Search Results (1,670)

Generative artificial intelligence (AI)-based music generation has the potential to create new opportunities for music therapy; however, integrated examinations of generative AI and music therapy remain limited. This paper provides a focused survey of recent studies that apply generative AI within music therapy-related contexts, examining how such approaches have been explored in relation to therapeutic considerations, including emotional and physiological regulation. Rather than offering an exhaustive historical review, we analyze generative AI-augmented music therapy systems from a system-level perspective, focusing on their overall design and implementation. Based on this survey, we discuss open research challenges at the intersection of generative music, adaptive systems, and digital health, and outline future research directions toward scalable and personalized generative AI-based music therapy. Full article

Nowadays, educational software across all learning levels is increasingly enhanced with Artificial Intelligence (AI), primarily through content generation or post-session learning analytics. However, most existing systems remain weakly connected to learners’ real-time affective states and rarely exploit emotional information as a direct control signal for instructional adaptation. In this work, we propose a proof-of-concept closed-loop affect-aware educational adaptation framework that integrates real-time facial emotion recognition into a dynamic learning control system. The proposed approach is built upon a dual-model ensemble architecture, combining a transformer-based model (CAGE) and a CNN-based model (DDAMFN++) trained on large-scale in-the-wild datasets. To bridge heterogeneous emotion representations, we introduce a probabilistic fusion strategy that aligns continuous valence–arousal predictions with discrete emotion classification via a Gaussian Mixture Model (GMM), enabling unified emotion inference in real time. Based on the fused emotional state, a temporal aggregation mechanism is applied to capture sustained affective trends rather than transient expressions. These aggregated signals are then mapped to instructional decisions through an emotion-driven adaptive control policy, which adjusts activity difficulty using an Average Emotion Score (AES). This establishes a fully automated closed-loop adaptation cycle, where detected learner affect directly influences the learning environment without requiring explicit user input or post-session questionnaires. The framework is integrated into an open-source educational platform (eduActiv8) to demonstrate feasibility and system-level behavior. Results from alpha-level validation show that the system can continuously monitor learner affect, generate interpretable emotional analytics, and dynamically adjust task difficulty in real time, while reducing user interaction overhead. This study contributes a modular architecture for affect-aware educational systems by combining real-time ensemble emotion recognition, probabilistic fusion of heterogeneous outputs, and closed-loop instructional adaptation. The proposed framework provides a foundation for future research in scalable, emotion-driven intelligent tutoring and adaptive learning environments. Full article

Oncology nursing is one of healthcare’s most emotionally demanding specialties, characterized by sustained exposure to patient suffering and mortality. While global burnout rates reach 40–60%, emotional intelligence (EI) is a potential protective resource that remains underexamined in Middle Eastern contexts. Despite growing global evidence, little is known about these relationships in Middle Eastern healthcare systems, where cultural norms and workforce structures may shape emotional processes differently. This study examined whether EI was significantly associated with lower burnout across personal, work-related, and client-related dimensions among oncology nurses in Saudi Arabia. Methods: A cross-sectional correlational study enrolled 172 oncology nurses from three tertiary hospitals in Riyadh. Participants completed validated Arabic versions of the Schutte Self-Report Emotional Intelligence Test (SSEIT) and the Copenhagen Burnout Inventory (CBI). Hierarchical regression analyses examined predictive relationships while controlling for age and experience. Results: EI demonstrated significant inverse correlations with personal (r = −0.41), work-related (r = −0.38), and client-related burnout (r = −0.33, p < 0.001). In hierarchical models, EI emerged as a significant predictor of lower scores across all dimensions, explaining 11–17% of unique variance beyond demographic factors. The strongest association was with personal burnout. Causality cannot be inferred from this cross-sectional design. Conclusion: EI functions as a significant protective factor against burnout. Healthcare organizations should integrate EI development into professional training to strengthen workforce resilience and sustain care quality. Full article

The COVID-19 pandemic significantly increased adolescent digital engagement, but whether the rise in cyberbullying persists beyond the crisis is not well understood, especially in Southeast Asia. This study examined social media addiction, perceived stress, emotional intelligence, and cyberbullying among 416 Thai secondary students (grades 7–12) during the pandemic-to-endemic transition (June–October 2023). Participants completed validated Thai-language instruments assessing cyberbullying, social media addiction, perceived stress, and emotional intelligence. Results showed 66.4% of adolescents were involved in cyberbullying, with 32.2% as bully-victims. Social media addiction correlated with cyberbullying perpetration (r_s = 0.33, p < 0.001) and victimization (r_s = 0.22, p < 0.001), as did perceived stress (r_s = 0.20 and 0.29; p < 0.001). Emotional intelligence showed negative correlations with cyberbullying perpetration (r_s = −0.15, p = 0.002) and victimization (r_s = −0.10, p = 0.048). Over one-third (34.4%) were at high risk for social media addiction. These findings indicate that during the pandemic-to-endemic transition, Thai adolescents showed elevated cyberbullying involvement, high social media addiction, and moderate-to-high stress—a profile consistent with sustained digital risk. These results highlight the need for integrated interventions that address digital wellness, stress management, and the development of emotional intelligence among Thai adolescents. Full article

This study investigates how two key characteristics of AI-enabled chatbots in mobile banking applications—perceived intelligence and perceived anthropomorphism—influence users’ cognitive and hedonic evaluations, namely perceived usefulness, confirmation, and perceived enjoyment, and how these evaluations subsequently shape user satisfaction and continuance intention. Grounded in the Expectation–Confirmation Model (ECM), the study also examines the moderating role of users’ need for interaction with service employees in these relationships. Using a quantitative research design, data were collected through a structured survey from 402 users of AI-enabled mobile banking applications in Türkiye. The proposed model was tested using partial least squares structural equation modeling (PLS-SEM), and moderated mediation effects were analyzed using Hayes’ PROCESS Macro (Model 58). The results reveal that perceived intelligence positively affects perceived anthropomorphism, perceived usefulness, perceived enjoyment, and confirmation, while perceived anthropomorphism further reinforces these effects. Cognitive and emotional evaluations significantly enhance user satisfaction, which in turn strongly predicts continuance intention toward chatbot usage. Moreover, the need for interaction with service employees significantly moderates the indirect effects of perceived usefulness, perceived enjoyment, and confirmation on satisfaction and continuance intention. By extending the expectation–confirmation model with both cognitive and emotional dimensions, this study offers novel insights into user-centered chatbot design in mobile banking and highlights the importance of individual differences in shaping sustained technology use. Full article

Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by inattention, hyperactivity, and impulsivity, compounded by difficulties in emotional regulation, which have sparked growing interest due to their relationship with emotional intelligence (EI). Background/Objectives: The objective of this study was to analyze the effectiveness and characteristics of interventions aimed at developing EI in people diagnosed with ADHD. Methods: A systematic review was conducted following PRISMA 2020 in the Web of Science, Scopus, PubMed, Dialnet, ERIC, and SpringerLink databases. After applying inclusion and exclusion criteria and evaluating methodological quality, 31 studies were selected. Results: The evidence shows that children and adolescents with ADHD have lower levels of EI than the typically developing population, especially in emotional regulation, stress management, adaptability, and interpersonal skills. Interventions focused on emotional training have demonstrated improvements in emotional competencies, self-control, ADHD symptoms, and social functioning. However, variations are observed according to age, clinical subtype, the presence of comorbidities, and the type of informant, as well as heterogeneity in the assessment instruments used. Conclusions: Strengthening EI emerges as a promising complementary strategy for improving the emotional and social adaptation of people with ADHD. It is recommended to move toward longitudinal studies and more personalized interventions tailored to the clinical and developmental characteristics of the disorder. Full article

Generative artificial intelligence (AI) is increasingly integrated into sustainability-oriented entrepreneurial practices, raising important questions about its role in shaping human creativity and innovation. This qualitative study examines how postgraduate social entrepreneurship students engage with generative AI during the creativity phase of sustainable startup development. Drawing on Amabile’s componential theory of creativity, this study explores how AI is perceived to relate to domain-relevant skills, creativity-relevant processes, task motivation, and social–contextual factors. Data were collected through an AI-assisted ideation task, followed by semi-structured interviews, and analyzed using reflexive thematic analysis. The findings reveal that generative AI was perceived as supporting information access and associative thinking, while being unable to replicate human intuition and the “aha” moment associated with deep creativity. Moreover, AI was perceived to have limited influence on intrinsic motivation, which remains driven by personal values and contextual responsibility. Socially, AI was consistently described as a tool rather than a teammate, with emotional responses regarded as superficial. The study further suggests that AI may be understood as a social–contextual condition and highlights a perceived trade-off between efficiency and creativity in AI-assisted ideation. These insights extend the application of creativity theory to AI-supported sustainability contexts and offer practical implications for fostering responsible, human-centered innovation in entrepreneurship education. Full article

In the context of the aesthetic economy and the rapid development of digital intelligence, product design is increasingly required to address not only functional performance but also users’ emotional needs. However, due to the ambiguity and subjectivity of perceptual requirements, it remains difficult to accurately translate user emotions into specific design solutions. To address this challenge, this study proposes an integrated Kansei Engineering–machine learning framework for optimizing product design. First, user perceptual data are collected through questionnaires and interviews, and key perceptual imagery words are extracted using the Latent Dirichlet Allocation (LDA) model and factor analysis. Then, product design elements are systematically decomposed, and their relative importance is determined using the fuzzy analytic hierarchy process (FAHP). Based on this, a mapping relationship between perceptual imagery and design elements is established. Subsequently, the XGBoost model is employed to predict and optimize design element combinations. The optimized design schemes are further generated using AIGC technology and validated through eye-tracking experiments and subjective evaluations.The results show that the proposed method achieves high predictive accuracy (R² = 0.87) and significantly improves the emotional expression of product design. This study contributes to the integration of Kansei Engineering and machine learning by providing a data-driven approach for emotional design optimization, offering theoretical, practical, and strategic guidance for intelligent product design in industrial contexts. Full article

This study examines the impact of explainable artificial intelligence (XAI) features on user satisfaction and purchase intention in Saudi mobile shopping applications, utilising the stimulus–organism–response (S–O–R) framework. With the increasing reliance on AI-driven decision support in e-commerce, enhancing transparency, fairness, trustworthiness, and interpretability has become crucial for shaping consumer perceptions and behavioural responses. The research employed a quantitative methodology using partial least squares structural equation modelling (PLS-SEM) to examine the relationships among stimulus factors, cognitive and affective states, consumer satisfaction, and purchase intention. In a survey of 597 respondents from Jeddah and Makkah, Saudi Arabia, the findings highlight that fairness and bias detection, trustworthiness, and transparency significantly influence consumers’ cognitive and affective states, which in turn enhance satisfaction and intention to purchase. Consumer satisfaction emerged as a critical mediator, reinforcing the role of positive emotional and cognitive experiences in driving purchase behaviours. However, interpretability showed limited impact, suggesting that consumers may prioritise fairness and trustworthiness over technical clarity of explanations. Theoretically, this study contributes to advancing knowledge on the role of XAI in consumer behaviour by integrating fairness, transparency, and affective responses into the S–O–R paradigm. From a managerial perspective, the results underscore the importance for mobile shopping platforms to design AI systems that foster trust, reduce perceived bias, and ensure transparency, thereby improving consumer engagement and purchase outcomes. By addressing gaps in interpretability and transparency, businesses can strengthen user trust and loyalty, ultimately enhancing competitive advantage in Saudi Arabia’s rapidly growing e-commerce sector. Full article

Artificial intelligence (AI) is increasingly embedded in digital marketing, enabling organisations to personalise communication, analyse consumer data, and optimise decision-making processes. Despite its widespread adoption, limited empirical research has examined whether AI-driven digital marketing contributes to responsible consumption and production, as articulated in Sustainable Development Goal 12 (SDG 12). Grounded in a capability-based and marketing intelligence framework, this study investigates the mechanisms through which AI-driven digital marketing influences responsible marketing outcomes. Using survey data from 120 professionals in multinational corporations (MNCs) operating in South Africa, the study examines how AI-driven digital marketing influences responsible marketing outcomes aligned with Sustainable Development Goal 12 (SDG 12), with particular emphasis on the mediating roles of predictive consumer analytics and sentiment-based consumer understanding as distinct dimensions of AI-enabled marketing intelligence. Instead, its influence operates indirectly through sentiment-based consumer understanding, while predictive consumer analytics show no significant effect. These results suggest that AI contributes to responsible consumption primarily when it enhances firms’ capacity to interpret consumer values, emotions, and ethical concerns. The study advances the digital marketing and sustainability literature by reframing AI as a relational and sense-making capability while offering practical guidance for aligning AI-driven marketing strategies with SDG 12 in emerging markets. Full article

This study examines how integrating Creative Problem Solving (CPS) and generative artificial intelligence (GenAI) within animation storytelling education can foster sustainability-related competencies in higher education. A twelve-week mixed-methods action research design was implemented in a “Storytelling and Scriptwriting” course at a university of technology in northern Taiwan (N = 60). The intervention design combined a CPS-aligned instructional sequence, six scaffolded assignments (including a text-to-image resemiotization task), pre–post CPS cognition and affect scales, CPS-dimensioned assignment self-assessments, reflective journals, and expert evaluations of final story prototypes using the Consensual Assessment Technique. Quantitative results showed significant gains in students’ CPS-related narrative cognition and affective resilience (p < 0.001), as well as consistently high self-reported engagement across CPS dimensions for all assignments, particularly for the text-to-image and personal narrative tasks. Expert ratings indicated high levels of originality, narrative coherence, emotional impact, and social relevance in final prototypes, while qualitative data highlighted reduced “blank page” anxiety, greater willingness to revise, and more collaborative, systems-oriented narrative reasoning. The findings suggest that a CPS- and GenAI-supported teaching model can function as a cognitive bridge for heterogeneous cohorts, positioning GenAI as a conditional amplifier embedded within a reflective CPS framework and helping to translate abstract sustainability-related competencies—such as anticipatory, normative, strategic, and interpersonal competencies—into concrete creative media practices. Full article

We propose a Dual-Channel assisted Music Emotion Perception and Visualization (DC-MEPV) framework designed for ambient lighting in intelligent vehicle cockpits, addressing the increasing demand for advanced human–machine interaction in the automotive industry. This framework consists of three main components: the Multi-Scale Feature Extraction Block (MSFEB), the Global Sequence Modeling Block (GSMB), and the Emotional Color Visualization Algorithm (ECV-Algo). The MSFEB extracts valence and arousal (V-A) features from dual channels at multiple temporal scales, with each channel employing a hybrid neural network architecture to capture multi-scale emotional representations. The GSMB integrates positional encoding, bidirectional long short-term memory (BiLSTM) networks, and multi-head self-attention mechanisms to dynamically model global emotional sequences. The ECV algorithm utilizes personalized emotion–color association rules to achieve expressive emotion-driven lighting visualization based on a continuous mapping from emotion space to color space. We conducted comprehensive comparison and ablation experiments to evaluate the model’s emotion perception performance, and designed three metrics to evaluate the quality of the generated visualizations. The model outperformed other networks in both comparative and ablation experiments. Additionally, the generated lights demonstrated strong performance in terms of CIEDE2000 variation rates, unique color ratios, and joint histogram entropy. DC-MEPV achieved excellent performance in emotion perception and visualizations on the DEAM and PMEmo datasets. Full article

The increasing prevalence of work-related stress requires advanced, non-intrusive physiological monitoring solutions. As conventional methods are often impractical for continuous, real-world applications, this study investigates the deployment of artificial intelligence models on embedded systems for real-time emotion recognition from physiological signals. The study identified critical constraints for embedded implementation, including model size and memory capacity. An evaluation of various machine learning algorithms revealed that, while models like K-Nearest Neighbors (KNN) achieve high accuracy (88.8%), their excessive memory footprints make them unsuitable for resource-constrained hardware. Consequently, Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and recurrent neural network (RNN) architectures were deployed on an STM32F411 microcontroller, for which model compression proved essential. An experimental study validated the approach, achieving high recognition rates for pronounced emotions such as hatred (91%) and anger (85%), though with a lower accuracy for more subtle states. These results confirm the potential of embedded AI systems for physiological monitoring, highlighting the critical importance of feature selection and model compression for practical implementation. Full article

Background: Intensive care units (ICUs) are high-acuity environments that require respiratory therapists (RTs) to maintain vigilance, manage emotions, and make rapid clinical decisions. In such settings, performance stability is critical for patient safety. Although emotional intelligence (EI) and work–life balance (WLB) have been linked to professional outcomes in health care, their independent and direction-specific associations with job performance among ICU respiratory therapists remain underexamined. Methods: A national cross-sectional survey was conducted among respiratory therapists working in ICUs across Saudi Arabia (June 2025–January 2026). EI was measured using the Wong and Law Emotional Intelligence Scale. WLB was assessed using the work interference with personal life (WIPL), personal life interference with work (PLIW), and work–personal life enhancement (WPLE) scales. Job performance was evaluated using the Individual Work Performance Questionnaire. Correlation and multivariable linear regression analyses were performed to estimate independent associations. Results: A total of 392 RTs were included in the final analysis. Higher EI was independently associated with greater task performance (B = 0.21, p < 0.01) and contextual performance (B = 0.30, p < 0.001), and with lower counterproductive work behaviours (B = −0.24, p < 0.001). Among WLB dimensions, PLIW showed the strongest adverse association, predicting lower task performance (B = −0.20, p < 0.05) and higher counterproductive behaviours (B = 0.39, p < 0.001), but was not significantly associated with contextual performance in the fully adjusted model. WPLE demonstrated modest positive associations with performance, whereas WIPL was not significant in adjusted models. Conclusions: Job performance among ICU respiratory therapists is shaped by both emotional regulatory capacity and cross-domain strain. Personal life interference with work emerged as the most influential adverse predictor, whereas EI was associated with constructive performance patterns. Findings should be interpreted in light of the cross-sectional design and self-reported data. Sustaining performance in high-acuity settings requires attention to emotional competencies and structural sources of role conflict alongside clinical expertise. These findings inform workforce strategies to support performance and sustainability in critical care settings. Full article

Background: Digitalization and artificial intelligence-supported clinical decision support systems (AI-DSS), defined here as tools that generate patient-specific alerts, risk estimates, prioritization prompts, documentation suggestions, or related recommendation outputs intended to support rather than replace professional nursing judgment, can improve clinical decision-making, yet they may also amplify technostress and burnout, with downstream effects on missed nursing care and implementation readiness. Methods: We surveyed 239 registered nurses from a tertiary-care hospital in Timișoara, Romania (January–March 2025), including critical care (n = 60) and general wards (n = 179). Measures included a 15-item technostress scale, eHEALS, Maslach Burnout Inventory–Human Services Survey (MBI-HSS), Safety Attitudes Questionnaire (SAQ) teamwork and safety climate subscales, a 10-item missed nursing care inventory, and a six-item AI-DSS acceptance scale reflecting perceived usefulness, trust, and stated willingness to use such tools if available as an attitudinal readiness outcome rather than as routine observed use. Multivariable regression, exploratory mediation models, cluster analysis, and exploratory ROC analysis were performed. Results: Higher technostress was associated with higher emotional exhaustion (r = 0.52) and more missed care (r = 0.41), whereas eHealth literacy correlated with higher AI-DSS acceptance (r = 0.35) and lower technostress (r = −0.34). In adjusted models, technostress (per 10 points) was associated with higher missed care (β = 0.28, p < 0.001) (equivalent to 0.14 points per 5-point increase) and higher odds of low AI-DSS acceptance (OR = 1.38, p = 0.001), while eHealth literacy was associated with lower odds of low acceptance (OR = 0.71 per 5 points, p < 0.001). Burnout and the safety climate statistically accounted for approximately 35% of the technostress–missed care association. Three workflow phenotypes were identified, with the high-strain/low-literacy cluster showing the most missed care (3.5 ± 1.8) and the lowest AI acceptance (19.7 ± 5.2). An exploratory in-sample ROC model for intention to leave achieved an AUC of 0.82. Conclusions: Higher technostress clustered with worse nurse well-being, more care omissions, and lower AI-DSS acceptance, whereas eHealth literacy appeared protective. Interventions combining digital skills support, usability-focused redesign, and a stronger safety climate may reduce missed care and support safer AI implementation. Full article