Computers and Education Artificial Intelligence最新文献

{"title":"Design and implementation of Math City: An inquiry-based metaverse platform for mathematics education","authors":"Manpreet Singh,&nbsp;Daner Sun,&nbsp;Yin Yang","doi":"10.1016/j.caeai.2025.100462","DOIUrl":"10.1016/j.caeai.2025.100462","url":null,"abstract":"<div><div>Responding to the need for innovative educational environments in higher education, this study presents “Math City”, an immersive Metaverse platform designed to enhance inquiry-based mathematics learning and develop 21st-century skills. Traditional university-level mathematics courses often encounter difficulties in sustaining student engagement and fostering the application of abstract concepts, such as the properties of three-dimensional shapes. To address these challenges, Math City was designed using the Unity game engine, which incorporates the 5E instructional model (Engage, Explore, Explain, Elaborate, and Evaluate) alongside gamification elements such as quests, rewards, and badges to enhance motivation and support conceptual understanding. Within a virtual abandoned city setting, students work collaboratively to complete four interrelated quests, each aligned with specific phases of the 5E model, guiding them through meaningful investigations of 3D shape properties in an engaging and authentic context. The platform was evaluated by 179 participants, utilizing the System Usability Scale (SUS) for data collection. The results showed an overall SUS score of 74.54, corresponding to a “B” grade on the Sauro and Lewis usability scale, indicating an acceptable level of usability. Although participants provided positive feedback regarding the platform's efficiency, effectiveness, and user satisfaction, slight variations in SUS scores were observed across demographic groups, including gender, age, and educational background. The implications of this study were discussed. Future development of Math City will focus on expanding its assessment capabilities to evaluate not only knowledge acquisition but also higher-order competencies such as critical thinking, collaboration, and creativity. Additionally, the development of a VR-compatible version is planned to further enhance the immersive experience and provide deeper insights into student learning within Metaverse-based educational environments.</div></div>","PeriodicalId":34469,"journal":{"name":"Computers and Education Artificial Intelligence","volume":"9 ","pages":"Article 100462"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Designing a model of sustainable education based on artificial intelligence in higher education","authors":"kamran Bagherimajd ,&nbsp;Kosar khajedad","doi":"10.1016/j.caeai.2025.100439","DOIUrl":"10.1016/j.caeai.2025.100439","url":null,"abstract":"<div><div>Artificial intelligence (AI) in higher education (HE) plays a role in promoting the sustainability of society by fostering innovation and preparing students for the digital age. In this regard, the aim of the present research has been to design an AI-based sustainable education (SE) model in HE. The research method was a monomethod design with multiple sequential, qualitative and qualitative phases. In the first part of the qualitative section, the meta-synthesis approach has been used in accordance with the findings of Springer, Emerald, and Elsevier international journals from 2000 to 2024. A total of 213 articles were reviewed and 39 articles were entered the final analysis. In the second part of the qualitative section, the focus group method was used to check the validity and discover gaps in the findings. For this purpose, five faculty members of the Education and Technology Department performed data analysis based on open, axial and selective coding in MAXQDA software. The results showed opportunities and challenges of AI in SE in seven main categories and 24 sub-categories, which include organizational structure (human resources, financial resources, facilities and equipment, rules and regulations), curriculum (tools and approaches to planning, curriculum design, curriculum development and change), global citizen (responsibility, global competence and global civil participation), continuous learning (adaptive learning, collaborative learning, personal learning and automatic learning), creativity and innovation (initiative, educational innovations, creative thinking and innovation in methodology), teaching and learning process (tools, methods, evaluation and feedback) and communication (interaction and international communication, scientific communication, emotional communication and social communication). Therefore, there are challenges and opportunities in using smart AI tools for fostering digital-age graduates and ensuring sustainable social and economic developments. Therefore, improving opportunities and reducing such challenges can promise a sustainable future for the global community.</div></div>","PeriodicalId":34469,"journal":{"name":"Computers and Education Artificial Intelligence","volume":"9 ","pages":"Article 100439"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144481641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing students’ DRIVE: A framework to evaluate learning through interactions with generative AI","authors":"Manuel Oliveira,&nbsp;Carlos Zednik,&nbsp;Gunter Bombaerts,&nbsp;Bert Sadowski,&nbsp;Rianne Conijn","doi":"10.1016/j.caeai.2025.100497","DOIUrl":"10.1016/j.caeai.2025.100497","url":null,"abstract":"<div><div>As generative AI (GenAI) transforms how students learn and work, higher education must rethink its assessment strategies. This paper introduces a conceptual framework, DRIVE, and a taxonomy to help educators evaluate student learning based on their interactions with GenAI chatbots. Although existing research maps student-GenAI interactions to writing outcomes, practice-oriented tools for assessing evidence of domain-specific learning beyond general AI literacy skills or general writing skills remain underexplored. We propose that GenAI interactions can serve as a valid indicator of learning by revealing how students steer the interaction (Directive Reasoning Interaction) and articulate acquired knowledge into the dialogue with AI (Visible Expertise). We conducted a multi-methods analysis of GenAI interaction annotations (<em>n</em> = 1450) from graded essays (<em>n</em> = 70) in STEM writing-intensive courses. A strong positive correlation was found between the quality GenAI interactions and final essay scores, validating the feasibility of this assessment approach. Furthermore, our taxonomy revealed distinct GenAI interaction profiles: High essay scores were connected to a ”targeted improvement partnership” focused on text refinement, whereas high interaction scores were linked to a ”collaborative intellectual partnership” centered on idea development. In contrast, below-average scores were associated with ”basic information retrieval” or ”passive task delegation” profiles. These findings demonstrate how the assessment method (output vs. process focus) may shape students’ GenAI usage. Traditional assessment can reinforce text optimization, while process-focused evaluation may reward an exploratory partnership with AI. The DRIVE framework and the taxonomy offer educators and researchers a practical tool to design assessments that capture learning in AI-integrated classrooms.</div></div>","PeriodicalId":34469,"journal":{"name":"Computers and Education Artificial Intelligence","volume":"9 ","pages":"Article 100497"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145519443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"How does students' perception of ChatGPT shape online learning engagement and performance?","authors":"Mahboobeh Mehrvarz ,&nbsp;Ghasem Salimi ,&nbsp;Samaneh Abdoli ,&nbsp;Bruce M. McLaren","doi":"10.1016/j.caeai.2025.100459","DOIUrl":"10.1016/j.caeai.2025.100459","url":null,"abstract":"<div><div>Artiicial intelligence technologies, such as ChatGPT, Bert, LaMDA, and T5 have become deeply integrated into universities, influencing numerous functions within higher education and various aspects of students' lives. This article examined how students' perceptions of ChatGPT influence their engagement and performance in online learning, focusing on the mediating role of engagement. The perception of ChatGPT involves a student's understanding of, willingness to utilize, and concerns regarding the technology. These interconnected factors can influence students' online learning engagement with the software and, consequently, affect their academic performance. The study used self-reported data from 305 participants at a large university in Iran. The findings from Structural Equation Modeling (SEM) revealed that students' perception of ChatGPT accounts for 19.2 % of the variance in online learning engagement, while the combination of ChatGPT perception and online learning engagement explains 40.4 % of the variance in academic performance. Furthermore, students' perceptions of ChatGPT had direct effects on online learning engagement (β = 0.438) and academic performance (β = 0.268). Additionally, online engagement significantly mediated this relationship, with an indirect effect of β = 0.206. The observed direct and indirect effects highlighted the essential role of online learning engagement in fostering interaction and enhancing students' performance. Overall, our conceptual model provides researchers and university administrators with a comprehensive understanding of students' perceptions of ChatGPT, their engagement, and their academic performance in an online setting. This model also provides valuable insights for future research on designing student activities that leverage artificial intelligence technologies, including ChatGPT-based tools.</div></div>","PeriodicalId":34469,"journal":{"name":"Computers and Education Artificial Intelligence","volume":"9 ","pages":"Article 100459"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144809563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping the evolution of AI in education: Toward a co-adaptive and human-centered paradigm","authors":"Shihui Feng ,&nbsp;Huilin Zhang ,&nbsp;Dragan Gašević","doi":"10.1016/j.caeai.2025.100513","DOIUrl":"10.1016/j.caeai.2025.100513","url":null,"abstract":"<div><div>This study analyzes 2398 research articles published between 2020 and 2024 across eight core venues related to the field of Artificial Intelligence in Education (AIED). Using a three-level knowledge co-occurrence network analysis, this study analyzes the knowledge structure of the field, the evolving knowledge clusters, and the emerging frontiers. The findings reveal that AIED research is centered on developing AI-assisted systems and using AI to support educational analysis, with sustained themes such as intelligent tutoring systems, learning analytics, and natural language processing, alongside rising interest in large language models (LLMs) and generative artificial intelligence (GenAI). By tracking the bridging keywords over the past five years, this study identifies four emerging frontiers in AIED, including <em>LLMs, GenAI, multimodal learning analytics</em>, and <em>human-AI collaboration</em>. The current research interests in GenAI are centered around GAI-driven personalization, self-regulated learning, feedback, assessment, motivation, and ethics. Our findings underscore the need to consciously shape these technical pursuits through co-adaptive and human-centered principles. It is essential to proactively bridge these advanced technical capabilities with core educational values and purposes to ensure that technological development is guided by educational goals, ethics, and a commitment to human agency and education equity. This study provides a large-scale field-level mapping of AIED's transformation in the GenAI era and sheds light on the future research development and educational practices.</div></div>","PeriodicalId":34469,"journal":{"name":"Computers and Education Artificial Intelligence","volume":"9 ","pages":"Article 100513"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145681343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Promoting pre-service music teachers’ TPACK with generative AI: an intervention through designing with AI","authors":"Haiying Li ,&nbsp;Ching Sing Chai ,&nbsp;Xinlei Wang","doi":"10.1016/j.caeai.2025.100525","DOIUrl":"10.1016/j.caeai.2025.100525","url":null,"abstract":"<div><div>Generative artificial intelligence (GenAI) presents transformative opportunities for education, yet its integration into music teacher preparation remains underdeveloped. Two critical gaps exist: (1) scant empirical studies on how pre-service music teachers can leverage GenAI to develop their expertise; and (2) the potential of designing with AI to develop technological pedagogical content knowledge (TPACK) in music education is unexplored, despite evidence of the effectiveness of learning by design in other disciplines. This study implemented a six-week designing with AI intervention grounded in TPACK framework, engaging 59 pre-service music teachers in collaborative GenAI-assisted lesson design. Pre-service music teachers employed GenAI tools to develop music lesson plans incorporating the 5E instructional model. Mixed-methods analysis indicated that this program: (1) significantly enhanced pre-service music teachers' GenAI-specific TPACK across all dimensions; (2) revealed three phases of pre-service teacher development of GenAI-supported music lesson design; and (3) fostered pre-service music teachers' critical understanding of GenAI's pedagogical affordances in music education. As an early empirical study investigating pre-service music teachers' GenAI-TPACK development, this research demonstrates how collaborative design with AI fosters pre-service music teachers' GenAI-TPACK development.</div></div>","PeriodicalId":34469,"journal":{"name":"Computers and Education Artificial Intelligence","volume":"9 ","pages":"Article 100525"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145681346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization method for academic English content based on generative adversarial networks and data augmentation","authors":"Hui Gao","doi":"10.1016/j.caeai.2025.100492","DOIUrl":"10.1016/j.caeai.2025.100492","url":null,"abstract":"<div><div>With the globalization of academic exchanges, the importance of academic English writing quality has become increasingly prominent. Especially for non-native speakers, grammar and language quality in academic English writing significantly affect the readability and academic value of articles. Therefore, this study proposes an academic English content optimization method based on generative adversarial networks and data augmentation. The method uses Transformer as the generator, combines generative adversarial networks with data augmentation techniques to generate high-quality pseudo error correction sentence pairs, and optimizes model performance through policy gradient methods. Although academic English is used as the application context in this study, the architecture can be adapted to other English writing genres given appropriate training corpora. From the results, when the iteration reached 500, the precision was 0.98 and the recall was 0.10. The accuracy-2, F1 score, mean absolute error, correlation coefficient index, and accuracy-7 values of the proposed academic English content optimization model were 87.8, 89.2, 0.05, 0.69, and 97.6. The proposed model has higher accuracy and efficiency on multiple datasets, which can effectively optimize various types of English grammar errors, providing new solutions for content optimization in academic English writing.</div></div>","PeriodicalId":34469,"journal":{"name":"Computers and Education Artificial Intelligence","volume":"9 ","pages":"Article 100492"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145415150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Engagements with GPT responses and learner prompts in ChatGPT-based learning of English argumentative writing logic and their impacts","authors":"Ruofei Zhang ,&nbsp;Di Zou ,&nbsp;Haoran Xie ,&nbsp;Fu Lee Wang","doi":"10.1016/j.caeai.2025.100489","DOIUrl":"10.1016/j.caeai.2025.100489","url":null,"abstract":"<div><div>ChatGPT can be defined as a chatbot powered by OpenAI's GPT language models, which has shown promise in improving English-as-a-foreign-language (EFL) writing knowledge and skills. However, its application to developing EFL argumentative writing logic remains largely unexplored, despite the importance of this area. Moreover, existing studies have highlighted deep learner engagement with ChatGPT-based learning but have not examined how engagement varies between two key components of this learning method: GPT responses (GPT's messages to learners) and learner prompts (learners' messages to GPT). To better understand the mechanisms and efficacy of ChatGPT-based learning for EFL argumentative writing, we developed a discipline-specific GPT-4-powered chatbot for learning English argumentative writing logic. Forty-two Chinese university students used the tool for 45–75 min. Learner engagement in GPT responses and learner prompts was assessed via eye movements on corresponding interface areas of ChatGPT recorded by a Tobii eye-tracker. Their learning outcomes were assessed via pre-post-delayed tests and pre-post writing tasks. Semi-structured interviews were also administered. Our findings revealed that learners engaged with GPT responses frequently but for short durations, and with learner prompts infrequently but for longer durations. Engagement in GPT responses appears to facilitate logic knowledge development, whereas engagement in learner prompts may be associated with challenges in developing writing logic. Based on the results, we explored the factors influencing the patterns and impacts of learner engagement with ChatGPT-based learning of English argumentative writing logic and offered implications for future implementation of this learning method.</div></div>","PeriodicalId":34469,"journal":{"name":"Computers and Education Artificial Intelligence","volume":"9 ","pages":"Article 100489"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145415152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Designing a generative AI enabled learning environment for mathematics word problem solving in primary schools: Learning performance, attitudes and interaction","authors":"Jingxi Liu ,&nbsp;Daner Sun ,&nbsp;Jin Sun ,&nbsp;Jingyun Wang ,&nbsp;Philip Leung Ho Yu","doi":"10.1016/j.caeai.2025.100438","DOIUrl":"10.1016/j.caeai.2025.100438","url":null,"abstract":"<div><div>Mathematics word problem solving is a critical component of elementary education, yet many students encounter persistent difficulties in this area due to the combined cognitive demands of linguistic comprehension and mathematical reasoning. While previous studies have explored various pedagogical strategies to enhance problem-solving skills, the integration of generative artificial intelligence (GenAI) in this domain remains underexplored. This study introduces the ChatGPT-supported Mathematics Problem-Solving System (ChatGPT-MPS), a GenAI-enabled learning environment designed to support primary students in developing problem-solving strategies and deepening conceptual understanding. To evaluate its effectiveness, a quasi-experimental design was employed involving 104 fifth-grade students, assigned to an experimental group (using ChatGPT-MPS) and a control group (traditional instruction). Both groups completed a pre- and post-tests of MPS and interests scale to evaluate their word problem-solving proficiency and learning interests. Quantitively data analysis and its results showed that the experimental group exhibited significantly greater improvements in post-test performance compared to the control group. In addition, student feedback revealed increased interest, perceived value, and motivation when engaging with the ChatGPT-MPS learning environment. These findings provide empirical support for the use of GenAI in mathematics education and demonstrate the potential of ChatGPT-MPS to enhance students' mathematical thinking and engagement in problem-solving tasks. The study contributes to the growing body of research on AI-driven personalized learning in primary education, offering insights into the design and implementation of effective GenAI-enabled learning environments.</div></div>","PeriodicalId":34469,"journal":{"name":"Computers and Education Artificial Intelligence","volume":"9 ","pages":"Article 100438"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144322508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identifying active ingredients and uptake patterns in the implementation of an AI-based writing support tool: Insights from a randomized controlled trial","authors":"Yue Huang ,&nbsp;Corey Palermo ,&nbsp;Joshua Wilson","doi":"10.1016/j.caeai.2025.100479","DOIUrl":"10.1016/j.caeai.2025.100479","url":null,"abstract":"<div><div>While AI-based educational technologies offer many features designed to support learning, it remains unclear which specific components actually contribute to improved student outcomes. Identifying these <em>active ingredients</em>—the subset of an intervention's core components that are demonstrably associated with learning gains—is essential. Yet, evidence from experimental studies remains limited. To address this gap, we conducted a secondary analysis of data from the treatment group of a randomized controlled trial involving 902 middle school students across three U.S. school districts who used <em>MI Write</em>, an automated writing evaluation (AWE) system. Drawing on implementation science, we examined which core components of MI Write, and which uptake patterns, were most strongly associated with student outcomes. Hierarchical linear modeling identified the amount of writing and revisions completed within MI Write as active ingredients, as both were significantly associated with improvements in students' argumentative writing performance. However, uptake of these active ingredients varied across districts, with greater engagement correlating with improved outcomes in one district. Student-level factors, such as baseline writing performance, perceptions of teacher caring, and demographic characteristics, influenced writing task completion and revisions, while teacher-level factors primarily explained variability in writing task completion. These findings emphasize the importance of reaching specific uptake benchmarks in writing and revision to optimize AWE's impact. Furthermore, fostering positive classroom climates may enhance engagement, particularly among underserved student populations. This study advances the understanding of AWE's active ingredients and contextual dependencies, offering actionable insights for improving the design, implementation, and scalability of AI-based writing support tools.</div></div>","PeriodicalId":34469,"journal":{"name":"Computers and Education Artificial Intelligence","volume":"9 ","pages":"Article 100479"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}