This study examines the gap between digitalization agendas and school realities, where connectivity constraints, limited devices, and uneven support restrict pedagogical innovation. It evaluates the Model for Integrative and Predictive Smart Teaching Adaptation, integrating artificial intelligence, learning analytics, and Internet of Things components, within a holopraxic cycle of diagnosis, design, implementation, evaluation, and readaptation driven by field feedback. Over a semester, 120 rural teachers participated in a quasi-experimental study combining a competence questionnaire, interviews, and system usage logs. Baseline competence was comparable between groups, and gain was defined on a zero to one hundred scale as post minus pre. The experimental group showed a median gain of 6.25 points, whereas the control group remained at 0.00; the common-language effect size was 0.765. Engagement was sustained with peaks (twenty-five to thirty-seven sessions per week), indicating selective appropriation rather than linear growth. Results support improvement and emphasize adoption conditions: teacher agency, ethical trust, and institutional sustainability, operationalized through pseudonymization and bias auditing.
This study utilizes the Digital Competence Framework for Educators (DigCompEdu) and machine learning (ML) techniques to evaluate and predict the ICT proficiency levels of public school teachers in Bukidnon. Analyzing a dataset of 1,275 responses and addressing data imbalances, several classification models were evaluated to identify the most reliable predictor of teacher competence. The findings indicate that the majority of teachers currently operate at the 'Integrator' (B1) level. Key predictors of proficiency include skills in online safety, collaborative learning, and the creative use of digital tools. Among the tested algorithms, Random Forest emerged as the most effective model for accurately classifying teacher skill levels. This research provides a data-driven roadmap for educational policymakers, offering actionable insights for designing targeted professional development programs that foster transformative teaching and improved student outcomes.
Student engagement is a crucial aspect of higher education learning. However, it may be challenging to ensure active engagement, especially if students lack motivation to participate. This research proposes an innovative technique for increasing student participation in online sessions that incorporates real-time chat interaction, engagement reminders, and attendance tracking. Unlike traditional research, which focuses on post-session analysis, the developed Bot actively monitors student participation during session itself, providing real-time notifications to disengaged students without requiring the need for human intervention. It records attendance for each session, monitors weekly student participation, and dispatches updates via email to both instructors and students. To provide a more interesting and responsible learning environment, the Bot also utilizes AI to evaluate student responses and provide suggestions for their improvement.
The rapid maturation of large language models has opened new opportunities for capable of enhancing learning outcomes, enriching instructional practice, and supporting large-scale computing education with high reliability through personalized, scalable, and data-driven instructional support. The ChatGPT Learning Companion (ChatGPT-LC) introduces a multimodal framework that integrates conversational scaffolding, code reasoning, misconception diagnostics, and learner analytics into a unified system capable of adapting instruction in real time. Deployed across 260 undergraduate learners in three programming courses, ChatGPT-LC produced substantial performance gains, including a 35.20% increase in concept mastery, 27.90% improvement in debugging accuracy, and error-type reductions ranging from 53.60% to 65.50%. Behavioral analytics revealed strong correlations between engagement intensity and performance (up to r = 0.740), with reflective and exploratory learners achieving scores above 88–90%. Instructor workload decreased by more than 32 hours per week, supported by high expert-verified accuracy (92–96%) of AI-generated feedback. System-level benchmarks demonstrated robust scalability, maintaining 97.00% success rates at 500 concurrent users and reducing latency from 450 ms to under 100 ms after optimization. Collectively, these results show that ChatGPT-LC functions not only as an automated tutor but as an adaptive cognitive partner capable of enhancing learning outcomes, enriching instructional practice, and supporting large-scale computing education with high reliability and pedagogical fidelity.
This article primarily aims to introduce high school students to the mystery of Lobachevsky geometry, one of the cornerstones of non-Euclidean geometries. Lobachevsky geometry, often known as hyperbolic geometry, differs from Euclidean geometry in several basic ways. The concepts and figures of Lobachevsky geometry can appear in different plane models, such as the Klein and Poincaré disk models. It further examines students' general attitudes and behaviors toward non-Euclidean geometries. Lobachevsky's geometry has helped expand students' horizons and enriched their critical thinking skills by challenging traditional Euclidean paradigms. This study is supported by a mixed-method approach utilizing quantitative and qualitative data. The mock exam results obtained from students during the educational process were compared, and the study was further supported by the positive feedback received from the participating students. The intriguing lessons on Lobachevsky geometry were conducted over 4 weeks, with weekly 2-hour geometry classes involving 12th-grade students at Stirling Schools in Erbil. Throughout the study, we observed significant improvements in students' ability to adopt, understand, and apply advanced geometric concepts. This article also discusses findings and implications that address gaps in the literature and considers the potential for curriculum updates to enhance the future of geometry education.
An accurate and comprehensive assessment of student engagement in classrooms is crucial for enabling data-driven teaching and personalized education. Current approaches primarily rely on teacher observation or student self-reports, which are often subjective, delayed, and unable to capture cognitive engagement. To address these limitations, this study proposes a Multimodal Cognitive-Attention Fusion (MCA Fusion) framework, grounded in Fredricks’ three-dimensional engagement model. The framework integrates electroencephalography (EEG), facial expressions, and body posture to simultaneously quantify cognitive, emotional, and behavioral engagement. Built on a Transformer architecture, it employs self-attention to extract temporal features within each modality and introduces a cognition-guided cross-attention mechanism to dynamically integrate multimodal signals. To validate the framework, experiments were conducted with 36 undergraduate students in real classroom settings. The results demonstrate that our framework significantly outperforms all single-modality baselines, achieving an accuracy of 92% and an F1-score of 94.87%. Compared with the best single-modality model (EEG), the F1-score improves by 34.58 percentage points. Ablation studies further confirm the critical role of the cognitive modality (EEG) and the MCA Fusion mechanism, the removal of which leads to F1-score reductions of 62.58 and 56.16 percentage points, respectively. The proposed approach not only provides a theoretically informed and technically evaluated framework for engagement recognition but also provides a methodological foundation for future closed-loop “perception–assessment–feedback” systems in intelligent learning environments.
This study proposes and empirically evaluates a pedagogical framework for ethical skill development in higher education within smart learning environments. The framework conceptualizes ethical competence as a multidimensional, process-oriented construct cultivated through authentic ethical scenarios, structured reflective cycles, adaptive learning support, and competence-aligned assessment. A quasi-experimental design was implemented with 90 undergraduate participants assigned to three groups: Group A (n = 30) learned using the framework with teacher guidance, Group B (n = 30) learned using the framework without teacher involvement, and Group C (n = 30) learned under traditional instruction without the framework. Ethical competence was measured via pre-test and post-test questionnaires capturing overall ethical skills and specific dimensions including ethical awareness, moral reasoning, reflective capacity, and ethical responsibility. Statistical analyses combined gain-score comparisons and covariate-adjusted models. Results indicate that the framework-based condition (Groups A+B) achieved significantly higher overall ethical skill development than the traditional condition, supported by large practical effects. Multivariate analysis further revealed significant framework-related advantages on the combined outcomes of ethical awareness and moral reasoning, with stronger effects observed for ethical awareness. Ethical responsibility also increased substantially under the framework relative to traditional instruction. Teacher guidance demonstrated a differentiated contribution: no significant difference emerged between Groups A and B in overall ethical skill development, whereas teacher-mediated scaffolding produced a significant and large improvement in reflective capacity compared to autonomous framework-based learning. These findings suggest that smart learning environments can support scalable ethical competence formation when pedagogical design integrates adaptive ethical tasks and structured reflection, while targeted instructor scaffolding remains important for deep reflective development. The study contributes actionable guidance for embedding ethics into smart education curricula and motivates future longitudinal and multi-institutional research using behavioral measures and discipline-specific adaptations.
Curriculum mapping for AUN-QA is often time-consuming and prone to inconsistency because learning-outcome evidence is scattered across multiple courses and program documents. This study examines the reliability of large language models in supporting course learning outcome–program learning outcome (CLO–PLO) alignment decisions for AUN-QA–aligned curriculum mapping. Using Mechatronics Engineering curriculum materials (2022–2024), AUN-QA v4.0 indicators were operationalized into a structured evidence schema to guide prompting and interpretation. GPT-4 produced 120 CLO–PLO alignment decisions, which were independently annotated by two domain experts and adjudicated by a third expert to establish reference labels. Model–reference agreement was evaluated using precision, recall, F1-score, and Cohen’s kappa (κ), yielding 0.89, 0.85, 0.87, and 0.81, respectively. We also developed a dashboard that summarizes alignment coverage and supports PDCA-based curriculum improvement by flagging potential gaps and redundancies. The findings suggest that LLM-assisted alignment can reduce mapping workload and improve auditability while remaining consistent with expert judgment, enabling more scalable evidence-based AUN-QA evaluation.
Students attending school experience stress due to a variety of factors that can originate either on campus or from home. In managing stress and other related issues, educational institutions now have counselling units that operate as centres. Moreover, several institutions have designated academic counsellors in departments to address the increasing demand for counselling services due to an expanding student population. Timely detection and proactive counselling of stress among students can help avert dropouts, health issues, and other learner behaviours that are detrimental to academic work. This study proposes two approaches to facilitate the automation of student counselling for stress management. We first implemented the K-means algorithm and formed clusters using the elbow and the Silhouette methods. The clusters formed reveal three groups of students. The stressors significantly affected one group, making it vulnerable. The stressors moderately impacted another group, while the final group experiences minimal stress. In the second part of the study, we proposed a classification model to identify the cluster group of any new student. The results of the classification show superior performance for the Decision Tree algorithm with an accuracy of 97.64%. The improvement in the efficiency of the classification algorithms was attained through feature engineering using the Chi-square method.
The widespread distribution of fake news poses a critical societal challenge by influencing public opinion and shaping political discourse. Addressing this problem requires models that can capture multimodal cues beyond text alone. This work proposes a lightweight Multimodal Cross-attention Fusion–based Fake News Detection (MCAF-FND) model which combines textual and visual features through cross-attention strategy. The study evaluates MCAF-FND on the Fakeddit benchmark, a large-scale dataset comprising 682,996 multimodal samples collected from social media. Textual features are extracted using DistilBERT, while spatially aware image representations are derived from VGG-19 convolutional layers. The cross-attention module enables semantic alignment between text tokens and image patches, modeling inter-modal dependencies more effectively than conventional fusion strategies. The fused representation is classified using a Multilayer Perceptron(MLP) with softmax, ensuring contributions from both modalities. Experimental results demonstrate that MCAF-FND consistently outperforms unimodal baselines and traditional fusion methods, achieving 93.2% accuracy with strong precision, recall, and F1-score. Cross-attention based visualizations illustrate how the model aligns textual cues with salient visual regions, enhancing interpretability. By combining computational efficiency with robust multimodal reasoning, the proposed approach provides a reliable and extensible solution for automated fake news detection.
The purpose of the study was to develop a mechanism for training physical education and sports professionals. The methodology included an analysis of the use of innovative methods such as module-rating training implemented at the Kazakh Academy of Sport and Tourism, programmes for the development of digital competencies of coaches through the Open Sport Academy platform, and dual programmes such as the cooperation of the Vasyl Levsky National Sports Academy with Bulgarian sports federations through the Dual Education for Sports Professionals programme. The study found that the training of physical education and sports professionals should be closely linked to labour market requirements, in particular through the integration of modern technologies and increased practical training. The study of the labour market in countries such as Kazakhstan and Bulgaria showed that successful educational programmes should take into account not only theoretical aspects, but also the opportunity for students to gain real-world experience in sports clubs, federations and other organisations. In addition, it has been found that the introduction of dual educational programmes that combine university studies and practical workplace activities has a significant impact on the competitiveness of graduates. An important aspect is also the use of digital technologies, such as online learning platforms and virtual simulators, which allow students to acquire the necessary skills to work in the context of the digital transformation of the sports industry. The practical significance of the study lies in the fact that the findings can serve as a basis for improving curricula and enhancing cooperation between educational institutions and employers in the field of physical education and sports.
This paper proposes the hybrid framework of privacy preserving that combines the concept of federated learning and homomorphic encryption with differential privacy, to address the privacy issue of collaborative machine learning for healthcare application. The proposed approach makes three contributions: (1) multi-layered architecture using federated learning in combination homomorphic encryption (based on CKKS scheme) and differential privacy that offers defense against inference attacks at different layers, (2) the implementation which alleviates the computational overhead compared to homomorphic encryption only with optimised cryptographic parameters, and (3) the application of the Grasshopper-Black Hole Optimization (G-BHO) for the optimisation of privacy parameters (e, deltas, gradient clipping thresholds) in order to balance the privacy-utility trade-off. Cryptographic keys are produced using the principles of cryptographically secure random number generation. Experimental evaluation on two healthcare data sets (MIMIC-III and chest X rays of the patients of Covid-19) to compare the hybrid approach to the single technique baselines in four metrics: classification accuracy (93.0±1.2% vs. 89.0±1.5% for federated learning only), differential privacy guarantee ( , ), computational overhead (2.5x baseline vs. 8x for homomorphic encryption only) and the resistance to membership inference attacks (92% vs. 68%) The observed improvement in the accuracy is unexpected, and potentially a consequence of side-effects due to the effects of the regularization in the differential privacy noise; this finding needs to be further explored in theory. The evaluation is restricted to the tasks of healthcare classification, while generalization to other domains needs more validation. The main contribution is an empirical proof that by using a combination of several privacy mechanisms, it will be possible to achieve a stronger attack resistance with a lower computational overhead than by using homomorphic encryption alone.
The implementation of Blended Learning (BL) in teacher training, which demands learners to have high autonomy and complete tasks independently in an online environment, has established self-directed learning (SDL) a prerequisite for success. However, traditional SDL scales primarily focus on psychological attributes in face-to-face settings, often failing to capture the unique self-regulatory and technological dimensions required in a BL environment. While online readiness scales exist, they frequently treat SDL as a single dimension rather than a multidimensional competency essential for pre-service teachers. To address this gap, the study developed and validated a new SDL scale, specifically tailored to pre-service teachers in a BL context. Based on established theoretical frameworks (e.g. SDLI, AMS, and PRO), the study conducted a pilot survey (N=183) and a main survey (N=1,041) with pre-service teachers. The scale was validated through Cronbach’s Alpha, EFA (using SPSS), and a PLS-SEM model to ensure reliability, convergent validity, and discriminant validity. The results established an SDL scale consisting of 7 core factors, suitable for BL context. Furthermore, the model identified 4 key factors, explaining 67.4% of the variance in SDL. These factors include: Awareness (Student awareness), Community (Community interaction), Tech (Technology competence), and Year (School year). Notably, demographic variables such as Gender and Major were determined to have no statistically significant effect on SDL. These findings provide a valid assessment tool and a robust explanatory model, allowing educators and administrators to design effective pedagogical interventions, focusing on factors that can directly impact and improve core SDL competencies for the next generation of teachers.
The efficient allocation of finite resources to a dynamic patron base represents a core challenge in modern library management. Traditional heuristic approaches often lack the formal rigor needed for verifiable optimization and proactive planning. This paper introduces a novel formal framework grounded in automata theory to model library operations, patron behavior, and resource allocation strategies. We define a Library Resource Automaton (LRA), a deterministic finite automaton whose states represent distinct configurations of resource availability, whose input alphabet encapsulates patron interactions, and whose transition function formally encodes allocation policies. By interpreting sequences of patron actions as strings in a formal language, the LRA provides a computationally tractable and analytically powerful model for simulating library states, predicting bottlenecks, and synthesizing optimal allocation strategies. We elaborate on the theoretical foundations of the model, present a detailed multi-layer automata architecture for handling complex, multi-resource scenarios, and discuss algorithms for state space analysis and policy optimization. Furthermore, we explore the integration of temporal logic for specifying and verifying critical system properties such as fairness and liveness. This work establishes a rigorous bridge between theoretical computer science and library information science, offering a new paradigm for building predictable, efficient, and patron-centric library management systems.
In the context of increasing cyber threats, digital misinformation, and online ethical dilemmas, the role of teachers in promoting safe and responsible digital behavior has become more critical than ever. This study explores the effectiveness of the Cyber Safety and Security Literacy Program (CSLP) in enhancing cyber security competency and cyber socialization among prospective teachers. The CSLP was designed as a structured educational intervention aimed at equipping future educators with the knowledge, skills, and ethical orientation necessary to navigate cyberspace confidently and responsibly. A pre-experimental one-group pre-test and post-test design was adopted, involving 50 purposively selected B.Ed. students from various teacher education institutions. The two-month intervention was delivered through Google Classroom and Google Meet, ensuring flexibility and interactive participation. The CSLP comprised 12 carefully curated modules covering critical themes such as cyber threats, digital identity protection, cyber bullying prevention, cyber ethics, safe communication, and responsible social media use. To evaluate the program‘s impact, data were collected using two standardized tools—the Cyber Security Competency Scale (CSC) and the Cyber Socialization Scale (CSS) both were developed through systematic procedures and supported by strong theoretical grounding and expert validation, providing evidence of their validity. Statistical analysis using paired-sample t-tests revealed significant improvements in participants' cyber security competency (t(49) = 30.55, p < .01, d = 4.32) and cyber socialization (t(49) = 17.75, p < .01, d = 2.51), indicating a large effect size in both domains. The findings affirm that the CSLP is an effective intervention for fostering digital responsibility, ethical awareness, and safe online behavior among future educators. The study emphasizes the urgent need to integrate comprehensive cyber security literacy programs within teacher education curricula, positioning teachers not only as informed digital citizens but also as proactive facilitators of cyber safety and ethical conduct in the learning environment.
As Large Language Models (LLMs) become increasingly embedded in intelligent tutoring systems (ITSs), a growing need exists to understand how learners engage with these tools, especially in cognitively demanding domains such as computer programming. While prior research has focused mainly on LLM-generated scaffolding, less attention has been paid to student-side engagement, including how learners think, respond, and regulate their learning during natural language tutoring sessions. This study addresses that gap by identifying learner engagement state profiles based on behavioral and metacognitive patterns in student dialogue. Drawing on data from 36 recorded LLM-mediated C introductory programming tutorials, 1,046 dual-annotated student utterances were analyzed using K-means clustering. The analysis revealed three distinct learner engagement state profiles: Passive Reactors, Clarification Seekers, and Reflective Performers. These engagement states differed in response accuracy, metacognitive expression, and interaction style. Passive Reactors showed low initiative and limited self-regulation; Clarification Seekers demonstrated moderate accuracy and reactive help-seeking; Reflective Performers exhibited strategic engagement and high metacognitive activity. This study introduces an exploratory, scalable approach to learner profiling through natural language dialogue, advancing the design of adaptive, learner-aware LLM tutoring systems. The findings support the development of real-time learner modeling techniques that move beyond correctness, offering actionable insights for delivering more personalized and effective AI-assisted instruction in programming education.
This study examines the integration of computational deep learning and digital literacy from 2011 to June 2025. Employing a hybrid methodology of Systematic Literature Network Analysis and Latent Dirichlet Allocation topic modeling, 141 high impact documents were synthesized following the PRISMA 2020 protocol. Findings reveal a conceptual shift from technical exploration (2011–2018) toward human-centric, pedagogical deep learning frameworks (2019–2025). While publications peaked in 2024, Australia and South Korea emerged as leading centers of excellence in citation impact. Latent Dirichlet Allocation modeling identified ten topics, uncovering a significant research gap in using AI for fundamental research processes compared to its dominance in instructional assessment. This study provides a novel mapping of thematic evolution and offers strategic recommendations for longitudinal empirical studies and inclusive AI-driven pedagogical designs.
This study investigates the use of AI-driven macro expression analysis to enhance the engagement of hyperactive students in English language learning. By utilizing Convolutional Neural Networks (CNN) and K-Nearest Neighbors (K-NN), this research aims to detect and analyze students' macro facial expressions, as well as their correlation with engagement levels. Data was obtained from 24 learning videos, consisting of 13,263 frames, analyzed to identify expressions of boredom, sadness, and happiness. The analysis results show that boredom and sadness dominate, while happiness is recorded at a lower frequency, indicating the need for a more varied and responsive teaching approach. This study also finds that AI-driven emotion detection can provide more adaptive feedback for hyperactive students, allowing teachers to adjust teaching methods in real-time according to the students' emotional responses. The findings contribute new insights into the field of inclusive education by integrating AI technology to monitor and tailor learning for students with special needs. Theoretically, this research enriches the understanding of the role of macro expressions in student engagement, particularly in the context of ADHD. Practically, the results offer technology-based solutions to support more adaptive and responsive teaching that aligns with students' emotional changes. This research contributes to the development of more holistic and interactive learning methods, which can improve learning outcomes for students with special needs, especially in English language education.
Consistent and objective assessment of Course Learning Outcomes remains a challenge in every engineering program. This paper develops EAUT-OBE, an AI-supported system that utilises OCR, Vietnamese NLP, and Bloom's Taxonomy classification to extract, categorize, and map CLOs to Program Learning Outcomes across the entire Automotive Engineering program at East Asia University of Technology. Using 71 preprocessed syllabi, the system extracted 301 CLOs, which were mapped to 12 PLOs. The EAUT-OBE system was developed on and fine-tuned with the GPT-OSS-20B, resulting in approximately 91% accuracy in Bloom-level classification. It also reduced processing time by about 85%, compared to the baseline models PhoGPT-4B and EraX-7B. The results indicated better curriculum transparency and the achievement of accreditation and consistency in staff evaluation. Limitations could be due to OCR quality and dataset scale. Future work will expand the OBE dataset in Vietnamese and integrate predictive learning analytics.
Recently, the academic recommendation system represents the process of suggesting suitable institutions, courses, or learning pathways for students based on their performances and interests. Yet, the conventional systems didn’t concentrate on temporal dynamic pattern analysis within the Indian higher education institutions, leading to less effective or static academic recommendations. Thus, an academic recommendation system is proposed for Indian higher education institutions using Few-Shot PairNorm-Apical Dendrite Graph Attention Networks (FSPN-ADGAT) by considering temporal dynamic pattern analysis. Primarily, the student data undergoes pre-processing. Further, student performance analysis is done, followed by feature extraction. Now, the institutional course data undergoes pre-processing, followed by contextual embedding of text using Adapter Layers-Bidirectional Encoder Representations from Transformers (AL-BERT). Similarly, by using SRC, course similarity is analyzed between the pre-processed course data and extracted features. Similarly, the temporal dynamic pattern analysis is done from the pre-processed course data using Student-t Likelihood-based Bayesian Change Point (SL-BCP) and indicator extraction. Now, based on the analyzed course similarity, extracted features, contextual embedding output, analyzed temporal dynamic patterns, and extracted indicators, the node and matrix construction is performed. Lastly, the academic recommendation using FSPN-ADGAT provides personalized course suggestions to the students. Therefore, the proposed FSPN-ADGAT attained a lower Mean Absolute Error (MAE) of 0.171 than the conventional techniques.
