Search Results (154)

Millimeter-wave (mmWave) radar point clouds offer a privacy-preserving solution for Human Activity Recognition (HAR), but their inherent sparsity and noise limit single-modal performance. While multimodal fusion mitigates this issue, existing methods often suffer from severe negative transfer during visual degradation and incur high computational costs, unsuitable for edge devices. To address these challenges, we propose Tac-Mamba, a lightweight cross-modal state space model. First, we introduce a topology-guided distillation scheme that uses a Spatial Mamba teacher to extract structural priors from visual skeletons. These priors are then explicitly distilled into a Point Transformer v3 (PTv3) radar student with a modality dropout strategy. We also developed a Trust-Aware Cross-Modal Attention (TACMA) module to prevent negative transfer. It evaluates the reliability of visual features through a SiLU-activated cross-modal bilinear interaction, smoothly degrading to a pure radar-driven fallback projection when visual inputs are corrupted. Finally, a Lightweight Temporal Mamba Block (LTMB) with a Zero-Parameter Cross-Gating (ZPCG) mechanism captures long-range kinematic dependencies with linear complexity. Experiments on the public MM-Fi dataset under strict cross-environment protocols demonstrate that Tac-Mamba achieves competitive accuracies of 95.37% (multimodal) and 87.54% (radar-only) with only 0.86M parameters and 1.89 ms inference latency. These results highlight the model’s exceptional robustness to modality missingness and its feasibility for edge deployment. Full article

The increasing integration of artificial intelligence (AI) in educational decision-making raises a critical question: how to design AI systems that can effectively support teachers while maintaining an appropriate level of trust. Addressing this question requires not only continuous improvements in the technical capabilities of AI systems but also an examination from a human-AI interaction perspective of how different system designs influence users’ cognitive performance and affective responses, thereby providing guidance for system optimization and design. Therefore, this study conducted a randomized controlled experiment with 120 pre-service teachers to investigate how AI-assisted decision-making paradigms and AI explainability jointly influence teachers’ task performance and trust in AI, and whether these effects transfer to subsequent independent tasks. The results indicate that the effect of explanatory interface on task performance is context dependent and yields an immediate positive impact. Under the concurrent paradigm, the explanatory interface of the AI system significantly improves immediate task performance, whereas no significant effect is observed under the sequential paradigm. Moreover, this improvement is confined to the task execution stage and does not transfer to subsequent independent tasks. In contrast, the effect of explanatory interface on trust exhibits a delayed and negative pattern. The explanatory interface has no significant impact on situational trust, while it exerts a negative effect on learned trust and suppresses the natural development of both cognitive trust and emotional trust. In addition, different AI-assisted decision-making paradigms exhibit distinct patterns of influence on task performance and trust. Although the concurrent paradigm performs worse than the sequential paradigm in terms of immediate task performance, it is more effective in promoting users’ emotional trust. Overall, these findings extend the theoretical understanding of the mechanisms of explainability in human-AI interaction and provide empirical evidence for the joint design of explainable AI systems and human-AI collaboration paradigms. Full article

With advances in artificial intelligence and computer vision, pose recognition-based feedback systems are increasingly being introduced into dance classes to support movement understanding and error correction. However, how learners interpret and adopt such feedback during actual classroom use, and how this process shapes their intention to continue using the system, remains insufficiently understood. This study develops and validates a three-layer “System–Psychological–Experience” model, with learning experience positioned as the key mechanism linking antecedent factors to usage intention. A sequential mixed-methods design was employed. In Phase 1, interviews were conducted with 20 dance majors to identify factors relevant to classroom integration. In Phase 2, structural equation modeling was performed using 398 valid survey responses. In Phase 3, explanatory interviews with five students and five teachers were conducted to further interpret the underlying mechanisms. The results showed that learning experience was the strongest direct predictor of usage intention (β = 0.409, p < 0.001). At the system layer, perceived usefulness and perceived ease of use contributed to usage intention mainly by strengthening learning experience. At the psychological layer, system trust and perceived value showed the same indirect pattern through learning experience. Teaching context also played an important role. Teaching compatibility directly enhanced learning experience, while teacher influence both strengthened learning experience and indirectly contributed to usage intention by increasing system trust and perceived value. Overall, the findings suggest that learners’ intention to continue using pose recognition-based feedback systems is closely associated with their overall learning experience in teacher-mediated classroom practice, and the study offers implications for classroom-oriented design. Full article

Generative AI is reshaping university teaching and creating tension around authority, evidence, and accountability when decisions are made using algorithms. From a student perspective, this study constructed a typology of distributed teacher–AI agency (TAI) and examined the discursive mechanisms that produce the illusion of teacher autonomy. A non-experimental, cross-sectional, explanatory study was conducted: a lexicometric analysis of the ALCESTE (IRAMUTEQ) questionnaire, using open-ended responses from 3120 students (Mexico, n = 2051; Ecuador, n = 1069), segmented into 1077 units, and analyzed using positioning theory. Co-agency was operationalized using Teacher Agency (A), Delegation to AI (D), Governance (G: disclosure, criteria, verification), and the Illusion Index (II = A/(D + G + 1)). Three configurations emerged: Immediate Customizer (28.8%) with very high A and minimal D/G (II = 25.4); Technological Literacy Facilitator (27.3%) with visible delegation and safeguards (II ≈ 2.0); and Operational Optimizer (43.9%) oriented toward accelerating tasks with moderate governance (II ≈ 2.7). The illusion was associated with the agentive erasure of AI and a rhetoric of immediacy/efficiency that replaced verifiable criteria. These findings transform the student voice into a criteria-based diagnostic tool for strengthening traceability, minimal verification, and responsible orchestration of AI in higher education. Full article

The proliferation of fake reviews on e-commerce and social platforms has severely undermined consumer trust and market integrity, necessitating robust and interpretable real-time detection mechanisms with multi-sensor data fusion capabilities. While traditional machine learning approaches have shown promise in identifying fraudulent reviews, they often lack transparency and fail to leverage the rich contextual knowledge embedded in large-scale datasets. In this paper, we propose KE-MLLM (Knowledge-Enhanced Multimodal Large Language Model), a unified framework that integrates knowledge-enhanced prompting with parameter-efficient fine-tuning for explainable fake review detection. Our approach employs LoRA (Low-Rank Adaptation) to fine-tune lightweight large language models (LLaMA-3-8B) on review text, while incorporating multimodal behavioral sensor signals including temporal patterns, user metadata, and social network characteristics for comprehensive anomaly sensing. To address the critical need for interpretability in fraud detection systems, we implement a Chain-of-Thought (CoT) reasoning module that generates human-understandable explanations for classification decisions, highlighting linguistic anomalies, sentiment inconsistencies, and behavioral red flags. We enhance the model’s discriminative capability through a knowledge distillation strategy that transfers domain-specific expertise from larger teacher models while maintaining computational efficiency suitable for edge sensing devices. Extensive experiments on two benchmark datasets—YelpChi and Amazon Reviews from the DGL Fraud Dataset—show that KE-MLLM achieves strong performance, reaching an F1-score of 94.3% and an AUC-ROC of 96.7% on YelpChi and outperforming the strongest baseline in our comparison by 5.8 and 4.2 percentage points, respectively. Furthermore, human evaluation indicates that the generated explanations achieve 89.5% consistency with expert annotations, suggesting that the framework can improve the interpretability and practical usefulness of automated fraud detection systems. The proposed framework provides a useful step toward more accurate and interpretable fake review detection and offers a practical reference for building more transparent and accountable AI systems in high-stakes applications. Full article

Behaviour management represents a complex dimension of the teaching profession, especially in contexts of high social vulnerability. This instrumental case study qualitatively analysed the experiences of four teachers from a technical–professional high school in Santiago, Chile, focusing on how they construct and sustain behaviour management in everyday classroom work. Data were generated through semi-structured interviews and analysed using qualitative content analysis. Findings foreground a central tension in which reactive management predominates over preventive strategies, shaping how teachers sustain pedagogical continuity under recurrent disruption. Teachers describe this work as a reflective construction negotiated between routines and adaptation to contingencies, supported by bonds of trust with students and informal peer collaboration within an institutional structure perceived as fragmented. These insights can inform teacher education by strengthening practice-oriented preparation for behaviour management and can support the refinement of educational coexistence policies in context-sensitive ways. Full article

Generative artificial intelligence (GenAI) has rapidly emerged as a transformative educational technology, raising questions about how educators and pre-service teachers critically engage with AI-produced content. This case study investigates how WebQuests, a long-established, inquiry-based pedagogical model, can foster critical engagement with GenAI tools. Situated within an initial teacher education programme, a WebQuest, incorporating GenAI sources, was implemented with 24 pre-service language teachers, who engaged with curated resources alongside ChatGPT and Copilot to produce infographics for secondary school audiences. Data were collected through semi-structured interviews and were analysed using Braun and Clarke’s thematic analysis. Findings indicate that scaffolded engagement with GenAI encouraged participants to compare AI-generated outputs with trusted sources, critically evaluate accuracy and reliability, and reflect on integration into their future practice. Whilst pre-service teachers valued GenAI’s accessibility and efficiency, they expressed concerns about clarity, verbosity, and trustworthiness. The WebQuest model effectively supported synthesis of multiple information sources, fostering functional AI engagement and critical evaluation of its affordances and limitations. This case study concludes that integrating GenAI within structured, inquiry-based pedagogies advances digital and AI literacy in initial teacher education, whilst highlighting the need for institutional guidance, professional development, and further research in this area. Full article

Generative Artificial Intelligence (GenAI) has the potential to bring substantial benefits to language education, making it essential to examine how teachers engage with these technologies in practice. This exploratory qualitative case study draws on semi-structured interviews with four in-service upper-secondary English teachers in Norway to examine the factors shaping their engagement with GenAI. Drawing on the Unified Theory of Acceptance and Use of Technology (UTAUT), the study examined factors shaping teachers’ engagement with GenAI, including performance expectancy, effort expectancy, social influence, and facilitating conditions. Thematic analysis revealed a pattern of selective, context-sensitive use rather than straightforward adoption. While teachers recognised the potential of GenAI to support planning, idea generation, and formative feedback, their engagement was constrained by concerns about assessment validity, academic integrity, privacy, and institutional guidance. The findings suggest that teachers’ use of GenAI is shaped not only by perceptions of usefulness and ease of use but also by trust, assessment considerations, and the availability of clear policy frameworks. By using UTAUT as a qualitative analytical lens, this study contributes to research on technology acceptance and teacher agency by showing how teachers negotiate the use of GenAI in ways that reshape assessment practices and professional roles. The findings point to the need for clear institutional guidance, AI-resilient assessment practices, and targeted teacher education that supports ethical, pedagogically grounded use of GenAI. Full article

Artificial intelligence (AI), particularly generative AI, is rapidly reshaping medical education worldwide. While AI-enabled tools offer significant opportunities for personalized learning, feedback automation, and clinical reasoning support, they simultaneously challenge foundational principles of assessment integrity and professional conduct. Traditional assessment models—largely predicated on individual authorship, knowledge recall, and observable performance—are increasingly strained by AI systems capable of generating sophisticated responses, analyses, and clinical narratives. This disruption has prompted urgent reconsideration of what constitutes academic honesty, valid assessment, and professional identity formation in contemporary medical training. This article critically examines the intersection of AI, assessment integrity, and professionalism in medical education from a global perspective, with particular attention to the experiences and emerging lessons from the Gulf Cooperation Council (GCC). The GCC provides a distinctive context characterized by rapid digital transformation, centralized accreditation and licensing systems, high-stakes assessments, and strong sociocultural norms governing professional behavior. These features make the region an instructive case for understanding how medical education systems respond to AI-driven challenges at scale. The article employs a critical narrative and conceptual framework, positioning generative AI as a normative disruptor that necessitates a reevaluation of assessment validity, ethical accountability, and the construction of professional identity. Utilizing worldwide scholarship, policy frameworks, and regional experiences, the analysis underscores that misalignment between assessment design and professional expectations jeopardizes trust, fairness, and public confidence. The essay advocates for a transition from reactive restriction to the principled integration of AI, highlighting the need for assessment redesign, AI literacy matched with professionalism, teacher development, and cohesive governance. These insights are intended to guide educators, institutions, and regulators in maintaining professional standards inside AI-enhanced medical education systems. Full article

Against the backdrop of China’s national initiatives to strengthen the teaching workforce, fostering teachers’ work passion is essential not only for enhancing professional well-being but also for improving educational quality. This study examines how kindergarten principals’ caring leadership influences teachers’ work passion by testing the sequential mediating roles of teacher trust and teacher buoyancy. Using an independent quota sampling strategy, survey data were collected from 395 kindergarten teachers across China. The results indicate that principals’ caring leadership positively influences teachers’ work passion, but this effect is entirely indirect, operating through teacher trust, teacher buoyancy, and their sequential mediation, thereby confirming the “second-order effect” mechanism of leadership. Further mediation analyses reveal that the independent mediating effect of teacher trust (72.47%) is substantially stronger than that of teacher buoyancy (15.15%), while the sequential mediation pathway from teacher trust to teacher buoyancy accounts for 11.73% of the total effect. Overall, this study advances understanding of psychological mechanisms linking caring leadership to teachers’ passion and offers actionable insights for kindergarten principals seeking to refine leadership practices and foster sustained teacher engagement and enthusiasm. Full article

As artificial intelligence (AI) is increasingly used in classrooms, tutoring systems, and learning platforms, it is essential that these tools are not only powerful, but also easy to understand, fair, and supportive of real learning. Many current AI systems can generate fluent responses or accurate predictions, yet they often fail to clearly explain their decisions, reflect students’ cultural contexts, or give learners and educators meaningful control. This gap can reduce trust and limit the educational value of AI-supported learning. This paper introduces the PEARL framework, a human-centered approach for designing and evaluating explainable AI in education. PEARL is built around five core principles: Pedagogical Personalization (adapting support to learners’ levels and curriculum goals), Explainability and Engagement (providing clear, motivating explanations in everyday language), Attribution and Accountability (making AI decisions traceable and justifiable), Representation and Reflection (supporting fairness, diversity, and learner self-reflection), and Localized Learner Agency (giving learners control over how AI explains and supports them). Unlike many existing explainability approaches that focus mainly on technical performance, PEARL emphasizes how students, teachers, and administrators experience and make sense of AI decisions. The framework is demonstrated through simulated examples using an AI-based tutoring system, showing how PEARL can improve feedback clarity, support different stakeholder needs, reduce bias, and promote culturally relevant learning. The paper also introduces the PEARL Composite Score, a practical evaluation tool that helps assess how well educational AI systems align with ethical, pedagogical, and human-centered principles. This study includes a small exploratory mixed-methods user study (N = 17) evaluating example AI tutor interactions; no live classroom deployment was conducted. Together, these contributions offer a practical roadmap for building educational AI systems that are not only effective, but also trustworthy, inclusive, and genuinely supportive of human learning. Full article

This article reports on a comparative case study that examined the ground rules used to facilitate a dialogic space in two discrete and diverse research studies: Year 5 & 6 children learning to code with ScratchMaths as part of their mathematics programmes, and crop farmers in rural east Africa developing their practice through various communications. The intention was to see if there were common actions or principles important for the establishment of ground rules in dialogic spaces in general. Understanding the nature of dialogic space has become increasingly important in many areas of education. STEM subjects, particularly when integrated, frequently involve collaborative interaction, and utilise a dialogical approach. Some initial aspects of ground rules were collaboratively identified, with both studies then independently analysed to identify emerging themes related to these ground rules. Several key elements emerged: developing the processes for interaction and communication; developing trust between participants; developing respectful dialogue; teacher roles; and facilitating collaborative work and the co-construction of meaning. The comparative case study suggested that these were important for other education work when establishing dialogic space. Full article

This study examines how Artificial Intelligence (AI) is reshaping the role of university teachers and transforming the foundations of academic work in the digital age. Building on the Dynamic Capabilities Theory (sensing–seizing–transforming), the article proposes a theoretical reframing of university teachers’ perceptions of AI. This approach allows us to bridge micro-level emotions with meso-level HR policies and macro-level sustainability goals (SDGs 4, 8, and 9). The empirical foundation includes a survey of 453 Ukrainian university teachers (2023–2025) and statistics, supplemented by a bibliometric analysis of 26,425 Scopus-indexed documents. The results indicate that teachers do not anticipate a large-scale replacement by AI within the next five years. However, their fear of losing control over AI technologies is stronger than the fear of job displacement. This divergence, interpreted through the lens of dynamic capabilities, reveals weak sensing signals regarding professional replacement but stronger signals requiring managerial seizing and institutional transformation. The bibliometric analysis further demonstrates a theoretical evolution of the university teacher’s role: from a technological adopter (2021–2022) to a mediator of ethics and integrity (2023–2024), and, finally, to a designer and architect of AI-enhanced learning environments (2025). The study contributes to theory by extending the application of Dynamic Capabilities Theory to higher education governance and by demonstrating that teachers’ perceptions of AI serve as indicators of institutional resilience. Based on Dynamic Capabilities Theory, the managerial recommendations are divided into three levels: government, institutional, and scientific-didactic (academic). Full article

Digital inclusion has become an essential component in ensuring the autonomy, social participation, and well-being of older adults. However, their learning of digital skills depends to a large extent on the quality of support provided by the facilitator, whose age, training, and experience directly influence teaching processes and how older adults relate to technology. This study compares the digital competences, and ICT skills of 107 facilitators of digital literacy programs, classified into three groups: peer educators (PEERS), young students without gerontological training (YOS), and young gerontology specialists (YGS). A quantitative design was used. Statistical analyses included non-parametric tests (Kruskal–Wallis, Mann–Whitney, Kendall’s Tau) and parametric tests (ANOVA, t-tests), to examine associations between socio-demographic variables, the level of digital competence, and ICT skills for teachers (technological and pedagogical). The results show clear differences between profiles. YOS achieved the highest scores in digital competence, especially in problem-solving and tool handling. The YGS achieved a balanced profile, combining competent levels of digital skills with pedagogical strengths linked to their gerontological training. In contrast, PEERS recorded the lowest levels of digital competence, particularly in security and information management; nevertheless, their role remains relevant for fostering trust and closeness in training processes among people of the same age. It was also found that educational level is positively associated with digital competence in all three profiles, while age showed a negative relationship only among PEERS. The findings highlight the importance of creating targeted training courses focusing on digital, technological, and pedagogical skills to ensure effective, tailored teaching methods for older adults. Full article

This study aimed to develop and validate a self-report instrument—the Perceived Teacher Trust Behavior Scale (PTTBS)—to assess primary school students’ perceptions of trust-related behaviors exhibited by their teachers. Adopting a child-centered perspective within the school context, we first conducted in-depth interviews and applied a grounded theory approach to identify dimensions and generate initial items. A cluster sampling method was used to recruit 1400 students (Grades 3~5) from three schools in Guizhou Province, China, who completed the questionnaire. The collected data were analyzed via exploratory factor analysis and confirmatory factor analysis using SPSS 30.0 and Mplus8.10 software. The final version of the PTTBS consists of 13 items across four dimensions: Emotional Support, Competence Recognition, Academic Support, and Moral Recognition. The scale demonstrated excellent internal consistency (Cronbach’s α = 0.90) and split-half reliability (Spearman–Brown coefficient = 0.847). Significant correlations with an established Student-Teacher Relationship Scale were observed, along with good convergent validity (0.502~0.629) and construct validity. The PTTBS exhibits robust psychometric properties and serves as a valid tool for measuring Chinese primary school students’ perceptions of teacher trust behaviors, suitable for both research and practical applications. Full article