Educational assessment has changed from “one size fits all” model to learner-centered, responsive, and adaptable dynamic rubrics and feedback procedures. Improved instructor-student communication and transparency boost, engagement and assessment confidence with dynamic rubrics.  Dynamic rubrics could improve feedback and assessment. Pre-processed standard dataset texts are used. Pre-processed texts are delivered to Word2Vec to extract key features and vectorize them. Fuzzy clustering model with dynamically weighted rubrics evaluates the assignment. The dynamic rubric clearly outlines the assignment's evaluation criteria, and weights assist decide how much each criterion contributes to the overall grade using Foraging Phase Updated Addax Optimization. Subsequently, the assessment score is obtained, and based on this score, feedback generation is performed on the developed model using Generative Attention Long Short Term Memory. Finally, the developed model provides the optimal responses to the students by using the dynamic rubric with a deep learning model and an enhanced optimization algorithm. The experiment scores on two datasets observed over existing models shows average accuracy of 99.36% with 2.7% improvement over K-Means Clustering.  Average MAE of 31.85%, reduced by 81% over K-Means. Average Efficiency increase by 21.30% over other models. Thus, the developed model is more effective and robust than the existing approaches.

This study evaluates the performance of six generative artificial intelligence (AI) systems in solving Thai-language multiple-choice examinations in the subject of Programmable Logic Controllers (PLC), This study evaluates the performance of six generative artificial intelligence (AI) systems in solving Thai-language multiple-choice examinations in the subject of Programmable Logic Controllers (PLC), a core component of Industrial Electrical Engineering education. Six large language models (LLMs), including ChatGPT, Claude, DeepSeek, Gemini, Copilot, and Grok, were tested using fifteen sets of PLC examination questions. Statistical analysis was conducted using one-way ANOVA and two-sample t-Tests with Bonferroni correction to examine performance differences. In addition, effect size measures, including Eta-squared (η²) and Cohen’s d, were calculated to assess the magnitude of the observed differences. The results show that ChatGPT achieved the highest mean score (77.27%), while DeepSeek followed closely (76.73%) and demonstrated the lowest standard deviation (±1.83%), indicating the most consistent performance across test sets. Claude also performed strongly (74.80%), whereas Gemini, Copilot, and Grok obtained similar mid-tier scores ranging from 72.40% to 72.73%. Although all LLMs achieved scores within the passing grade range, ANOVA confirmed statistically significant differences among systems (p-value = 0.0002). However, after applying the Bonferroni correction, only a subset of pairwise differences remained statistically significant, particularly between DeepSeek and several mid-tier LLMs, while the differences among ChatGPT, Claude, and DeepSeek were not statistically significant under the adjusted threshold. Effect size analysis further indicates that some of these differences represent meaningful practical variation in LLM performance. These findings indicate that contemporary LLMs demonstrate baseline comprehension of PLC concepts and can achieve passing-level performance in technical examinations conducted in a non-English language. The study contributes empirical evidence on AI performance in Thai-language technical assessments and highlights the potential role of generative AI as a complementary learning support tool in vocational and engineering education. 

This study examines how critical thinking skills influence the relationship among cognitive load, self-efficacy, and problem-solving abilities in the context of immersive learning experiences and perceived academic performance among college students in technical education programs. Emerging technologies such as augmented reality (AR) and game-based learning are employed in the study to enhance student engagement and cognitive function. A quantitative approach was employed to gather data from 748 Indonesian college students enrolled in technical education programs. The study employed structural equation modeling (SEM) via SmartPLS 4.0 to examine direct, indirect, and moderating effects. Digital literacy was examined as a moderating variable in the model. The results indicate that critical thinking significantly influences the relationship between cognitive load, self-efficacy, and problem-solving skills in facilitating meaningful learning and academic success. The ability to solve problems was the most significant predictor of critical thinking. Surprisingly, digital literacy exerted a detrimental moderating influence on the correlation between critical thinking and immersive learning. This indicates that digital proficiency lacking cognitive regulation may hinder engagement in deep learning. The findings underscore the significance of cultivating critical thinking abilities within immersive and game-based learning contexts. Digital literacy programs ought to encompass more than mere technical competencies. Students should also be instructed in critical thinking regarding their knowledge and metacognition. This research contributes to existing literature by demonstrating a novel approach to integrating cognitive-affective factors, critical thinking, and immersive learning experiences in Indonesian higher education. It emphasizes the significance of digital literacy and reiterates the importance of augmented reality and game-based learning in attaining essential educational objectives.

The modern challenges of digitalizing education require effective strategies for developing value competencies in future teachers. Despite the widespread adoption of mobile learning in education, its impact on personal and professional attitudes remains underexplored. This study examines the relationship between primary pre-service teachers' engagement with mobile learning and the development of value competencies within the context of pedagogical training in Kazakhstan. A cross-sectional, quantitative design was employed to assess how mobile learning influences the growth of value competencies among primary pre-service teachers. Undergraduate students majoring in primary education participated in the study. Validated questionnaires were used for data collection, and analyses involved descriptive statistics, correlation, and regression, with appropriate tests of statistical assumptions. Results indicated that a majority of students actively use mobile platforms for learning. Positive correlations were observed between the frequency of mobile resource use and students’ cognitive understanding of values. The regression model demonstrated that engagement in mobile learning contributed significantly to the variance in value competencies. Additional analyses revealed stronger effects among certain participant groups and notable differences based on gender.
These findings underscore the effectiveness of mobile learning as a tool for shaping the values of future teachers and support its targeted integration into Kazakhstan's teacher training programs. The results provide a foundation for revising pedagogical approaches to focus not only on digital skills but also on the cultivation and transformation of personal values in future educators.

In this study, the needs of preschool teachers were analyzed to determine the applicability of STEAM+X approach in early childhood education. The study was conducted within the framework of the case study model, one of the qualitative research methods. The study group consisted of 16 preschool teachers working in independent preschools or kindergartens within primary schools affiliated to the Ministry of National Education in the 2024-2025 academic year. As a data collection tool, the "Applicability of STEAM+X Approach in Early Childhood Education: Teacher Needs Analysis SWOT Form" developed by the researchers was used. The data obtained were evaluated by content analysis method through MAXQDA program. The findings of the study revealed that teachers have a conceptual understanding of STEAM fields, use various methods and techniques effectively in educational processes, integrate technological tools in their classrooms, and are open to innovative approaches. However, it was determined that they lacked experience in implementing STEAM practices in the classroom, there was a lack of materials, the physical and infrastructural  facilities of the school were  limited, the administration and parental support were insufficient, guidance mechanisms were lacking, and mixed age groups made applicability difficult. Among the main threats preventing the adoption of the STEAM+X approach, teachers emphasized the need to raise awareness of parents, insufficient school resources, intense workload and time constraints, lack of access to technology, and lack of knowledge about the STEAM+X approach. On the other hand, within the scope of opportunities related to STEAM education, teachers stated that some STEAM materials are available at the institutional level and that they can benefit from online resources, in-service trainings and academic publications. However, it was also found that they did not have sufficient knowledge on how to effectively select and evaluate these resources. Accordingly, it was determined that teachers should be supported in integrating the STEAM+X approach into the preschool education program, developing applications with different methods and techniques, and using this approach as an effective tool. As a result, it was revealed that it is necessary to develop practice-based programs based on the STEAM+X approach to guide teachers and to expand teacher trainings.

The widespread use of Generative Artificial Intelligence tools among students across different educational levels is reshaping students’ attitude and education experience. They use it in various fields, including idea generation, writing assistance, and content creation. This study investigates the impact of the Modern Digital Skills course offered by the University of Jordan on students' digital literacy in Generative Artificial Intelligence. The study will employ a quantitative approach by conducting pre- and post-course surveys to measure changes in students' knowledge, skills, and attitudes across approximately 1,000 undergraduates from different majors at the university. Key variables include students' understanding of Generative Artificial Intelligence, their confidence in using Generative Artificial Intelligence tools, and their ability to critically evaluate AI-generated content and its ethical implications. The findings will determine whether the course significantly enhances students' knowledge, proficiency, critical thinking, and ethical awareness, while also exploring challenges and opportunities in integrating such a course into the academic curriculum. Ultimately, this study aims to provide insights for curriculum committees and decision-makers at universities in Jordan and the Middle East, emphasizing the importance of designing educational programs that foster essential Artificial Intelligence competencies and prepare students for a professional landscape increasingly shaped by Artificial Intelligence technologies.

The increasing dominance of Android devices has driven a surge in demand for skilled mobile programmers, prompting educational institutions to incorporate mobile programming courses into their curricula. This trend, combined with the rise of self-learning platforms, highlights the need for innovative educational technologies that enhance programming instruction. While automated assessment systems have improved the grading process in programming education, there remains a gap in mobile programming education, particularly due to the complexities of assessing Android applications. To address this, an innovative framework for Android application development is proposed, leveraging automated grading and assistance mechanisms. The framework employs a Test-Driven Development (TDD) approach, providing structured guidance and immediate feedback through automated testing tools including JUnit and Robolectric. A study involving 125 students revealed high engagement and success in basic topics, though challenges persisted in more complex areas, indicating a need for ongoing refinement and additional instructional support to elevate the learning experience in mobile application development.

Curiosity is a foundational driver of learning, exploration, and lifelong intellectual growth. This study presents an AI-based temporal–causal model of educational curiosity that integrates psychological mechanisms with computational dynamics to explain how curiosity evolves within learning environments. The model formalizes the interactions among key factors—novelty, uncertainty, motivation, engagement, and autonomy—capturing their collective influence on learners’ adaptive behavior over time. A series of simulated learning scenarios, varying in novelty and uncertainty levels, demonstrate how contextual and personal conditions—including teacher–student relationships, socio-economic status, and environmental support—shape the temporal progression of curiosity. Mathematical and logical analyses confirm system stability, showing convergence of long-term novelty and uncertainty toward equilibrium and validating causal coherence through Temporal Trace Logic (TTL). The results reveal that curiosity thrives under moderate novelty and manageable uncertainty, reflecting adaptive equilibrium between cognitive tension and motivation. Findings provide a theoretical and computational foundation for AI-driven educational systems that dynamically sustain curiosity and engagement, contributing to inclusive and lifelong learning aligned with UN SDG 4.

A hybrid analytic–holistic evaluation framework is developed and validated for assessing Information Technology (IT) undergraduate capstone projects in Thai higher education. Drawing on five academic years of multi-stakeholder assessment data, the research identifies five critical dimensions influencing evaluation outcomes: student competency performance, project proposal quality, advising effectiveness, panel variability, and assessment-criteria weighting. By integrating structured analytic rubrics with holistic panel judgments, the framework addresses persistent challenges of grading inconsistency, evaluator bias, and misalignment between academic assessment and industry expectations. Statistical analyses indicate that documentation quality, project innovation, and internship performance are the strongest predictors of final panel grades, explaining 72% of evaluation variance. The principal contribution lies in providing empirical evidence of assessment variability and a validated, replicable model that improves fairness, transparency, accreditation compliance, and alignment with professional IT competencies. The framework supports outcome-based education standards (ABET, ASIIN, ETQA) and offers practical guidance for enhancing quality assurance and graduate employability.

The focus of this research is on the process of conducting distance education online, which is undergoing rapid transformation due to the impact of digitalization. The primary objective is to examine how cognitive load arising during online distance learning affects the perceived system usability, and the role of cognitive control and flexibility in this relationship. By revealing the direct and indirect effects of cognitive load, the study aims to contribute to the improvement of online education platforms in terms of user experience. The research was conducted on online courses taken by Akdeniz University students via the Microsoft Teams platform. Cognitive control and flexibility were measured using the Cognitive Control and Flexibility Scale, cognitive load was measured using the NASA-TLX, and the perceieved system usability was determined using the System Usability Scale. The findings show that, as cognitive load increases, perceived system usability decreases; conversely, this perception increases with higher cognitive control and flexibility. Furthermore, it was determined that cognitive load indirectly affects system usability via cognitive control and flexibility. Consequently, online education systems should be designed to reduce users’ cognitive load while supporting their cognitive control and flexibility.

This study examines the integration of Question Answering (QA) technology into e-health education using scaffold method to address stunting prevention and understanding of early childhood nutrition in Indonesia. The research developed a computer-supported learning platform that combines adaptive QA systems with structured scaffolding techniques to support maternal knowledge development and informed nutrition practices. Data was collected from Indonesian stunting education programs and nutrition improvement initiatives targeting children under five years old. The platform implemented progressive learning modules that provided real-time responses to user queries while offering contextual support through scaffolded feedback mechanisms. Knowledge improvement was evaluated using a pre-test and post-test design administered before and after system interaction, with a follow-up assessment conducted four weeks later to measure retention. Results demonstrated improvements in knowledge retention scores (mean increase of 42%) and understanding of nutrition guidelines among participating mothers. The QA system helped clarify common misconceptions about complementary feeding practices while maintaining engagement through personalized learning paths. These findings indicate that scaffolded QA technology has potential as a supportive tool for e-health education in resource-limited settings, although broader implementation and long-term impact require further investigation.

Crowdsourcing is a distinct innovation strategy that invites contributions from external actors and represents a key form of collaborative innovation. It plays a vital role in enhancing the visibility of educational institutions and supporting territorial development. Drawing on a bibliometric analysis of publications indexed in the SCOPUS database, this study seeks to examine the extent to which crowdsourcing has been adopted within educational establishments. Covering a variety of dimensions over a broad period from 1999 to 2023. This analysis provides an overview of the current state of the crowdsourcing field in relation to education. Using an extensive database, a combination of keywords and inclusion/exclusion criteria, we extracted 305 distinct articles. ScientoPy and VOSviewer were employed to explore and analyze the data raised. After a dip in 2016, a recovery in the volume of literature relating to crowdsourcing and education in educational institutions began to emerge in 2020. These results indicate the particular interest shown in the subject of open innovations in public and private institutions. The crowdsourcing theme was ranked in the top ten, with 28 publications before 2022 and a proportion of 20% between 2022 and 2023. Crowdsourcing in the academic context has been growing in recent years. However, the studies carried out in this area remain insufficient, particularly bibliometric studies analyzing crowdsourcing in educational establishments and learning in general. Practitioners and academics can take advantage of different research models in open innovation, crowdsourcing and education. Ultimately, this work aims to guide researchers and practitioners by mapping the current dynamics and major trends shaping this field.