Jul 2026· Journal of English language teaching and applied linguistics· 0 citations· 51 references
TL;DR
Results suggest that AI-based feedback tools represent a powerful and scalable approach to enhancing English writing skills, and blended learning environments yielded stronger effects than traditional classroom settings, highlighting the importance of flexible and technology-supported contexts.
Abstract
Artificial intelligence has increasingly transformed educational practices, particularly in writing instruction. Among these innovations, AI-based feedback tools have appeared as favourable solutions for giving personalized, immediate, and accessible support to learners. This study aims to assess the effect of AI-based feedback on English writing performance, filling research gaps regarding the impact of English language proficiency level, duration of intervention, and implementation setting on the effectiveness of AI-based feedback tools in improving students’ English language writing performance. A systematic review and meta-analysis were utilized to examine 24 empirical studies published from January 2022 to March 2026 across five databases (including EBSCO, ProQuest, ERIC, Web of Science, and Wiley Online Library). The results indicated that AI-based feedback tools had a large overall effect size (Hedges' g = 1.298, p < 0.001) on students’ writing performance. Moreover, moderator analyses revealed that learners with intermediate proficiency benefited more substantially compared to advanced learners, suggesting that AI feedback is particularly effective for developing writers. In terms of implementation settings, blended learning environments yielded stronger effects than traditional classroom settings, highlighting the importance of flexible and technology-supported contexts. Although the duration of intervention did not significantly moderate the results, consistently strong effects were observed across the three periods of intervention: short, medium, and long-term. These findings suggest that AI-based feedback tools represent a powerful and scalable approach to enhancing English writing skills.
This study aims to explore the application effects of AI-assisted writing tools in English for Specific Purposes (ESP) writing instruction and their impact on learners' writing strategies. Using a blended learning empirical research design, this study recruited 128 students majoring in economics and management at a college. Through a 16-week teaching experiment, by combining writing tests, questionnaires, and in-depth interviews, this study systematically explored the specific mechanisms by which AI-assisted tools affect the quality of ESP writing. The results show that AI-assisted writing tools have the potential to improve learners' writing performance in five dimensions: grammatical accuracy, lexical richness, register appropriateness, content completeness, and structural logic. Simultaneously, these tools encourage learners to develop three adaptive writing strategies: human-computer collaboration, process monitoring, and metacognitive regulation. Interestingly, there were significant intergroup differences in tool use and strategy selection based on learners' English proficiency levels. This study provides empirical evidence and practical insights for AI-assisted ESP writing instruction in blended learning environments.
The integration of artificial intelligence (AI) technology into education has become increasingly important in supporting the writing proficiency of non-English major students in English for Specific Purposes (ESP) courses. This study investigates the effectiveness of ChatGPT in improving the clarity, coherence, and grammatical accuracy of students’ writing drafts. Employing a quasi-experimental design, the study examined differences in learning outcomes between a ChatGPT-assisted class (experimental group) and a traditionally taught class (control group). Data were collected through writing draft assessments, participant surveys, and interviews. The findings indicate that the experimental group demonstrated a significant improvement in writing performance, particularly in organizing and presenting ideas clearly and coherently. Furthermore, the personalized guidance provided by ChatGPT contributed to students’ learning autonomy and self-confidence. These findings highlight the potential of ChatGPT as a supportive tool for language learning while emphasizing the continued role of lecturers in validating recommendations generated by AI systems. Future research is encouraged to explore AI-assisted writing in more specialized disciplinary contexts and to investigate its long-term effects on students’ learning retention and writing development.
Rachmat Ari Wibowo· English Language and Educati...· 0 citations
This study systematically reviews the current evidence on AI in academic writing using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines and contributes a comprehensive synthesis of current research by integrating pedagogical, assessment, and human perspectives through the TPACK, assessment, and Technology Acceptance Model frameworks.
Saidatul Akmar Zainal Abidin, Noor Hanim binti Rahmat· International journal of res...· 0 citations
Writing skills are essential in English as a Foreign Language (EFL) learning, yet many high school students experience difficulties in generating ideas, organizing texts, and revising their writing effectively. Integrating Artificial Intelligence (AI) Writing Assistants with Collaborative Online Writing (COW) offers a promising approach to enhancing writing performance through collaborative and process-oriented learning. This study investigates the effectiveness of AI-assisted COW in improving students' English writing skills, with self-efficacy and digital literacy examined as moderating variables. A quantitative approach employing a quasi-experimental non-equivalent control group design was adopted. Participants consisted of eleventh-grade public high school students assigned to experimental and control groups. Data were collected through pre- and post-writing tests, self-efficacy questionnaires, and digital literacy questionnaires, then analyzed using inferential statistics and moderation regression analysis. The results revealed that students receiving AI-assisted COW achieved significantly greater improvements in writing skills than those in the control group, with a substantial effect size. Moreover, self-efficacy and digital literacy significantly strengthened the positive relationship between AI-assisted COW and writing achievement, indicating that students with higher levels of both variables gained greater learning benefits. These findings demonstrate that integrating collaborative online writing with AI technology effectively enhances EFL students' writing skills while highlighting the importance of fostering self-efficacy and digital literacy to maximize learning outcomes.
Firlia Nurul Anisa, Mohammad Sofyan Adi Pranata· JURNAL ILMIAH GEMA PERENCANA· 0 citations
It is argued that the thoughtful integration of AI feedback with teacher feedback, grounded in pedagogical principles and human judgment, can significantly enhance L2 writing instruction.
O. Jamoom, Saaid Ali Omar· Comprehensive Journal of Sci...· 0 citations
Artificial intelligence (AI) is increasingly transforming mathematics education through adaptive tutoring systems, automated feedback, and AI-supported assessment tools. However, evidence regarding the effectiveness of these technologies remains dispersed across diverse contexts and study designs. This systematic review synthesised empirical research on the effectiveness of AI-based tutoring and assessment systems in mathematics education published between 2015 and 2025. Guided by the PRISMA framework, a comprehensive search was conducted in Scopus and Web of Science using database-specific search strings. After screening 1,749 records and assessing 76 full-text articles for eligibility, 12 studies met the inclusion criteria and were included in the final synthesis. Data were extracted using a structured framework and study quality was appraised using the Mixed Methods Appraisal Tool (MMAT). Due to heterogeneity in interventions, populations, and outcome measures, a narrative synthesis was employed. Findings indicate that AI-based tutoring systems and adaptive learning platforms generally support improvements in mathematics achievement, particularly among lower-performing learners, although effectiveness varies depending on implementation fidelity, learner characteristics, and instructional context. Studies focusing on generative AI tools such as ChatGPT primarily reported positive perceptions and increased engagement, but evidence of direct achievement gains remains limited. Overall, the evidence base demonstrates moderate methodological quality, with stronger conclusions drawn from experimental and quasi-experimental designs. The review highlights the potential of AI-based tutoring and assessment systems to enhance mathematics learning while emphasising the need for rigorous, large-scale experimental research and clearer reporting of intervention mechanisms.
Neo J. Molemane, Moeketsi Mosia, F. Egara· Discover Education· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
