Improving Academic Writing Proficiency for EFL Students: Leveraging ChatGPT Using Data-Driven Learning Principles

This research examines a learner-centered approach to using ChatGPT based on data driven learning principles in essay writing instruction. A quasi-experimental study was adopted with three groups comprising 92 international students enrolled in a pre-sessional foundation writing course at a Thai university. The control group followed the usual textbook-centric curriculum. Experimental Group 1 was taught to compare their own writing with paper-based sample IELTS essays, and Experimental Group 2 used ChatGPT (GPT 3.5) generated paraphrases of their own compositions and guided worksheets for students to compare and analyze. Within group and between group posttest analysis of student compositions found that the participants that used ChatGPT significantly outperformed the other groups (control group posttest writing score x̄ = 74.03%; Experimental Group 1 writing posttest x̄ = 73.68%; Experimental Group 2 writing posttest score x̄ = 94.3% 0.001 at 0.05). A follow-up questionnaire and interview revealed that the participants in Experimental Group 2 appreciated using AI in this way and developed an increased level of confidence. The study concludes that the adapted use of AI powered chatbots is effective for developing short essay writing skills.

Authors

Institutions

Publication Details

Journal
rEFLections
Published
2025-04-25
DOI
https://doi.org/10.61508/refl.v32i1.280410
Primary Topic
Online Learning and Analytics
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Improving Academic Writing Proficiency for EFL Students: Leveraging ChatGPT Using Data-Driven Learning Principles

Harald Kraus, Edward Devere Bacon
rEFLections
Online Learning and Analytics
article

Improving Academic Writing Proficiency for EFL Students: Leveraging ChatGPT Using Data-Driven Learning Principles

Harald Kraus, Edward Devere Bacon
article en

Abstract

This research examines a learner-centered approach to using ChatGPT based on data driven learning principles in essay writing instruction. A quasi-experimental study was adopted with three groups comprising 92 international students enrolled in a pre-sessional foundation writing course at a Thai university. The control group followed the usual textbook-centric curriculum. Experimental Group 1 was taught to compare their own writing with paper-based sample IELTS essays, and Experimental Group 2 used ChatGPT (GPT 3.5) generated paraphrases of their own compositions and guided worksheets for students to compare and analyze. Within group and between group posttest analysis of student compositions found that the participants that used ChatGPT significantly outperformed the other groups (control group posttest writing score x̄ = 74.03%; Experimental Group 1 writing posttest x̄ = 73.68%; Experimental Group 2 writing posttest score x̄ = 94.3% 0.001 at 0.05). A follow-up questionnaire and interview revealed that the participants in Experimental Group 2 appreciated using AI in this way and developed an increased level of confidence. The study concludes that the adapted use of AI powered chatbots is effective for developing short essay writing skills.

rEFLectionsVol. 32(1)
Thammasat University (TH)
Openalex Percentile: Top 92%
Online Learning and Analytics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Improving Academic Writing Proficiency for EFL Students: Leveraging ChatGPT Using Data-Driven Learning Principles — Harald Kraus, Edward Devere Bacon · rEFLections (2025) | TGRS Research Map | TGRS