Search Results (584)

Multimodal emotion recognition (MER) is essential for understanding human emotions from diverse sources such as speech, text, and video. However, modality heterogeneity and inconsistent expression pose challenges for effective feature fusion. To address this, we propose a novel MER framework combining a Dynamic Weighted Graph Convolutional Network (DW-GCN) for feature disentanglement and a Cross-Attention Consistency-Gated Fusion (CACG-Fusion) module for robust integration. DW-GCN models complex inter-modal relationships, enabling the extraction of both common and private features. The CACG-Fusion module subsequently enhances classification performance through dynamic alignment of cross-modal cues, employing attention-based coordination and consistency-preserving gating mechanisms to optimize feature integration. Experiments on the CMU-MOSI and CMU-MOSEI datasets demonstrate that our method achieves state-of-the-art performance, significantly improving the $AC{C}_7$, $AC{C}_2$, and $F1$ scores. Full article

Background: Nemaline myopathy is a rare congenital neuromuscular disease associated with progressive weakness and frequent respiratory complications. In emergency situations, families often serve as the first and only responders. The aim of this study is to explore how parents in Spain care for children with nemaline myopathy during emergency situations, focusing on the clinical responses performed at home and the organizational challenges encountered when interacting with healthcare systems. Methods: A qualitative phenomenological study was conducted with 17 parents from 10 families belonging to the Asociación Yo Nemalínica. Semi-structured interviews were performed via video calls, transcribed verbatim, and analyzed using Giorgi’s descriptive method and ATLAS.ti software (version 24). Methodological rigor was ensured through triangulation, reflexivity, and member validation. Results: Four themes were identified. First, families were described as acting under extreme pressure and in isolation during acute home emergencies, often providing cardiopulmonary resuscitation and respiratory support without professional backup. Second, families managed ambiguous signs of deterioration using clinical judgment and home monitoring tools, often preventing fatal outcomes. Third, parents frequently assumed guiding roles in emergency departments due to a lack of clinician familiarity with the disease, leading to delays or errors. Finally, the transition to the Pediatric Intensive Care Unit was marked by emotional distress and rapid decision-making, with families often participating in critical choices about invasive procedures. These findings underscore the complex, multidisciplinary nature of caregiving. Conclusions: Parents play an active clinical role during emergencies and episodes of deterioration. Their lived experience should be formally integrated into emergency protocols and the continuity of care strategies to improve safety and outcomes. Full article

The COVID-19 pandemic has exposed and intensified structural tensions surrounding work−life balance, precarity, and gender inequalities in academia. This paper examines the spatial, temporal, and emotional disruptions experienced by early-career and precarious researchers in Italy during the first national lockdown (March–April 2020) and their engagement in remote academic work. Adopting an exploratory and qualitative approach, the study draws on ten narrative video interviews and thirty participant-generated images to investigate how structural dimensions—such as gender, class, caregiving responsibilities, and the organizational culture of the neoliberal university—shaped these lived experiences. The findings highlight the implosion of boundaries between paid work, care, family life, and personal space and how this disarticulation exacerbated existing inequalities, particularly for women and caregivers. By interpreting both visual and narrative data through a sociological lens on gender, work, and organizations, the paper contributes to current debates on the transformation of academic labor and the reshaping of temporal work regimes through the everyday use of digital technologies in contemporary neoliberal capitalism. It challenges the individualization of discourses on productivity and flexibility and calls for gender-sensitive, structurally informed policies that support equitable and sustainable transitions in work and family life, in line with European policy frameworks. Full article

This study investigated individuals’ emotional responses to bed bugs and how these were influenced by sex, proximity, and educational intervention. Using a pre-post experimental design, participants (n = 157) completed emotional assessments before and after viewing an educational video about bed bugs. Contrary to our initial hypothesis that only fear and disgust would be observed, participants also exhibited high levels of anxiety and anger. Following the educational intervention, disgust, fear, and anger toward bed bugs increased significantly. Participants experienced greater disgust and fear when imagining encounters with bed bugs in closer proximity, with home infestations giving stronger responses than workplace scenarios. The educational video reduced disgust toward bed bugs in the home but increased fear of them in public spaces, potentially promoting vigilance that could limit bed bug spread. Females reported higher levels of disgust and fear than males across all proximity conditions, supporting evolutionary theories regarding sex-specific disgust sensitivity. The educational video successfully increased participants’ knowledge about bed bugs while simultaneously shifting emotional responses from contamination-based disgust to threat-specific fear. These findings suggest that educational interventions can effectively modify emotional responses to bed bugs, potentially leading to more rational management behaviors by transforming vague anxiety into actionable awareness of specific threats. Full article

The extensive use of digital media among adolescents has raised concerns about its impact on emotional development and mental health. Understanding the psychological factors behind problematic digital media use is essential for effective prevention. This study examined whether the relationships between emotion regulation (negative and positive), compulsive use, cognitive preoccupation, and negative outcomes linked to digital media are consistent across sex and academic year. We used a cross-sectional design with 2357 adolescents (12–16 years old) from Compulsory Secondary Education. Participants completed validated self-report questionnaires assessing problematic digital media use, and associated consequences in four domains: internet, video games, social networking, and messaging. Four structural equation models (SEMs), each focused on a media type, tested whether these relationships remained stable across sex and academic year. All models showed good fit, and differences between groups were minimal, supporting valid comparisons. Results confirm that emotion regulation difficulties and problematic digital media use are consistently associated with negative outcomes in all adolescents, regardless of sex or academic level. Preventive strategies targeting emotional regulation and digital media behaviors may be broadly applied to reduce emotional and functional problems related to excessive media use. Full article

This paper examines how Marley Dias’ activism on Instagram promotes racial justice, Black feminist thought, and youth mobilization through digital storytelling, representation, and audience engagement. Using a mixed-methods analysis of 744 posts published between 2016 and 2025, the study combined critical thematic coding, temporal mapping, and engagement metrics to analyze the discursive and emotional strategies behind Dias’ activism. Five key themes were identified as central to her activist work: diversity in literature, lack girl empowerment, racial justice, Black representation, and educational advocacy. The findings reveal that Dias strategically tailors her messages to suit Instagram’s unique features, using carousels and videos to enhance visibility, foster intimacy, and provide depth in education. Posts that focused on identity, aesthetics, and empowerment garnered the highest levels of engagement, while posts that concentrated on structural issues received lower, yet still significant, interaction. The paper argues that Dias’ Instagram account serves as a dynamic platform for youth-led Black feminist resistance, where cultural production, civic education, and emotional impact converge. This case underscores the political potential of digital literacies and encourages a reconsideration of how youth-driven digital activism is reshaping contemporary public discourse, agency, and knowledge production in the social media age. Full article

Police officers work in high-stress environments that demand emotional resilience, interpersonal skills, and effective communication. Occupational stress can negatively impact their motivation, conflict resolution abilities, and professional effectiveness. Loving-Kindness Meditation (LKM), a mindfulness-based intervention focused on cultivating compassion and empathy, has shown promise in enhancing prosocial attitudes and emotional regulation. With the rise of short video platforms, digital interventions like video-guided LKM may offer accessible mental health support for law enforcement. This study examines the effects of short video app-guided LKM on police officers’ mindfulness, public service motivation (PSM), conflict resolution skills (CRSs), and communication skills (CSSs). It aims to determine whether LKM can enhance these psychological and professional competencies. A randomized controlled trial (RCT) was conducted with 110 active-duty police officers from a metropolitan police department in China, with 92 completing the study. Participants were randomly assigned to either the LKM group (n = 46) or the waitlist control group (n = 46). The intervention consisted of a 6-week short video app-guided LKM program with daily 10 min meditation sessions. Pre- and post-intervention assessments were conducted using several validated scales: the Mindfulness Attention Awareness Scale (MAAS), the Public Service Motivation Scale (PSM), the Conflict Resolution Styles Inventory (CRSI), and the Communication Competence Scale (CCS). A 2 (Group: LKM vs. Control) × 2 (Time: Pre vs. Post) mixed-design MANOVA was conducted to analyze the effects. Statistical analyses revealed significant group-by-time interaction effects for PSM (F(4,177) = 21.793, p < 0.001, η² = 0.108), CRS (F(4,177) = 20.920, p < 0.001, η² = 0.104), and CSS (F(4,177) = 49.095, p < 0.001, η² = 0.214), indicating improvements in these areas for LKM participants. However, no significant improvement was observed for mindfulness (F(4,177) = 2.850, p = 0.930, η² = 0.016). Short video app-guided LKM improves public service motivation, conflict resolution skills, and communication skills among police officers but does not significantly enhance mindfulness. These findings suggest that brief, digitally delivered compassion-focused programs can be seamlessly incorporated into routine in-service training to strengthen officers’ prosocial motivation, de-escalation competence, and public-facing communication, thereby fostering more constructive police–community interactions. Full article

Humor is widely recognized for its positive effects on well-being, including stress reduction, mood enhancement, and cognitive benefits. Yet, the lack of reliable tools to objectively quantify amusement—particularly its temporal dynamics—has limited progress in this area. Existing measures often rely on self-report or coarse summary ratings, providing little insight into how amusement unfolds over time. To address this gap, we developed a Random Forest model to predict the intensity of amusement evoked by humorous video clips, based on participants’ facial expressions—particularly the co-activation of Facial Action Units 6 and 12 (“% Smile”)—and video features such as motion, saliency, and topic. Our results show that exposure to humorous content significantly increases “% Smile”, with amusement peaking toward the end of videos. Importantly, we observed emotional carry-over effects, suggesting that consecutive humorous stimuli can sustain or amplify positive emotional responses. Even when trained solely on humorous content, the model reliably predicted amusement intensity, underscoring the robustness of our approach. Overall, this study provides a novel, objective method to track amusement on a fine temporal scale, advancing the measurement of nonverbal emotional expression. These findings may inform the design of emotion-aware applications and humor-based therapeutic interventions to promote well-being and emotional health. Full article

Audio-driven emotional talking face generation aims to generate talking face videos with rich facial expressions and temporal coherence. Current diffusion model-based approaches predominantly depend on either single-label emotion annotations or external video references, which often struggle to capture the complex relationships between modalities, resulting in less natural emotional expressions. To address these issues, we propose MF-ETalk, a multimodal feature-guided method for emotional talking face generation. Specifically, we design an emotion-aware multimodal feature disentanglement and fusion framework that leverages Action Units (AUs) to disentangle facial expressions and models the nonlinear relationships among AU features using a residual encoder. Furthermore, we introduce a hierarchical multimodal feature fusion module that enables dynamic interactions among audio, visual cues, AUs, and motion dynamics. This module is optimized through global motion modeling, lip synchronization, and expression subspace learning, enabling full-face dynamic generation. Finally, an emotion-consistency constraint module is employed to refine the generated results and ensure the naturalness of expressions. Extensive experiments on the MEAD and HDTF datasets demonstrate that MF-ETalk outperforms state-of-the-art methods in both expression naturalness and lip-sync accuracy. For example, it achieves an FID of 43.052 and E-FID of 2.403 on MEAD, along with strong synchronization performance (LSE-C of 6.781, LSE-D of 7.962), confirming the effectiveness of our approach in producing realistic and emotionally expressive talking face videos. Full article

The accelerating pace of digital life has intensified psychological strain, increasing the demand for accessible and systematized emotional support tools. Relaxing video games—defined as low-pressure, non-competitive games designed to promote calm and emotional relief—offer immersive environments that facilitate affective engagement and sustained user involvement. This study proposes a computational framework that integrates sentiment analysis and topic modeling to investigate the affective mechanisms and behavioral dynamics associated with relaxing gameplay. We analyzed nearly 60,000 user reviews from the Steam platform in both English and Chinese, employing a hybrid methodology that combines sentiment classification, dual-stage Latent Dirichlet Allocation (LDA), and multi-label mechanism tagging. Emotional relief emerged as the dominant sentiment (62.8%), whereas anxiety was less prevalent (10.4%). Topic modeling revealed key affective dimensions such as pastoral immersion and cozy routine. Regression analysis demonstrated that mechanisms like emotional relief (β = 0.0461, p = 0.001) and escapism (β = 0.1820, p < 0.001) were significant predictors of longer playtime, while Anxiety Expression lost statistical significance (p = 0.124) when contextual controls were added. The findings highlight the potential of relaxing video games as scalable emotional regulation tools and demonstrate how sentiment- and topic-driven modeling can support system-level understanding of affective user behavior. This research contributes to affective computing, digital mental health, and the design of emotionally aware interactive systems. Full article

Background: Binge eating is a disordered eating behavior implicated in eating disorders such as binge eating disorder (BED) and bulimia nervosa; it significantly affects an individual’s physical and mental health. Recent studies suggest shared neurobiological mechanisms between binge eating and addictive behaviors. Comorbid addiction (e.g., substance use disorders and behavioral addictions) is also frequently reported in binge-eating patients. However, it is still unclear whether binge-eating individuals with comorbid addictions differ in their cognitive and mental health characteristics from those without comorbid addictions. Objectives: The present study aimed to examine the cognitive and mental health profiles of binge-eating individuals with and without co-occurring addictions. We hypothesized that binge-eating individuals with comorbid addictions would show greater impairments in impulsivity and self-control, as well as elevated depression and emotion dysregulation. Methods: In the present study, we assessed psychometric scales on various cognitive and mental health domains (e.g., impulsivity, behavioral inhibition, self-control, emotion regulation, mood, and anxiety) across 30 binge-eating individuals with co-occurring addictive behaviors (i.e., alcohol, nicotine, gambling, and video games), 32 binge-eating individuals without addiction, and 180 healthy control subjects with neither binge-eating tendencies nor addiction. Results: Both binge-eating groups showed a significant increase in punishment sensitivity, perceived stress, and state/trait anxiety compared to healthy controls, but there was no difference between the two binge-eating groups. Higher impulsivity and lower self-control were observed in both binge-eating groups to a significantly greater degree in the group with comorbid addiction. Notably, significantly increased depression and impaired emotion regulation (reduced use of cognitive reappraisal) were observed only in the binge-eating group with comorbid addiction when compared to the healthy controls. Conclusions: Our findings demonstrated the commonalities and differences in binge-eating populations with and without comorbid addiction. It will help to elucidate cognitive and mental health aspects of comorbid addiction in the binge-eating population and to develop more tailored diagnoses and treatments. Full article

We explore the feasibility of classifying perceived pain intensity—despite the stimulus being identical—using multimodal physiological signals and self-reported emotional ratings. A total of 112 healthy participants watched the same anger-inducing video, yet reported varying pain intensities (5, 6, or 7 on a 7-point scale). We recorded electrocardiogram, skin conductance (SC), respiration, photoplethysmogram results, and finger temperature, extracting 12 physiological features. Participants also rated their valence and arousal. Using a random forest model, we classified pain versus baseline and distinguished intensity levels. Compared to baseline, the painful stimulus altered heart rate variability, SC, respiration, and pulse transit time (PTT). Higher perceived pain correlated with more negative valence, higher arousal, and elevated SC, suggesting stronger sympathetic activation. The classification of baseline versus pain using SC and respiratory features reached an F1 score of 0.83. For intensity levels 6 versus 7, including PTT and skin conductance response along with valence achieved an F1 score of 0.73. These findings highlight distinct psychophysiological patterns that reflect perceived intensity under the same stimulus. SC features emerged as key biomarkers, while valence and arousal offered complementary insights, supporting the development of personalized, psychologically informed pain assessment systems. Full article

Facial expression recognition (FER) plays a critical role in affective computing, enabling machines to interpret human emotions through facial cues. While recent deep learning models have achieved progress, many still fail under real-world conditions such as occlusion, lighting variation, and subtle expressions. In this work, we propose FERONet, a novel hyper-attentive multimodal transformer architecture tailored for robust and real-time FER. FERONet integrates a triple-attention mechanism (spatial, channel, and cross-patch), a hierarchical transformer with token merging for computational efficiency, and a temporal cross-attention decoder to model emotional dynamics in video sequences. The model fuses RGB, optical flow, and depth/landmark inputs, enhancing resilience to environmental variation. Experimental evaluations across five standard FER datasets—FER-2013, RAF-DB, CK+, BU-3DFE, and AFEW—show that FERONet achieves superior recognition accuracy (up to 97.3%) and real-time inference speeds (<16 ms per frame), outperforming prior state-of-the-art models. The results confirm the model’s suitability for deployment in applications such as intelligent tutoring, driver monitoring, and clinical emotion assessment. Full article

This bibliometric analysis aims to provide a comprehensive overview of the use of 360-degree video in healthcare, identifying key research trends and emerging topics in this field. Data was sourced from the Web of Science Core Collection, Scopus, and PubMed, and analyses were performed using the Biblioshiny package. Network visualization was conducted using VOSviewer. A total of 272 studies on 360-degree video were included in the analysis. The number of publications has shown a consistent upward trend from 2009 to 2024. Most publications (n = 234) were articles, indicating a maturing field. Institutions in North America and Germany lead the list of top affiliations. Research areas reflect interdisciplinary use of 360-video in healthcare, led by computer science (20.2%), followed by education (14.3%), healthcare sciences (10.7%), psychology (10.3%), and nursing (8.1%), demonstrating broad applicability across sectors. Recent emerging topics, such as empathy, stress, and well-being, indicate a growing research interest in the holistic aspects of healthcare interventions, particularly the psychological and emotional dimensions. Additionally, the concept of “presence” has gained increasing attention, reflecting its psychological and emotional impact. The findings suggest that further research is needed to evaluate the effectiveness of interactive learning and user engagement in 360-degree video experiences. Full article

This study investigates Spanish-language public discourse on YouTube following the unprecedented Iberian Peninsula blackout of 28 April 2025. Leveraging comments extracted via the YouTube Data API and analyzed with the OpenAI GPT-4o-mini model, it systematically examined 76,398 comments from 360 of the most relevant videos posted on the day of the event. The analysis explored emotional responses, sentiment trends, misinformation prevalence, civic engagement, and attributions of blame within the immediate aftermath of the blackout. The results reveal a discourse dominated by negativity and anger, with 43% of comments classified as angry and an overall negative sentiment trend. Misinformation was pervasive, present in 46% of comments, with most falsehoods going unchallenged. The majority of users attributed the blackout to government or political failures rather than technical causes, reflecting a profound distrust in institutions. Notably, while one in five comments included a call to action, only a minority offered constructive solutions, focusing mainly on infrastructure and energy reform. These findings highlight the crucial role of multilingual, real-time crisis communication and the unique information needs of Spanish-speaking populations during emergencies. By illuminating how rumors, emotions, and calls for accountability manifest in digital spaces, this study contributes to the literature on crisis informatics, digital resilience, and inclusive sustainability policy. Full article