Search Results (1,109)

This study investigates how the origin and language of public attention influence financial markets during geopolitical conflict, using Israel’s experience during the 2023–2025 Gaza War as a case study. We use Google Trends data—in Hebrew, English, and Arabic, sourced both worldwide and domestically—to explain fluctuations in the Tel Aviv Stock Exchange’s TA-35 Index and the Israeli shekel’s exchange rates (USD/ILS and EUR/ILS). The results uncover a striking asymmetry: international searches, especially those in Hebrew and English, have significant power to explain Israeli market performance, while local, domestic searches are largely insignificant. Specifically, global Hebrew attention is positively associated with the shekel appreciating, suggesting that expressions of confidence or solidarity from the diaspora may actively reinforce market stability. In contrast, spikes in global English-language searches correspond with lower equity returns and temporary shekel depreciation, consistent with heightened international risk perception. These findings demonstrate that transnational behavioral networks and diaspora attention critically shape financial resilience during war. By integrating behavioral finance, conflict economics, and computational analytics, this research shows that the geographic and linguistic origin of attention, not just its sheer volume, is the key determinant of market reactions in times of crisis. Full article

Motorcyclists face a disproportionately high risk of severe injury or death compared to other road users, highlighting the need for intelligent rider assistance technologies. This paper presents an initial, modular, and interpretable AI pipeline that generates context-aware safety advice from first-person motorcycle videos with practical inference latency suitable for on-device deployment, framing large language models as interpretable cognitive support agents for motorcycle safety. The system integrates lightweight perception and reasoning components to emulate the function of an Advanced Rider Assistance System (ARAS). Video frames are processed at 1 FPS using Pixtral, a Mistral-based multimodal large language model (MLLM), to produce descriptive scene captions, while YOLOv8 identifies key objects such as vehicles, pedestrians, and road hazards. A Mistral-small language model then fuses this information to generate concise, imperative safety tips. Preliminary evaluations on publicly available motorcycle POV datasets demonstrate promising performance in terms of contextual accuracy, interpretability, and scalability, suggesting potential for real-world deployment in low-resource or embedded environments. The proposed framework offers interpretable, context-aware safety assistance that is particularly valuable for young and newly licensed riders during the transition from supervised training to independent riding, where real-time hazard interpretation support is most needed. Full article

This work explores user needs for educational games and gamification that incorporates Generative Artificial Intelligence (GenAI). As GenAI is increasingly incorporated in educational settings, we must consider both the wide-spanning literature on gamification and games that have been shown to benefit learning, and characterize the needs and desires of relevant stakeholders in developing educational games that incorporate GenAI generally, and specifically for higher education. A mixed-methods questionnaire inquired 345 undergraduate students about their perceptions, use patterns, needs, and desires related to GenAI, educational and non-educational games, and text-based games. GenAI tools are widely used for educational purposes already, but mostly as a supplementary source. Despite the wide use, participants expressed being concerned with accuracy, transparency, and quality. Participants also expressed a desire for an educational game/tool to have scaffolded interactions and to help with learning material in math, science, and language arts. Taken together the findings provide a road map and specific recommendations for developing an educational game incorporating GenAI. The roadmap includes instructional design (i.e., the gamified tools’ content and type(s) of instruction and interaction) through information regarding preferred platforms, game genres, gamified properties (e.g., characters, challenges), and lastly, clear information about concerns students have related to trust and equity that will need to be addressed in an educational game incorporating GenAI. Full article

Learning environment and student engagement (SE) are widely considered valuable to foreign language learning, but how they influence foreign language achievement (LA) remains underexplored. Drawing on sociocultural theory, this survey study explored the impact of the online learning environment (OLE) on LA of Chinese as a Foreign Language (CFL) and the mediating role of SE among 447 international students in China by using structural equation modeling. The results indicated that: (1) the participants had favorable perceptions toward OLE, SE and LA; (2) OLE factors, i.e., accessibility of online learning materials, student interaction, and course organization significantly positively influenced LA, whereas teacher support did not influence LA; (3) SE mediated the positive effects of all the OLE factors on LA. The results suggest that enhancing online learning environment and increasing student engagement are effective means to improve online CFL learning achievement. Full article

Adverse weather removal aims to restore images degraded by haze, rain, or snow. However, existing unified models often rely on implicit degradation cues, making them vulnerable to inaccurate weather perception and insufficient semantic guidance, which leads to over-smoothing or residual artifacts in real scenes. In this work, we propose AWR-VIP, a prior-guided adverse weather removal framework that explicitly extracts semantic and perceptual priors using a frozen vision–language model (VLM). Given a degraded input, we first employ a degradation-aware prompt extractor to produce a compact set of semantic tags describing key objects and regions, and simultaneously perform weather-type perception by prompting the VLM with explicit weather definitions. Conditioned on the predicted weather type and selected tags, the VLM further generates two levels of restoration guidance: a global instruction that summarizes image-level enhancement goals (e.g., visibility/contrast) and local instructions that specify tag-aware refinement cues (e.g., recover textures for specific regions). These textual outputs are encoded by a text encoder into a pair of priors (${\mathbf{P}}_{global}$ and ${\mathbf{P}}_{local}$), which are injected into a UNet-based restorer through global-prior-modulated normalization and instruction-guided attention, enabling weather-adaptive and content-aware restoration. Extensive experiments on a combined benchmark show that AWR-VIP consistently outperforms state-of-the-art methods. Moreover, the VLM-derived priors are plug-and-play and can be integrated into other restoration backbones to further improve performance. Full article

Tomato leaf diseases exhibit subtle inter-class differences and substantial intra-class variability, making accurate identification challenging for conventional deep learning models, especially under real-world conditions with diverse lighting, occlusion, and growth stages. Moreover, most existing approaches rely solely on visual features and lack the ability to incorporate semantic descriptions or expert knowledge, limiting their robustness and interpretability. To address these issues, we propose LPDiag, a multimodal prototype-attention diagnostic framework that integrates large language models (LLMs) for fine-grained recognition of tomato diseases. The framework first employs an LLM-driven semantic understanding module to encode symptom-aware textual embeddings from disease descriptions. These embeddings are then aligned with multi-scale visual features extracted by an enhanced Res2Net backbone, enabling cross-modal representation learning. A set of learnable prototype vectors, combined with a knowledge-enhanced attention mechanism, further strengthens the interaction between visual patterns and LLM prior knowledge, resulting in more discriminative and interpretable representations. Additionally, we develop an interactive diagnostic system that supports natural-language querying and image-based identification, facilitating practical deployment in heterogeneous agricultural environments. Extensive experiments on three widely used datasets demonstrate that LPDiag achieves a mean accuracy of 98.83%, outperforming state-of-the-art models while offering improved explanatory capability. The proposed framework offers a promising direction for integrating LLM-based semantic reasoning with visual perception to enhance intelligent and trustworthy plant disease diagnostics. Full article

Vignettes are brief, descriptive, hypothetical scenarios that have been used to extract attitudes, beliefs, or perceptions from participants across psychology, healthcare, and human–computer interaction. Traditional vignette development is often time and labor-intensive and large language models (LLMs) like ChatGPT-4o may streamline this process. This exploratory between-subjects online survey (n = 66) compared participants’ perceptions of clinically reviewed LLM-generated versus human-written mental health vignettes describing social anxiety, depression, or schizophrenia. Participants rated each vignette on realism, clarity, engagement, emotional impact, perceived likelihood of AI authorship, and likelihood that the target diagnosis applied. Mixed-effects linear regression analyses showed no statistically significant differences between AI-generated and human-written vignettes for any perceived quality rating; estimated source effects were small (|β| ≤ 0.10) with 95% confidence intervals spanning zero across outcomes. Perceived AI authorship likelihood (β = 0.09, 95% CI [−0.22, 0.40]) and correct-diagnosis likelihood ratings (β = −0.07, 95% CI [−0.30, 0.16]) also did not differ by source. Overall, we did not detect statistically significant differences between AI-generated and human-written vignettes. These findings reflect perceptions of AI-generated vignettes that underwent expert clinical review and suggest that LLMs may assist in vignette generation with expert oversight, while highlighting the need for further research on clinical accuracy, diagnostic validity, and generalizability. Full article

This article examines graduate employability challenges in the tourism and hospitality sector of Marrakech, a major tourism destination and strategic regional labour market in Morocco, characterised by strong seasonality, high labour turnover, and persistent education–employment mismatches. Rather than focusing exclusively on technology, the study analyses employability as a multidimensional and context-dependent process, in which digitalisation and artificial intelligence (AI) constitute one influencing factor among others. The research adopts a qualitative, purposive design based on semi-structured interviews conducted between August and October 2025 with 20 stakeholders directly involved in recruitment, training, or early career integration. These include five-star hotel general managers and HR officers, riad managers, travel agencies, recruitment intermediaries, representatives of Morocco’s public employment service (ANAPEC—National Agency for the Promotion of Employment and Skills) and private, regional tourism authorities, academics and young tourism graduates. Interview transcripts were thematically analysed using NVivo to identify recurrent patterns in recruitment practices, skill expectations, and the impact of AI in employability. The results, reflecting stakeholders’ perceptions within this local labour market, show that employability is shaped by six interrelated dimensions: (1) the structure and functioning of the tourism labour market (segmentation, turnover, mobility); (2) partial misalignment between training provision and operational service realities; (3) recruitment standards that prioritise behavioural and relational competences alongside formal qualifications, particularly for frontline positions; (4) language proficiency, especially English and French, as a baseline employability condition; (5) growing expectations regarding digital literacy linked to tourism operations (property management systems, reservation platforms, online reputation management); and (6) the perceived impact of AI-enabled tools (automation of routine tasks, decision-support systems, chatbots), which is seen less as a source of job destruction than as a driver of task reconfiguration and skill upgrading. By situating employer and graduate perceptions within the broader Moroccan employment and training context, the study contributes a place-based understanding of employability in tourism. It highlights the shared responsibility of individuals, employers, and education and training institutions in supporting skill development. The article concludes by discussing policy and practice-oriented levers to strengthen graduate employability, including co-designed curricula, structured internships and mentoring schemes, employer-supported upskilling in tourism-specific digital and AI-related competences, and reinforced labour-market intermediation through ANAPEC and regional governance actors. Full article

The accurate interpretation of land cover changes in multi-temporal satellite imagery is critical for Earth observation. However, existing methods typically yield static outputs—such as binary masks or fixed captions—lacking interactivity and user guidance. To address this limitation, we introduce remote sensing image change analysis (RSICA), a novel paradigm that enables the instruction-guided, multi-turn exploration of temporal differences in bi-temporal images through visual question answering. To realize RSICA, we propose DeltaVLM, a vision language model specifically designed for interactive change understanding. DeltaVLM comprises three key components: (1) a fine-tuned bi-temporal vision encoder that independently extracts semantic features from each image in the input pair; (2) a visual difference perception module with a cross-semantic relation measuring (CSRM) mechanism to interpret changes; and (3) an instruction-guided Q-former that selects query-relevant change features and aligns them with a frozen large language model to generate context-aware responses. We also present ChangeChat-105k, a large-scale instruction-following dataset containing over 105k diverse samples. Extensive experiments show that DeltaVLM achieves state-of-the-art performance in both single-turn captioning and multi-turn interactive change analysis, surpassing both general multimodal models and specialized remote sensing vision language models. Full article

Background/Objectives: Adolescence is a critical developmental period during which peer attitudes and school experiences play an important role in social inclusion and academic adjustment. Although attention-deficit/hyperactivity disorder (ADHD) is common in secondary school populations, adolescents’ own knowledge and attitudes toward ADHD remain underexplored, particularly in non-Anglophone contexts. This study aimed to assess knowledge and attitudes toward ADHD among Greek secondary school students, focusing on awareness of the disorder, perceptions of ADHD-related classroom behaviors, and views on educational support and intervention. Methods: A cross-sectional survey was conducted among 154 adolescents aged 12–18 years attending Gymnasium (Grades 7–9) and Lyceum (Grades 10–12) in Greece. Data were collected using an anonymous online questionnaire assessing prior awareness of ADHD, perceptions of classroom behaviors associated with ADHD, attitudes toward inclusion and teacher support, and views on educational and therapeutic interventions. Adolescents with and without a self-reported ADHD diagnosis completed different questionnaire sections according to study design. Descriptive statistics and chi-square tests were used for data analysis. Results: Approximately two thirds of participants (66.9%) reported prior awareness of ADHD. Among typically developing adolescents (n = 134), 83.0% recognized distractibility due to external noise, 70.4% noted off-topic interruptions, and 60.0% reported peers getting up without permission. While 75.5% believed students with ADHD can participate in the classroom, 65.9% also reported academic challenges such as incomplete homework or lower performance. Overall, 79.2% of participants stated that school success depends on teacher and specialist support; however, among adolescents with ADHD (n = 20), only 60.0% endorsed this, with 40.0% emphasizing personal effort. Speech-language therapy was viewed as helpful by 55.6% of typically developing adolescents, though 76.9% of adolescents with ADHD reported not receiving such services. Conclusions: Greek adolescents demonstrate moderate awareness of ADHD and generally supportive attitudes toward peers with ADHD, alongside some uncertainty regarding available educational supports. Schools may represent an important context for improving adolescents’ mental health literacy and understanding of ADHD-related support options. Full article

As one of the most representative cultural heritages, traditional Chinese opera is characterized by highly refined symbolic contexts and stylized narrative structures. Nevertheless, the contemporary generation often struggles with its abstract expression and language, leading to declining attendance. In addition, urbanization and digital entertainment have squeezed out its living spaces, increasing demand for more diverse experiences. To address these issues, this study conducts a systematic and thematically categorized review of the literature, exploring how extended reality (XR) reshapes the spatial and experiential representation of opera culture. Drawing upon the reality–virtuality continuum and spatial computing as theoretical foundations, the research investigates the features, workflows, and cultural adaptability of augmented reality (AR), virtual reality (VR), and mixed reality (MR), identifying how each modality of XR supports distinct modes of space generation and audience engagement. Through comparative analysis, we propose three XR-based approaches for reinterpreting Chinese opera: AR for theatrical spaces visualization, VR for performative narratives embodiment, and MR for opera cultural elements superposition. Overall, the research clarifies that XR can be used as a comprehensive medium to enhance replicability and user perception, contributing to the preservation and communication of humanity’s traditional culture. Full article

This study investigates students’ motivation and engagement when participating as pedagogical partners in co-creating assessment rubrics for English language learning. Grounded in self-determination theory, this research explores how students’ sense of autonomy, competence, and relatedness influence their motivation to engage in co-created assessment practices. Data was collected from 143 undergraduate students at a university in Dubai. Findings showed generally positive perceptions of autonomy, with many students valuing opportunities to contribute ideas to assessment design and reporting that co-creation enhanced their ownership of learning. Students also believed that co-created assessments improved their understanding of learning objectives. Students reported that co-creation clarified expectations, reduced anxiety, and allowed them to develop broader academic and soft skills. Despite these benefits, unfamiliarity with assessment design at times hindered effective participation. These findings suggest that co-created assessment can strengthen motivation by enhancing competence, autonomy, and relatedness, but it is also important for the students to have clear guidelines to support meaningful student involvement. Full article

The informational efficiency of stock prices is conditioned by the level of quality of financial reports, contributing to an accurate assessment of the company’s future performance. By approaching informational quality from two perspectives, we conducted an analysis of the impact of faithful representation and readability of annual reports on the reaction of the Romanian capital market, measured by annual stock returns (SR) and cumulative abnormal returns (CAR). The findings revealed an accentuated concern of investors regarding the faithful representation of the firm’s financial results (both at the time of financial statements’ publication and at the year-end) and a diminished significance of the comprehensibility level of financial information in the investment decision-making process. The annual reports of a sample of firms listed on the BSE between 2017 and 2023 have an increased level of linguistic complexity, which entails processing costs, and are intended for sophisticated users with financial expertise. Along with the specialized language, the extensive length of reports delays the incorporation of all information into the stock price, decreasing the informational efficiency of the market. This empirical study applies several indices to assess the readability and conciseness of financial information (FOG index, Flesch–Kincaid index, Flesch Reading Ease Score, and report length) and contributes to the expanding literature by providing a useful basis for future analysis of the influence of financial report quality on investors’ perceptions. Full article

Background: and objective: Globally, breast cancer (BC) raises global health concerns, being the most common cancer. Women with BC experience a significant increase in perception of stress. Therefore, this study aims to evaluate the stress levels and associated sociodemographic and clinical factors among BC women in Saudi Arabia. Methods: A cross-sectional study was conducted between January and May 2025. Women diagnosed with BC, who were at least 18 years old, were recruited conveniently from outpatient and inpatient departments in King Fahad Specialist Hospital, Dammam, Saudi Arabia. Data were collected in the Arabic language through self-reported questionnaires, including sociodemographic/clinical characteristics and the Cohen’s Perceived Stress Scale. The data were analyzed using the Statistical Package for the Social Sciences (SPSS) version 27. Results: A total of 200 participants were included in the study. The mean stress perception score was 26.52 ± 7.34. A high proportion (71.5%) of the sample reported elevated stress. A significant association was observed between age and stress levels. Most women aged 20–40 and 41–60 reported high stress, compared to women in the 61–80 age group (p = 0.003). Among all predictors, age was the only variable significantly associated with stress scores. Increasing age was associated with lower stress levels (B = −0.179, p = 0.013), indicating that younger participants tended to report higher stress. This corresponds to an adjusted decrease of approximately 1.8 points in the PSS-10 score per 10-year increase in age. Although participants with Stage IV cancer showed higher stress scores compared to those with Stage I cancer, this association approached but did not reach statistical significance (p = 0.054). Conclusions: This study highlights the substantial psychological burden experienced by women living with BC in Saudi Arabia. The majority of participants reported high levels of perceived stress. Younger women were particularly vulnerable to elevated stress. These findings highlight the need for targeted psychosocial support within oncology care to improve emotional well-being and quality of life. Full article

Autonomous driving (AD) systems remain vulnerable to rare, ambiguous, and out-of-label (OOL) hazards that are insufficiently represented in conventional training datasets. This work investigates perception robustness under such conditions by using the Challenge of Out-Of-Label (COOOL) benchmark dataset, which consists of 200 dashcam video sequences annotated with both common and uncommon traffic hazards. We analyze that the behavior of widely used methods in the perception of components and present a multimodal pipeline in which we integrate YOLO11x for object detection, Hough Transform for lane estimation, and GPT-4o for scene description, and for temporal modeling, we use Long Short-Term Memory (LSTM) networks. On the COOOL benchmark, YOLO11x achieves an $mAP@0.5$ of $54.1\%$ on the common object categories, whereas the detection of rare and OFL hazards remains challenging, with a recall of $72.6\%$. Incorporating temporal risk modeling improves hazard recall to $71.8\%$, indicating a modest but consistent gain in recognizing uncommon events. Hough Transform shows the stable behavior in standard conditions for lane estimation, with a mean lateral deviation of $8.9$ pixels in daylight scenes and $13.4$ pixels under low-light conditions. The temporal anomaly detection module attains an AUROC of $0.65$, reflecting the limitation but meaningful discrimination between nominal and anomalous driving situations. For interpretability, the GPT-4o scene description module generates context-aware textual explanations with an object coverage score of $0.72$ and a factual consistency rate of $78\%$, as assessed through manual inspection. The end-to-end pipeline operates at approximately 10–12 frames per second on a single GPU, supporting near-real-time analysis and optimization. Our results confirm that state-of-the-art perception models struggle with OOL hazards and that multimodal vision–language–temporal integration provides incremental improvements in robustness and interpretability when evaluated under the standardized out-of-distribution conditions. Full article