The emergence of artificial intelligence tools has attracted considerable attention from universities worldwide. Following the introduction of ChatGPT, substantial interest emerged among both academic communities and students. Although existing literature has extensively examined ChatGPT adoption, the perspectives, perceptions, and attitudes of higher education students toward ChatGPT remain insufficiently explored. Therefore, this study aimed to examine the key variables influencing ChatGPT acceptance and use among undergraduate students. The study employed an online survey questionnaire developed in accordance with the theoretical constructs of UTAUT2 and distributed it to 2,254 undergraduate students from 95 higher education institutions in the Philippines. Structural equation modeling using WARPPLS version 8.0 was utilized to analyze the relationships among the study constructs. The findings revealed not only the direct effects of the examined factors but also the moderating roles of age, gender, and experience in shaping ChatGPT acceptance and use behavior.
This study pioneers a digital humanities approach to systematically examine the millennium-spanning evolution of Chinese literary style. By constructing a cross-generational corpus from the pre-Qin through the Ming-Qing periods and developing a multidimensional quantitative index system, it integrates linguistic feature extraction with social network analysis to overcome the limitations of traditional chronological methods. Methodological innovations include dynamic time-window processing and an enhanced latent Dirichlet allocation model, which reveal key transition patterns between poetry and prose. Findings identify significant "style interpenetration" during the Tang-Song transformation and underscore the previously underestimated normative influence of imperial examination reforms, whose effects surpassed those of dynastic transitions. These insights challenge conventional literary historiography while providing new perspectives on the dynamic interplay between literary production and social structures.
This study examined the predictive and mediating relationships among the growth language mindset, the informal digital learning of English (IDLE), foreign language enjoyment, and academic achievement in the context of online English as a foreign language (EFL) courses. Data were collected from 237 EFL university students and analyzed using structural equation modeling. The results indicated that both growth mindset and IDLE significantly predicted foreign language enjoyment. Growth mindset also exerted a direct positive effect on academic achievement, whereas IDLE did not. Instead, foreign language enjoyment fully mediated the association between IDLE and achievement and partially mediated the link between growth mindset and achievement. These findings highlight the important role of enjoyment as an affective mechanism that connects learner beliefs and behaviors to academic outcomes in online learning environments. Overall, the study contributes to the growing literature on positive psychology and informal learning in EFL education.
This study examined the predictive and mediating relationships among the growth language mindset, the informal digital learning of English (IDLE), foreign language enjoyment, and academic achievement in the context of online English as a foreign language (EFL) courses. Data were collected from 237 EFL university students and analyzed using structural equation modeling. The results indicated that both growth mindset and IDLE significantly predicted foreign language enjoyment. Growth mindset also exerted a direct positive effect on academic achievement, whereas IDLE did not. Instead, foreign language enjoyment fully mediated the association between IDLE and achievement and partially mediated the link between growth mindset and achievement. These findings highlight the important role of enjoyment as an affective mechanism that connects learner beliefs and behaviors to academic outcomes in online learning environments. Overall, the study contributes to the growing literature on positive psychology and informal learning in EFL education.
This study proposes and evaluates a culturally adaptive digital platform for traditional music education in cross-cultural settings. Using a design-based research approach, the platform integrates multimodal resources, multilingual interfaces, and real-time feedback to enhance learner engagement, cultural understanding, and emotional resonance. Empirical results from diverse learners show improved cognitive mastery and strong emotional response, although participation in discussions requires further enhancement. The findings highlight the potential of technology-enhanced solutions in preserving intangible cultural heritage and promoting intercultural empathy in global educational environments. Future work will focus on artificial intelligence personalization and broader cultural scalability.
This study addresses the use of ChatGPT as a psychometric scale applied to university students, a topic of great relevance in the current academic and technological landscape. Given the rapid evolution of artificial intelligence (AI) and its increasing integration into educational environments, it is essential to examine how students interact with AI-powered tools. The research employed a quantitative methodology, incorporating both exploratory and confirmatory factor analyses to determine the factor structure of the scale. In addition, reliability measures such as McDonald's omega and Cronbach's alpha were used to assess internal consistency. The results demonstrated strong validity and reliability, indicating that the scale is a robust tool to assess the use of ChatGPT in academic contexts. One of the key contributions of this study is its empirical evaluation of ChatGPT through a robust psychometric analysis. By applying well-established validation methods, this research ensures that the proposed scale is reliable and valid for use in educational settings.
In the era of digital communication, multimedia design has become a key tool for enhancing advertising, user interfaces, and brand communication. Dynamics, sound, and interaction—core elements of multimedia design—strongly influence visual impact and memory formation. However, current research mainly focuses on individual elements, lacking a systematic understanding of their synergistic effects. To address this gap, this study proposes a multimedia memory formation model based on multimodal memory theory, dual coding theory, and the working memory model. Case analysis and experiments have found that dynamic design boosts visual appeal and attention span, synchronized sound effects enhance emotional engagement and short-term memory, and interactive design strengthens long-term memory through active user participation. The study develops a dual evaluation index system, confirming the integrative power of multimedia elements. It not only advances theoretical understanding but also offers practical strategies for optimizing multimedia synergy in visual communication.
This study pioneers a digital humanities approach to systematically examine the millennium-spanning evolution of Chinese literary style. By constructing a cross-generational corpus from the pre-Qin through the Ming-Qing periods and developing a multidimensional quantitative index system, it integrates linguistic feature extraction with social network analysis to overcome the limitations of traditional chronological methods. Methodological innovations include dynamic time-window processing and an enhanced latent Dirichlet allocation model, which reveal key transition patterns between poetry and prose. Findings identify significant “style interpenetration” during the Tang-Song transformation and underscore the previously underestimated normative influence of imperial examination reforms, whose effects surpassed those of dynastic transitions. These insights challenge conventional literary historiography while providing new perspectives on the dynamic interplay between literary production and social structures.
This research investigated factors influencing Jordanian academics’ intention to use virtual reality (VR) technology in higher-education institutions. Recognizing VR’s transformative potential in education, the study integrated the unified theory of acceptance and use of technology with protection motivation theory to develop a comprehensive theoretical framework for VR adoption. An online survey collected data from Jordanian academics, analyzed using structural equation modeling. Findings revealed that threat appraisals, telepresence, effort expectancy, social influence, and facilitating conditions positively impacted academics’ intention to use VR. Conversely, performance expectancy showed no correlation with VR usage intention within higher-education institutions. These results offered valuable insights into the conditions that both facilitate and hinder VR implementation in higher education, providing practical recommendations for institutions aiming for effective VR technology application in their educational practices.
This study benchmarks multiple machine learning models to predict student academic performance. The research analyzes data from students in mathematics and Portuguese language courses, examining the relationship between various factors and academic performance. The benchmark implementation includes data preprocessing, exploratory data analysis, feature engineering, model training, and hyperparameter tuning for both regression (predicting final grades) and classification (predicting pass/fail outcomes) tasks. The findings demonstrate that ensemble methods, particularly gradient boosting models, outperform other algorithms with root mean square error of 3.34 for regression and F1 score of 0.88 for classification after hyperparameter tuning. Feature importance analysis reveals that past failures, alcohol consumption, study time, and parent education level are among the most influential predictors of academic performance. The results provide valuable insights for educational stakeholders to implement targeted interventions for at-risk students and improve overall academic outcomes.
With the rapid development of artificial intelligence (AI), traditional educational evaluation models are increasingly inadequate in data processing, dynamic feedback, and personalized analysis—limiting their ability to support quality monitoring in adult and vocational education. This study addresses this gap by constructing an AI-based educational assessment model tailored to diverse learning contexts. First, a multi-level, quantifiable evaluation framework grounded in data-driven principles is developed, and then machine learning and deep learning algorithms are optimized to enhance model adaptability and accuracy. Empirical analyses verify the model’s performance in evaluating learning processes and outcomes, demonstrating its advantages in improving efficiency and feedback precision. The discussion highlights practical challenges and refinements, emphasizing the model’s value in providing scientific decision support for educators and administrators in adult education settings.
Machine learning encompasses perception, understanding, and application of knowledge. Traditional English teaching struggles to meet modern demands, prompting universities to innovate. This research explored the multimodal concept and proposed a new approach for university-level English instruction, an ensemble multimodal adaptive boosting-based teaching model. Through simulation studies, the ensemble multimodal adaptive boosting-based teaching model was developed and tested in two classrooms via a grammar proficiency post-test. Results showed that the study group significantly outperformed the control group, demonstrating enhanced English grammar abilities. This innovative teaching method not only boosted students’ performance but also improved interaction between students and educators, highlighting its effectiveness in enhancing English education.
Rural primary schools in Namibia face challenges such as low socio-economic status, inadequate infrastructure, and limited funding, which hinder effective teaching and learning. Despite minimal exposure to technology, some teachers in these schools integrate ICT independently. This study examined the experiences of veteran teachers (digital immigrants) using technology in rural primary schools in the Endola circuit of the Ohangwena region and was framed through a constructivist lens using the UTAUT framework. Thirteen public rural school teachers were purposively selected for this qualitative study, which used semi-structured interviews and classroom observations. Thematic analysis revealed that teachers encountered advanced digital skills in learners, transformed roles, evolving beliefs, and experimentation with technologies. Challenges included inadequate ICT training, scarce resources, and keeping pace with digitally native learners. The study recommends subject-specific ICT training for teachers.
With the rapid development of information technology and its enhancing effects on learning activities, increasing attention is being paid to improving learning efficacy, with an emphasis on students’ learning characteristics and the context. Using structural equation modeling and business English learners as the sample, the author explored the relationships among information technology–supported language learning, outcomes of English development, engagement in cooperative learning activities, and student perceptions of professional qualifications. The data supported the hypothesized model. The results indicated that student engagement in cooperative activities and their perceptions of professional cognition on required competencies had significant indirect effects on information technology–supported language learning. The author discusses the implications of keeping a good balance between improving professional skills and developing language abilities, and of designing workplace learning activities to improve the cognition of professional required competencies.
A gap exists between traditional chemical engineering curricula and the growing need for cybersecurity awareness in the chemical process industry. For chemical engineering education, we developed cybersecurity education modules for Plant Design, Advanced Analysis, and Process Control Laboratory courses. Students engaged in interactive social engineering games and hacking simulations to learn cyber threats and defenses. Industry expert lectures provided real-world insights. Student feedback showed strong engagement and positive reception. This article shares implementation insights, challenges, successes, and best practices for integrating cybersecurity education into engineering curricula.
Facing the urgent need for personalized and real-time interaction in music education, this study constructed an artificial intelligence-assisted interactive platform that offers targeted support in pitch recognition, rhythm training, and classroom feedback. Through function planning and algorithm optimization, it enables diversified student-teacher communication while leveraging artificial intelligence to capture and analyze teaching data, helping teachers identify students' weaknesses in playing skills or music understanding for strategic teaching adjustments. The platform also overcomes compatibility issues across various hardware and user needs via inclusive design and management, provides precise counseling for individual learning difficulties, and offers real-time monitoring with personalized feedback to deliver technical guidance and emotional support. This research comprehensively explored the platform's requirements, design, evaluation, and user feedback, aiming to inspire the music education field and inform future studies.
With the continuous progress of educational technology, personalized teaching has become a key way to improve teaching quality. In view of the current situation that English teaching content lacks personalization and interactivity, this paper proposes a personalized English teaching content generation system based on neural network (NN). The system uses deep learning technology to accurately capture students' personalized learning characteristics, and combines the advantages of neural network intuitive presentation to tailor English teaching content for each student. Methodologically, we construct a neural network model that contains multidimensional data such as students' characteristics, learning behavior and teaching content, so as to analyze students' learning preferences and ability level. Through graphical and interactive content display, students' learning experience is enhanced.
Traditional assessment in international sports communication is often fragmented and subjective, limiting timely, learner-centered feedback. This study presents a curriculum framework enhanced by generative artificial intelligence, coupled with a deep learning (DL) model for instructional effectiveness assessment in international sports communication. The pipeline integrates de-identified learning analytics—learning management system clickstreams, interaction networks, and rubric-scored artifacts—into engineered features for DL training with parameter search and cross-validation. A 16-week field study across three undergraduate sections at a Chinese comprehensive university (N = 60; two involving generative artificial intelligence, one comparison) benchmarked DL against linear regression and decision tree baselines and against expert ratings on intercultural communication competence, framing diversity, and production quality. Results show that DL converged faster and yielded lower prediction error than the baselines, while closely aligning with expert scores, enabling actionable, personalized feedback and course tuning driven by constructive alignment.
Traditional teaching quality evaluation lacks comprehensive study; this paper constructed an evaluation index system of network teaching quality based on multi-source data. Against the background of multi-source data driving, the network teaching quality evaluation index system is constructed, which consists of five indexes: teaching platform function, teaching technology support, teaching service guarantee, teaching process, and teaching feedback. Based on probabilistic hesitation fuzzy sets and evidential reasoning, a network teaching quality evaluation model is established, and probabilistic hesitation fuzzy sets are used to describe the mixed assessment information uniformly. Probabilistic hesitation, fuzzy entropy, and expert weighting are used to assign weights to evaluation indexes. The example verification demonstrated that combining evidential reasoning with utility theory can effectively assess the quality of network teaching. The evaluation results are ranked, and the comparison indicates that this method enhances the accuracy of teaching quality evaluation.
Traditional learning management systems are cloud-based and teacher-centric, limiting accessibility, flexibility, and student-centered learning. We present the Active Learning EXperience (ALEX), a decentralized learning management system aligned with Education 4.0, supporting flipped and project-based learning. ALEX leverages Web3 technologies (blockchain, InterPlanetary File System, and offline-first mechanisms) to enhance security, privacy, and access in low-connectivity environments. This study evaluated, through the case study method, ALEX's usability, performance, and pedagogical impact with nine third-year information systems students and one facilitator in an authentic project-based course at a Brazilian university, with two non-governmental organizations taking part as clients. Instruments included a custom usability questionnaire, and a pre/post-test skill assessment. Results showed significant improvements in hard and moderate improvement in soft skills, suggesting further enhancements. Future work will focus on expanding ALEX's collaborative features and scalability testing to strengthen its impact on student engagement and learning outcomes.
