BACKGROUND:Pulse characteristics are well-established biomarkers of physical health; however, their relevance to psychological well-being remains insufficiently explored. A key barrier is the difficulty of acquiring pulse recordings and blood pressure measurements of adequate quality outside clinical or laboratory settings by using accessible measurement approaches. OBJECTIVE:This study aimed to examine the feasibility of using smartphone photoplethysmography to extract fingertip pulse-waveform features and to evaluate their associations with psychological measures. It further aimed to systematically compare time-, curvature-, and frequency-domain pulse-waveform features in relation to psychological variables. METHODS:A total of 127 students and university employees in Shenzhen, China, were recruited. Participants recorded repeated 4-minute fingertip videos by using a custom smartphone app while a fingertip oximeter simultaneously acquired reference pulse signals. Smartphone videos were converted into photoplethysmography signals, segmented into beat-to-beat intervals, and summarized into time-, curvature-, and frequency-domain features, with normalization for heart rate and stature. Psychological well-being and mental health were assessed using the Satisfaction With Life Scale, Subjective Vitality Scale, Positive and Negative Affect Schedule, Patient Health Questionnaire-9, Generalized Anxiety Disorder-7, and the Self-Assessment Manikin. Associations between pulse-waveform features and psychological measures were examined using univariate regression with participant-level aggregation and cluster-robust standard errors. Random forest models evaluated multivariate predictive performance by using participant-level cross-validation. Agreement between smartphone-derived and oximeter-derived waveform features was assessed using Bland-Altman analysis. RESULTS:Correlation analyses revealed strong within-domain associations among time-, curvature-, and frequency-domain pulse-waveform features, with comparatively weaker cross-domain correlations. A correlation-based feature-selection procedure reduced multicollinearity and yielded a final set of 7 features: estimated reflection index, crest time (CT), the third curvature minimum (F/A), the fourth curvature minimum (H/A), the first power spectrum density component, the baseline of Fourier decomposition (V0), and systolic blood pressure. Univariate regression analyses indicated that negative psychological states were primarily associated with time- and curvature-domain features. Depressive symptoms were significantly related to F/A, V0, and the estimated reflection index. Anxiety showed an association with F/A, and negative affect was associated with CT and F/A. In contrast, positive affect measures showed fewer and weaker associations. Valence was related to F/A and H/A, whereas arousal was associated with CT and H/A. Random forest models demonstrated statistically significant but modest predictive performance for negative mental health outcomes, with weaker performance for positive affect. Bland-Altman analyses indicated minimal systematic bias for outcomes with significant predictive correlations. Comparisons with an oximeter showed significant correlations and acceptable agreement, with time-domain features demonstrating greater robustness than reflection-based metrics. CONCLUSIONS:Smartphone-based photoplethysmography can capture pulse-waveform features associated with psychological measures, particularly negative psychological states. However, predictive performance remains limited, and variability in signal quality from user-operated recordings poses a practical challenge.

Psychological scale refinement traditionally relies on response-based methods such as factor analysis, item response theory, and network psychometrics to optimize item composition. Although rigorous, these approaches require large samples and may be constrained by data availability and cross-cultural comparability. Recent advances in natural language processing suggest that the semantic structure of questionnaire items may encode latent construct organization, offering a complementary response-free perspective. We introduce a topic-modeling framework that operationalizes semantic latent structure for scale simplification. Items are encoded using contextual sentence embeddings and grouped via density-based clustering to discover latent semantic factors without predefining their number. Class-based term weighting derives interpretable topic representations that approximate constructs and enable merging of semantically adjacent clusters. Representative items are selected using membership criteria within an integrated reduction pipeline. We benchmarked the framework across DASS, IPIP, and EPOCH, evaluating structural recovery, internal consistency, factor congruence, correlation preservation, and reduction efficiency. The proposed method recovered coherent factor-like groupings aligned with established constructs. Selected items reduced scale length by 60.5

Using large language models (LLMs) to assist psychological counseling is an important task in the field of natural language processing. The construction of high-quality psychological support dialogue corpora serves as a critical foundation for training counseling-oriented conversational models. However, existing data generation approaches generally suffer from several limitations, including emotionally stable seekers, limited variation in emotional dynamics, and a high degree of compliance with counselors' guidance. These issues result in LLM that lack the capability to effectively respond to emotionally unstable scenarios. In addition, counselor responses are typically driven by problem-solving objectives, thereby overlooking the role of emotion-focused interaction, which are essential in psychological counseling. To address these gaps, we propose EmoTrace, a multi-turn dialogue corpus generation framework centered on modeling seekers' emotional trajectories. we construct seekers' cognitive profile and introduce a seeker module with emotional schemas and an associated activation mechanism, a counselor module, and an emotional trajectory control module, thereby enhancing the layering of the seeker's emotional expression and the counselor's targeted empathic expression. Experimental results demonstrate that the proposed method outperforms existing approaches in terms of emotional richness and empathy quality.

Background: Previous research has identified a high risk of smartphone addiction and its association with general and schoolcontextual mental health problems (ie, psychological distress and academic burnout) among Chinese adolescents. Nonetheless, the directional and symptom-level relationships among these problems remain underexamined, hindering understanding of the mechanisms underlying their co-occurrence. Based on the I-PACE (Interaction of Person-Affect-Cognition-Execution) model, this study addressed these gaps by performing a cross-lagged panel network (CLPN) analysis. Methods: Data were obtained from a survey of 589 adolescents in secondary schools in China at two time points, with a five-month interval. Using a CLPN approach, this study examined the directional relationships among smartphone addiction, academic burnout, and psychological distress at the symptom level. Results: The depression and anxiety symptoms of psychological distress, as well as the withdrawal symptom of smartphone addiction, emerged as strong bridging symptoms. Moreover, three mechanisms linking the three problems were identified. First, depression predicted cyberspace-oriented relationships and smartphone overuse, and anxiety predicted daily-life disturbances. Second, withdrawal predicted anxiety. Third, depression predicted exhaustion from studying, and withdrawal predicted cynical attitudes towards studying. Conclusion: The results support the predisposing factors-smartphone addiction cycle described in the I-PACE model, aligning with the vulnerability, predisposition entrenchment, and intensification mechanisms proposed by the model. Psychological distress symptoms, as predisposing factors, playing key roles in the cycle. However, the results indicate that school situational factors such as academic burnout may function as distal outcomes rather than triggers in the cycle. The key linking mechanisms identified in this study are informative for generating hypotheses for future research and developing practical intervention strategies.

As adolescents face increasing academic, familial, and social pressures, their stress levels rise, leading to persistent emotional distress and loss of interest in activities. This issue is exacerbated by immature psychological development and poor self-regulation, resulting in higher rates of hospitalizations and dropouts. Traditional stress management interventions, such as therapist-guided techniques, often lack engagement and fail to capture the interest of adolescents. This study introduces Soul Gate, a serious game designed for adolescents aged 11–17, which integrates biofeedback technology and Self-Efficacy Theory. Utilizing the Experience, Dynamics, and Artifacts (EDA) game design framework, the game incorporates engaging mechanics and is structured around Cognitive Behavioral Stress Management (CBSM), featuring four key stages: breathing exercises, heart rate training, attention bias training, and heart rate variability regulation. By leveraging these principles, it offers an interactive self-help tool to enhance stress regulation and emotional resilience. Soul Gate employs a dual-system biofeedback approach, monitoring physiological indicators such as heart rate and brainwaves, and providing real-time adaptive feedback in games that improves player awareness and emotional management. A randomized controlled trial will assess its effectiveness, with expected outcomes demonstrating its potential as a viable intervention for reducing adolescent stress and enhancing emotional self-regulation. This study highlights the value of integrating biofeedback with gamification in mental health therapy and outlines future research directions to improve cultural adaptability and device portability.

Positive psychology dialogue aims to support emotional distress and positive resource building, requiring models to produce not only empathetic replies but also coherent progression through a multi-turn support process. Existing resources often reduce supervision to turn-level strategies or holistic preference labels, leaving process position, support function, and local repair targets implicit. We introduce StageWell, a process-aligned Chinese corpus for positive psychology dialogue, together with HQS, a structured protocol for data construction and evaluation. StageWell organizes support into a six-stage support process and uses a multi-agent whole-dialogue rewriting workflow to construct 12,445 SFT instances, 1,849 DPO preference pairs, and a GroundTruth subset of 120 expert-revised dialogues and 977 QA pairs. Guided by HQS, DPO pairs are built as process-localized repairs: flawed model outputs are used as rejected responses, and targeted rewrites under the same context and stage constraint are used as chosen responses. Across four 9B-14B open-source LLMs, this supervision yields robust gains in process control, response quality, and safety. Averaged across models, BERTScore improves by 0.037, Q-Overall increases by 1.32 points, S-exact increases by 0.236, and the H-critical rate decreases by 0.167. These results highlight the value of modeling supportive dialogue as a structured multi-turn support process rather than as single-turn response generation.

Problematic gaming in adolescents has been an increasing concern in society. This study examined the roles of emotion-related (supportive and non-supportive responses to children’s negative emotions) and academic-related (parental involvement in education) parenting behaviors in adolescent problematic gaming and the possible mediators. We analyzed data from 4270 Chinese parent-adolescent dyads. Adolescents had an average age of 14.60 years (SD = 1.69; 69.86

Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental condition that can affect individuals across lifespan and is characterized by inattention, hyperactivity, and impulsivity. Traditional ADHD diagnostic methods commonly rely on subjective assessments, leading to potential inaccuracies. This study proposes a novel mobile game that utilizes a combined continuous screening paradigm, integrating classical psychological measures such as the Continuous Performance, Simon, and Go/No-Go tasks to provide a 4-min ADHD screening tool for children. The serious game screening design focuses on the two dimensions of sustained attention, and hyperactivity-impulsivity in ADHD and was verified using a test comparing children with ADHD and neurotypical children. The screening model achieved a sensitivity of 0.82. This study provides a methodological framework for leveraging serious games on mobile platforms to facilitate early ADHD screening.

Human emotion synthesis is a crucial aspect of affective computing. It involves using computational methods to mimic and convey human emotions through various modalities, with the goal of enabling more natural and effective human-computer interactions. Recent advancements in generative models, such as Autoencoders, Generative Adversarial Networks, Diffusion Models, Large Language Models, and Sequence-to-Sequence Models, have significantly contributed to the development of this field. However, there is a notable lack of comprehensive reviews in this field. To address this problem, this paper aims to address this gap by providing a thorough and systematic overview of recent advancements in human emotion synthesis based on generative models. Specifically, this review will first present the review methodology, the emotion models involved, the mathematical principles of generative models, and the datasets used. Then, the review covers the application of different generative models to emotion synthesis based on a variety of modalities, including facial images, speech, and text. It also examines mainstream evaluation metrics. Additionally, the review presents some major findings and suggests future research directions, providing a comprehensive understanding of the role of generative technology in the nuanced domain of emotion synthesis.

Leisure and work are two important aspects of human well-being. However, most studies on individuals’ psychological well-being have examined these aspects independently, based on either job characteristics or a leisure perspective. In this study, we used a unified theoretical framework of the physical activity-mediated demand–control model to explore the impacts of job characteristics and leisure activities on people’s psychological well-being. Over 4 weeks, 662 Chinese employees completed two waves of time-lagged surveys with items measuring job autonomy, leisure activities, life satisfaction, and emotional exhaustion. The results showed that job autonomy increases employees’ life satisfaction while decreasing emotional exhaustion. Moreover, leisure activities mediate the relationships between job autonomy, emotional exhaustion, and life satisfaction. This paper adopted the comprehensive framework to integrate job characteristics and leisure activity research areas and revealed a work-to-leisure positive spillover effect.

This study addresses the increasing prevalence of emotional and behavioral problems among adolescents by designing and validating a game-based intervention model grounded in the Process Model of Emotion Regulation. We propose a novel integration of biofeedback therapy with Rational Emotive Behavior Therapy to establish a three-stage intervention framework: “emotional exposure - biofeedback - strategy reinforcement”. The research introduces Balance Masters, a serious game featuring a platform balancing mechanic as its core gameplay, connected to a Bluetooth heart rate sensor to implement a real-time biofeedback system. Through a self-controlled experiment with adolescents in elementary schools, results demonstrated significant improvements in cognitive reappraisal scores and significant reductions in expressive suppression scores post-intervention. Heart rate measurements showed a significant decreasing trend throughout gameplay sessions, with particularly notable differences between late and early phases. Game experience evaluations indicated high levels of immersion and positive affect ratings with strong usability metrics. This research contributes an accessible, highcompliance innovative solution for addressing emotion regulation challenges in adolescents, with implications for digital mental health interventions.

Smartphone photoplethysmography (PPG) offers a cost-effective and accessible method for continuous blood pressure (BP) monitoring, but faces persistent challenges with accuracy and interpretability. This study addresses these limitations through a series of strategies. Data quality was enhanced to improve the performance of traditional statistical models, while SHapley Additive exPlanations (SHAP) analysis ensured transparency in machine learning models. Waveform features were analyzed to establish theoretical connections with BP measures, and feature engineering techniques were applied to enhance prediction accuracy and model interpretability. Bland–Altman analysis was conducted, and the results were compared against reference devices using multiple international standards to evaluate the method's feasibility. Data collected from 127 participants demonstrated strong correlations between smartphone-derived digital waveform features and those from reference BP devices. The mean absolute errors (MAE) for systolic BP (SBP), diastolic BP (DBP), and pulse pressure (PP) using multiple linear regression models were 7.75, 6.35, and 4.49 mmHg, respectively. Random forest models further improved these values to 7.34, 5.79, and 4.45 mmHg. Feature importance analysis identified key contributions from time-domain, frequency-domain, curvature-domain, and demographic features. However, Bland–Altman analysis revealed systematic biases, and the models barely meet established accuracy standards. These findings suggest that while smartphone PPG technology shows promise, significant advancements are required before it can replace traditional BP measurement devices.

In untrimmed video tasks, identifying temporal boundaries in videos is crucial for temporal video grounding. With the emergence of multimodal large language models (MLLMs), recent studies have focused on endowing these models with the capability of temporal perception in untrimmed videos. To address the challenge, in this paper, we introduce a multimodal large language model named MLLM-TA with precise temporal perception to obtain temporal attention. Unlike the traditional MLLMs, answering temporal questions through one or two words related to temporal information, we leverage the text description proficiency of MLLMs to acquire video temporal attention with description. Specifically, we design a dual temporal-aware generative branches aimed at the visual space of the entire video and the textual space of global descriptions, simultaneously generating mutually supervised consistent temporal attention, thereby enhancing the video temporal perception capabilities of MLLMs. Finally, we evaluate our approach on both video grounding task and highlight detection task on three popular benchmarks, including Charades-STA, ActivityNet Captions and QVHighlights. The extensive results show that our MLLM-TA significantly outperforms previous approaches both on zero-shot and supervised setting, achieving state-of-the-art performance.

Affective computing stands at the forefront of artificial intelligence (AI), seeking to imbue machines with the ability to comprehend and respond to human emotions. Central to this field is emotion recognition, which endeavors to identify and interpret human emotional states from different modalities, such as speech, facial images, text, and physiological signals. In recent years, important progress has been made in generative models, including Autoencoder, Generative Adversarial Network, Diffusion Model, and Large Language Model. These models, with their powerful data generation capabilities, emerge as pivotal tools in advancing emotion recognition. However, up to now, there remains a paucity of systematic efforts that review generative technology for emotion recognition. This survey aims to bridge the gaps in the existing literature by conducting a comprehensive analysis of over 320 research papers until June 2024. Specifically, this survey will firstly introduce the mathematical principles of different generative models and the commonly used datasets. Subsequently, through a taxonomy, it will provide an in-depth analysis of how generative techniques address emotion recognition based on different modalities in several aspects, including data augmentation, feature extraction, semi-supervised learning, cross-domain, etc. Finally, the review will outline future research directions, emphasizing the potential of generative models to advance the field of emotion recognition and enhance the emotional intelligence of AI systems.

Promoting positive mental health and well-being, especially in adolescents, is a critical yet underexplored area in natural language processing (NLP). Most existing NLP research focuses on clinical therapy or psychological counseling for the general population, which does not adequately address the preventative and growth-oriented needs of adolescents. In this paper, we introduce DeepWell-Adol, a domain-specific Chinese dialogue corpus grounded in positive psychology and coaching, designed to foster adolescents’ positive mental health and well-being. To balance the trade-offs between data quality, quantity, and scenario diversity, the corpus comprises two main components: human expert-written seed data (ensuring professional quality) and its mirrored expansion (automatically generated using a two-stage scenario-based augmentation framework). This approach enables large-scale data creation while maintaining domain relevance and reliability. Comprehensive evaluations demonstrate that the corpus meets general standards for psychological dialogue and emotional support, while also showing superior performance across multiple models in promoting positive psychological processes, character strengths, interpersonal relationships, and healthy behaviors. Moreover, the framework proposed for building and evaluating DeepWell-Adol offers a flexible and scalable method for developing domain-specific datasets. It significantly enhances automation and reduces development costs without compromising professional standards—an essential consideration in sensitive areas like adolescent and elderly mental health. We make our dataset publicly available.

Purpose: This study explores the effects of a customized virtual reality (VR) role-playing videogame, “the Transfer Student,” on the psychological resilience of Chinese rural-to-urban migrant adolescents, a population significantly underrepresented in resilience intervention research. Method: Sixty-two migrant adolescents (ages 12–17) were randomized to play the videogame (intervention), where the character overcame challenges as a rural student adapting to an urban school, or watch VR-based scenic videoclips (control). Results: The intervention group showed moderate-size improvements in resilience at immediate post-test, compared with the control (Hedge's g = 0.47, SE = 0.32). Additionally, participants’ level of immersion in the virtual environment was significantly related to intervention effects. Discussion: The findings preliminarily support the feasibility and efficacy of this VR-based game as a digital resilience intervention approach for migrant adolescents. Future research should test this approach in larger, more diverse samples.

Wellbeing has received increasing attention in research and practice, yet its complex structure remains insufficiently explored. Most studies rely on latent-variable models that treat wellbeing components as independent, failing to account for the covariation widely observed among them. Adopting a systems perspective, this study investigates the network structure of wellbeing and identifies its most influential components. The network analysis was applied to the Wellbeing Profiler 15, a theory-driven measure that comprises 15 wellbeing constituents: autonomy, competence, clarity of thinking, empathy, engagement, emotional stability, meaning, optimism, prosocial behavior, positive emotions, positive relationships, resilience, self-acceptance, self-esteem, and vitality. The dataset consists of a large sample of Chinese adolescents (N = 1093). The results revealed a highly interconnected network, with resilience, competence, and self-esteem emerging as the most influential components, while empathy and self-acceptance showed lower influence within the network. Our findings expand the understanding of the complex structure of wellbeing in an underrepresented cultural context and highlight the potential for targeted interventions focused on key constituents, such as resilience, to achieve synergistic improvements in adolescent wellbeing.

Psychological resilience refers to an individual's ability to adapt to adversity and stress. Education on psychological resilience during childhood can contribute to future mental health and well-being, such as reducing anxiety and depression [1] [2]. However, traditional psychosocial resilience training faces challenges with accessibility, heavily constrained by cost and spatiotemporal limitations. Recently, emerging large language models (LLMs) have demonstrated exceptional capabilities in conversational tasks, indicating new prospects for cultivating children's psychological resilience. In our work, 1) we conducted qualitative interviews with 10 Chinese children (aged 8-12) and their parents to understand their needs and current conditions; 2) based on the interview results and theories of psychological resilience, we summarized three pathways for developing children's psychological resilience using conversational agents (CAs) and identified six key challenges for designing child-centered CAs; 3) we designed and developed a web prototype using optimized LLMs (see Figure 1), which integrates personal and social support factors, to measure and foster children's psychological resilience through conversations; and 4) we invited 48 child volunteers in user testing and designed three sets of experiments to evaluate the effectiveness of system interventions, the effectiveness of measurements, and overall acceptability. Results indicate that the intervention tasks actively promoted psychological resilience in adolescents. Intelligent measurement scores were effectively consistent with traditional scales in objective scoring, while subjective evaluations, such as appeal and fun, significantly exceeded traditional scale scores. Through our practice, we show the potential of CAs in enhancing children's mental health and presented a reference application case. Moreover, we have unearthed notable future research issues, including challenges in designing psychologically educational CAs that are persistently attractive to children, combining real-life support factors with CAs, and ethical concerns regarding safety and privacy.

Positive psychology (PP) is in its third wave, evolving towards an interdisciplinary study of wellbeing. This article proposes computational positive psychology (CPP) as an emerging interdisciplinary field that integrates PP with computational science and technology to advance the understanding of wellbeing and develop evidence-based strategies to promote sustainable flourishing. The key features of CPP include addressing novel research questions that have received limited investigation in the existing literature, collecting large-scale and multimodal data, constructing computational models, and utilizing the results to advance theories, research, and the practice of wellbeing. We review CPP research topics such as: (1) advancing theoretical wellbeing models, (2) efficiently measuring wellbeing and positive traits, (3) exploring interdependent dynamics between individual and systemic wellbeing, (4) enhancing positive psychology interventions, and (5) improving collective wellbeing. The transformative potential of CPP for understanding and promoting wellbeing in the digital era is highlighted, and future research directions are discussed.

Over the past four decades, obesity in children of all ages has increased worldwide, which has intensified the search for innovative intervention strategies. Serious games, a youth-friendly form of intervention designed with educational or behavioral goals, are emerging as a potential solution to this health challenge. To analyze the effectiveness of serious games in improving body composition, physical activity, and dietary change, we performed a systematic review and meta-analysis of randomized controlled trials (RCTs) from PubMed, Web of Science, EMBASE, and Scopus databases. Pooled standardized mean differences (SMD) were calculated for 20 studies (n = 2238 the intervention group; n = 1983 in the control group) using random-effect models. The intervention group demonstrated a slightly better, although non-significant, body composition score, with a pooled SMD of −0.26 (95% CI: −0.61 to 0.09). The pooled effect tends to be stronger with longer duration of intervention (−0.40 [95% CI: −0.96, 0.16] for >3 months vs. −0.02 [95% CI: −0.33, 0.30] for ≤3 months), although the difference was not statistically significant (p-difference = 0.24). As for the specific pathways leading to better weight control, improvements in dietary habits due to serious game interventions were not significant, while a direct positive effect of serious games on increasing physical activity was observed (pooled SMD = 0.61 [95% CI: 0.04 to 1.19]). While the impact of serious game interventions on body composition and dietary changes is limited, their effectiveness in increasing physical activity is notable. Serious games show potential as tools for overweight/obesity control among children and adolescents but may require longer intervention to sustain its effect.