<![CDATA[This study aims to develop and evaluate an AI-assisted project-based instructional model for teaching descriptive text writing and to examine its feasibility and effectiveness in improving students’ writing performance. Employing a mixed-methods Research and Development (R&D) design based on the ADDIE framework, the study involved 36 tenth-grade students and one English teacher. Data were collected through questionnaires, interviews, expert validation sheets, observations, and pretest and posttest assessments. Quantitative data were analyzed using descriptive statistics and paired-samples t-tests, while qualitative data were examined through thematic analysis. The results indicated improvements in students’ writing performance across all assessed components, with the overall mean score increasing from M = 12.85 on the pretest to M = 15.68 on the posttest. The findings also showed high levels of student participation and positive evaluations of the instructional materials in terms of practicality and suitability. The structured use of ChatGPT, Grammarly, QuillBot, DeepL, Hemingway Editor, Wordtune, and Scribbr AI Proofreader provided scaffolding within the project-based framework and supported students’ writing development while remaining feasible for classroom implementation. This study contributes to the growing body of literature on technology-enhanced language learning by providing empirical evidence of an instructional model that integrates AI tools with sound pedagogical design and offers practical guidance for EFL educators.]]>
Copyrights © 2026
