framework adopts established label-wise attention, mixture-of-experts routing, Monte Carlo (MC) dropout, and post hoc temperature scaling as supporting mechanisms, while its architecture-level contribution is the conflict-conditioned integration of a residual global anchor with a conflict-aware fusion gate supervised by an automatically derived polarity-conflict target. We evaluated the framework on three Arabic benchmarks: SemEval-2018-Ar, ExaAEC, and SemEval-2025-Arq using predictive and reliability-oriented criteria. CONCORD-Emo remains competitive with strong MARBERT-based baselines. On SemEval-2025-Arq, it attains point estimates of 0.471 for Jaccard, 0.606 for micro-F1, and 0.582 for macro-F1. Paired bootstrap confidence intervals show that most predictive differences include zero, whereas the lower Expected Calibration Error and Brier scores on SemEval-2018-Ar and ExaAEC are consistently supported relative to the controlled baselines. Conflict-conditioned analysis shows that polarity-conflict instances yield lower predictive performance and higher Brier scores than blended-emotion instances. Taken together, these results support a reliability-aware evaluation of Arabic MLED in which polarity conflict, calibration, uncertainty estimation, and selective prediction are examined alongside predictive performance. Full article

Vision-based driver fatigue detection remains challenging because facial signals associated with fatigue are often ambiguous, while geometric indicators such as Eye Aspect Ratio (EAR) and Percentage of Eye Closure (PERCLOS) are prone to false positives caused by normal facial activity, including smiling or speaking. This paper proposes a context-aware framework that integrates behavioural, geometric, and emotional information for robust fatigue assessment. Facial landmarks are extracted using MediaPipe Face Mesh, while adaptive eye-closure detection is performed through multi-stage validation combining EAR trajectories, mouth activity, head-pose analysis, and event-level filtering. Emotion recognition is achieved using an EfficientNet-B0 convolutional neural network trained on the AffectNet dataset, enabling frame-level estimation of facial expression probabilities. These predictions are aggregated into descriptors representing emotional variability and fatigue-related emotional relevance over time. Behavioural information obtained from blinking, yawning, head nodding, and validated PERCLOS is fused with emotional context to construct a multi-level fatigue assessment model. The final Driver Fatigue Risk Index combines physiological eye-closure information with contextual behavioural–emotional analysis, providing an interpretable estimation of driver state rather than a binary classification alone. Experimental evaluation on the NTHU-DDD dataset achieved 94% accuracy and demonstrated improved robustness under non-frontal head poses and expressive facial behaviour. Full article

Recent advancements in sequence generation models have transformed the development of conversational chatbots, enabling more dynamic and emotionally aware interactions. While English-language chatbots have achieved notable progress through large language models (LLMs), Arabic-language systems continue to face significant challenges, particularly in handling dialectal variation, morphological complexity, and generating emotionally aligned responses. This paper introduces two innovative approaches to enhance empathetic response generation in Arabic conversational AI. The first, Emotion-Driven Response Generation (EDRG), employs a two-stage pipeline: it first classifies user emotions using marBERT and then routes inputs to the most suitable Arabic LLM (AraBERT, AraELECTRA, AraGPT-2, or MT5) for contextually appropriate response generation. The second, EmoLlama, is a Retrieval-Augmented Generation (RAG)-based framework that integrates a curated knowledge base with the LLaMA model to retrieve relevant conversational contexts before generating semantically rich and empathetic responses. To support these approaches, a large-scale open-domain Arabic dataset was curated, containing over 600,000 dialogue entries spanning empathetic and neutral responses across seven Ekman-based emotion categories. Experimental evaluations using BLEU, Perplexity (PPL), and Cosine Similarity metrics validated the effectiveness of our models. EDRG achieved strong BLEU scores across multiple emotions, reflecting high lexical alignment, while also attaining a Cosine Similarity of 0.51. In contrast, EmoLlama significantly outperformed in semantic similarity, achieving a Cosine Similarity of 0.91, demonstrating its superior ability to generate contextually and semantically rich responses. These results highlight the complementarity of lexical and semantic metrics in evaluating emotionally intelligent Arabic dialogue systems. Full article

Collaboration is increasingly treated as a core capability in contemporary working life, yet leadership-development research suggests that developmental efforts often remain too generic, weakly contextualized, and insufficiently connected to the conditions under which participants must learn and perform. This theory-informed exploratory study examines how Norwegian union representatives define, operationalize, and reflect on collaborative capability development within a semester-long university course. The study adopts a qualitative document design based on 25 written course reports produced by Parat union representatives enrolled in the course Collaboration for the Future Working Life at Kristiania University of Applied Sciences in autumn 2025. The reports are analyzed as structured reflective development documents using cross-case thematic analysis. Conceptually, the article draws on collaboration research, leadership development, self-directed learning, self-leadership, and job demands–resources theory. The findings indicate that participants conceptualized collaborative capability as a multidimensional professional capability combining dialogic competence, trust-building, psychological safety, role-based bridge-building, assertive boundary-setting, and self-regulation under pressure. Development was typically organized through iterative practice cycles of self-evaluation, feedback, goal setting, monitoring routines, micro-practices for attention and stress regulation, environmental redesign, implementation, reflection, and adjustment. At the same time, the reports suggest that collaborative development was constrained by time pressure, emotional exposure, cumulative role demands, and fluctuating energy. Reported outcomes were typically incremental, including clearer communication, increased awareness of triggers, stronger boundary-setting, more sustainable role professionalism, and improved presence under strain. The article contributes a bounded, context-sensitive account of collaborative capability development as a self-directed, self-regulated, and resource-sensitive process of professional becoming. It further develops two connected practical–theoretical models: the Performance Pyramid, which clarifies the developmental architecture from identity awareness to energy and capability regulation and performance enactment, and the Self-Leadership Wheel of Becoming, which functions as an operational scaffold for self-evaluation, goal setting, feasible program design, implementation, reflection, and revision. Rather than presenting these models as universally validated, the article positions them as heuristic and processual contributions for understanding and supporting capability development in collaboration-intensive roles. Full article

Background: Chronic stress contributes to mental and physical disorders, including burnout, anxiety, and depression. While self-report assessments remain valuable, they are inherently subjective and may be insensitive to short-term psychophysiological fluctuations. Remote photoplethysmography (rPPG) enables non-contact extraction of cardiovascular signals from facial videos and has increasingly been explored for stress-related monitoring through heart rate and heart rate variability features. Objective: This preliminary study aimed to assess the feasibility, usability, and preliminary construct validity of a mobile rPPG-based application for psychophysiological stress monitoring in daily life by examining usability, stress index distributions, and associations with self-reported psychological distress. Methods: A total of 252 participants from the general population and university students completed standardized facial video acquisition using a smartphone-based rPPG application and self-report questionnaires. The app extracted pulse wave signals, computed cardiovascular features related to heart rate and pulse rate variability, and integrated them into three indices: Stress Level, Stress Recovery, and Stress Response. Correlation and regression analyses examined associations with psychological distress. Results: The three indices showed substantial inter-individual variability. Stress Level was significantly associated with anxiety (r = 0.13, p = 0.036), depressive symptoms (r = 0.13, p = 0.047), and General Emotional Distress (r = 0.17, p = 0.006). In regression analysis, Stress Level emerged as the only significant independent correlate of General Emotional Distress (β = 0.21, p = 0.017). Younger participants and women showed higher Stress Level scores. Conclusions: The present findings should therefore be interpreted as preliminary and exploratory evidence of construct validity, suggesting that the app-derived indices may capture individual differences in stress-related physiological activation in everyday contexts. Currently, the observed associations were weak, the model explained limited variance, and the results do not demonstrate clinical validity, diagnostic utility, or predictive accuracy. Looking ahead, further longitudinal studies, repeated rPPG assessments, correction-aware analyses, and validation against reference physiological measures are needed before these indices can be considered suitable for clinical or preventive use. Full article