AI-Empowered English Writing Learning: A Review and Reflection Based on a Teaching Practice

Artificial Intelligence as a Source of Feedback in L2 Writing Classrooms: Best Practices and Pedagogical Strategies

Writing proficiency is a key element of academic success for English as a Second Language (ESL) and English as a Foreign Language (EFL) students, but it presents ongoing challenges that demand innovative pedagogical solutions. The rapid advancement of Artificial Intelligence (AI) has created unprecedented opportunities for enhancing writing instruction through automated feedback systems. This article brings together theoretical frameworks, empirical research, and pedagogical best practices to examine how AI tools can serve as effective sources of feedback in second language (L2) writing classrooms. Drawing on cognitive, sociocultural, and contrastive rhetoric theories of writing, the article explores the nature of L2 writing difficulties, the critical role of feedback in writing development, and the strengths and limitations of AI-generated feedback. A systematic review of recent empirical studies reveals that AI-powered feedback systems are consistently effective in enhancing micro-level writing skills, particularly grammatical accuracy and lexical diversity. However, limitations remain in addressing macro-level writing concerns, and hybrid feedback models that combine AI with teacher input appear to yield the most comprehensive benefits. The article presents evidence-based recommendations for teachers and students, including strategies for scaffolding AI use, developing feedback literacy, designing effective prompts, and integrating AI feedback with teacher and peer feedback. It also addresses ethical considerations and practical concerns to ensure effective use of AI tools. It concludes with implications for pedagogy and directions for future research. This article argues that the thoughtful integration of AI feedback with teacher feedback, grounded in pedagogical principles and human judgment, can significantly enhance L2 writing instruction.

AI-Mediated Writing Instruction in Higher Education: A Systematic Review of Empirical Evidence

It is suggested that AI can enhance drafting, revision, and feedback processes, improving coherence, metacognition, and writing confidence, however, these benefits are accompanied by persistent concerns regarding ethical ambiguity, inconsistent policy guidance, and insufficient faculty training.

Improving Writing Skill of Non-English Department Students Using AI

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.

Project-Based Learning as an Alternative Approach to Enhancing EFL Students' Grammar-Based Writing

Writing is one of the most challenging skills for English as a Foreign Language (EFL) learners because it requires grammatical accuracy, adequate vocabulary, and the ability to organize ideas coherently. Preliminary observations in a public junior secondary school in Central Sulawesi, Indonesia, revealed that many ninth-grade students experienced difficulties in constructing sentences using the present and past continuous tenses, resulting in frequent grammatical errors and low writing achievement. This study aimed to improve students’ writing skills through the implementation of Project-Based Learning (PjBL), with the Jigsaw technique integrated in the second cycle to strengthen collaborative learning. The study employed Classroom Action Research (CAR) based on the Kemmis and McTaggart model and involved 25 ninth-grade students. Data were collected through writing tests, classroom observations, field notes, and documentation and analyzed using descriptive quantitative and qualitative methods. The findings showed that the implementation of PjBL, supported by Jigsaw in Cycle II, improved students’ grammatical accuracy, sentence construction, classroom participation, and learning engagement. The average student score increased from 63.20 in the pre-cycle to 73.67 in Cycle I and reached 84.00 in Cycle II. In Cycle I, 18 of the 25 students (72%) achieved the minimum mastery criterion, while seven students (28%) did not. Following the instructional revision and integration of Jigsaw in Cycle II, all students (100%) successfully met the minimum mastery criterion. Students also demonstrated fewer grammatical errors, particularly in the use of auxiliary verbs (to be), -ing verb forms, and continuous tense structures. In addition, students became more actively involved in peer discussions, more confident in sharing their understanding, and more engaged in collaborative writing activities. These findings suggest that PjBL, when complemented by the Jigsaw technique, can provide a meaningful and collaborative learning environment for enhancing grammar-based writing skills and promoting active engagement in EFL classrooms.

Rewriting the Curriculum: Integrating AI Prompt Engineering into EFL Writing Instruction

The Impact of AI-Assisted Writing Tools on the Quality of English for Specific Purposes Writing and Learner Strategies: An Empirical Study of Blended Learning

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.