Original Research
AI-Driven Writing Assistance in a Flipped Classroom Model: A Pedagogical Approach to Enhancing Academic Writing and Critical Thinking in EFL Learners
- Abstract
- Full text
- Metrics
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.
Page 1 of
Download Count : 10
Visit Count : 32
Keywords
Academic Writing; Critical Thinking; AI-Driven Writing Assistance; Flipped Classroom Model
Author(s) Information
Publisher’s Note
The claims, arguments, and counter-arguments made in this article are exclusively those of the contributing authors. Hence, they do not necessarily represent the viewpoints of the authors’ affiliated institutions, or EUROKD as the publisher, the editors and the reviewers of the article.
Acknowledgements
The authors gratefully acknowledge the institutional support provided by Universitas Muhammadiyah Sumatera Utara and sincerely thank all the students who participated in this study for their valuable time and contributions.
Funding
This work was financially supported by Universitas Muhammadiyah Sumatera Utara, Indonesia under Grant No. 151/II.3-AU/UMSU-LP2M/C/2023.
CRediT Authorship Contribution Statement
Pirman Ginting: Conceptualization, Investigation, Methodology, Project Administration, Supervision, Writing–Original Draft
Yenni Hasnah: Data Curation, Formal Analysis, Investigation, Writing–Review & Editing
Adib Jasni Kharisma: Formal Analysis, Investigation, Visualization, Writing–Review & Editing
Dodi Mulyadi: Validation, Writing–Review & Editing
Generative AI Use Disclosure Statement
The authors used Grammarly and GPT to improve the manuscript's proofreading and language polish. The accuracy and integrity of the final manuscript were examined and revised thoroughly.
Ethics Declarations
Prior to data collection, ethical approval for this study was granted by the appropriate institutional authority. Written informed consent was secured from all participants, ensuring that participation was entirely voluntary and that participants could withdraw from the study at any time without academic or personal repercussions. Participants were fully informed about the objectives of the study, procedures, and their rights before giving consent. To ensure the confidentiality, all data were used solely for research purposes and remained strictly confidential.
Consent for Publication
Informed consent was obtained from the participants for the use and publication of their research data. No personally identifiable information is included in this article.
Competing Interests
The authors declare that they have no competing interests.
Data Availability
The data supporting the findings of this study comprise students’ writing and interview data. Owing to ethical consideration and participant confidentiality, these data are not publicly accessible. Data may be obtained from the author upon reasonable request.