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.

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.

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.

User stories are essential in agile software development for capturing software requirements, yet concerns over their quality persist globally. While prior studies have evaluated user story quality using practitioners and artificial intelligence, they primarily focus on general settings. This study addresses a gap by evaluating the quality of student-generated user stories in an educational context, specifically in Indonesia. The objective of this study is to compare evaluations by human evaluators and ChatGPT using the Quality User Story (QUS) Framework and evaluate the quality of the student-generated user story compared to the global studies. A total of 951 user stories from 103 student software projects were analyzed. Evaluations were conducted by three human evaluators and ChatGPT (GPT-4o). Percentage Agreement and Cohen’s Kappa measured inter-rater agreement, while the McNemar Test assessed statistical significance, and effect sizes were examined using Cohen’s g. Results show generally high agreement between human and ChatGPT evaluations, but lower consistency in several criteria, such as Conceptually Sound, Independent, and Unambiguous. Only four of the thirteen criteria—Conflict-Free, Unique, Well-Formed, and Atomic—showed no significant differences. Most criteria showed small to medium effect sizes, whereas Complete exhibited a large practical difference. Common quality issues among students included Uniform, Independent, and Complete (set criteria), Atomic, Conceptually Sound, and Unambiguous (individual criteria), with overlap observed in global studies. This study shows that ChatGPT can support user story evaluation in educational settings when guided by clear rubrics and validated by humans. It also offers practical insights for educators by identifying criteria that require stronger emphasis in teaching, particularly in software engineering education in Indonesia.

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.

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.

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.

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.

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. 

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 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 (ε=0.7, δ=10⁻⁵), 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.