AI-Driven Writing Assistance in a Flipped Classroom Model: A Pedagogical Approach to Enhancing Academic Writing and Critical Thinking in EFL Learners

Abstract

This study explores the AI-based flipped model to enhance academic writing proficiency and critical thinking among EFL learners. Employing a mixed method through a one-group pretest-posttest design, the study combined quantitative assessment using the IELTS Academic Writing Task 2 rubric and Facione's Critical Thinking framework with qualitative data drawn from open-ended post-intervention questionnaires. Descriptive statistics showed that the students' writing skills advanced from a pre-test mean of 4.75 to a post-test mean of 6.17, which stand for an average increase of 1.42 points (29.8%). Meanwhile, critical thinking scores increased from a mean of 42.87 to 68.14 with an average increase of 25.27 points (58.9%). The Wilcoxon signed-rank test further confirmed substantial rises for both outcomes (writing: Z = -5.163, p < .001; critical thinking: Z= -5.107), with the effect sizes (writing: r = .873, rrb = 1.000; critical thinking: r = .851, rrb = .976). Qualitative findings corroborated this trend, denoting significant improvements in writing organization, argument construction, evidence-based argumentation, and source evaluation. However, challenges such as over-reliance on AI output and difficulties related to adapting to self-paced learning were also observed. Implications for pedagogical design were highlighted, implying that AI-integrated flipped learning supported the teaching of writing and critical thinking skills.