CoChat
Sign Up
Cited by 45EFL/ESL Teaching and LearningEnglish Language Learning and TeachingSecond Language Acquisition and Learning

Investigating EFL Students' Writing Skills Through Artificial Intelligence: Wordtune Application as a Tool

Open access
Mahmud, Fawaz Al·2023·Journal of Language Teaching and Research
DOI 10.17507/jltr.1405.28
Open this paper in CoChat — free accountOpen PDF

Abstract

Artificial intelligence (AI) powered writing technologies such as Wordtune and Grammarly are increasingly penetrating the L2 writing domain. Despite the growing significance of such digital tools, few studies have explored how AI-driven applications impact Saudi English as a Foreign Language (EFL) writing. The current study aimed to fill this gap by investigating whether and to what extent Wordtune facilitates Saudi students' writing. The participants were divided into two male and two female groups using a mixed-method design. For both male and female samples, one group was identified as the control group, whereas the other one was identified as the experimental group. Quantitative data were collected using pretests and post-tests and analyzed using SPSS. Qualitative data were derived from students' writing samples and assessed by two human raters. The results showed that using Wordtune, students in the experimental group surpassed those in the control group. Quantitative findings demonstrated that using Wordtune, the experimental group upgraded their writing and outperformed the control group in the final writing exam. Qualitative findings indicate that using Wordtune, the experimental group made modest writing gains at the lexical and syntactic levels. While lexical gains included more concrete nouns, vivid adjectives, and precise verbs, sentence-structure gains included the increasing presence of complex phrases and complex and compound sentences. Finally, the impact of Wordtune on writing quality was the same for both male and female participants.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.17507/jltr.1405.28

Cites

37 of 37 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Constructivist theory treats learning as an active, iterative process in which students build knowledge through cycles of feedback, revision, and reflection.

    “Constructivist theory treats learning as an active, iterative process in which students build knowledge through cycles of feedback, revision, and reflection—processes that align directly with AI-supported writing workflows (Al-Mahmud, 2023; Liu et al., 2025).”

    From From tool to scaffold: structured human–AI collaboration and its effects on academic writing and digital critical thinking among Saudi EFL learners (2026) · cites this paper as Al-Mahmud, 2023

    The Research Implication and Recommendation section (page unavailable) describes students using Wordtune feedback and rewrites to identify problems and think about their writing. That supports the claimed alignment with AI-supported writing workflows, but the paper does not present these processes as a tenet of constructivist theory. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • The experimental group's substantially larger writing gains-from virtually identical pretest baselines-corroborate evidence that AI tools improve EFL writing most effectively when embedded within explicit pedagogical frameworks.

    “The experimental group’s substantially larger writing gains—from virtually identical pretest baselines—corroborate evidence that AI tools improve EFL writing most effectively when embedded within explicit pedagogical frameworks (Al-Mahmud, 2023; Abduljawad, 2024; Jamshed et al., 2024).”

    From From tool to scaffold: structured human–AI collaboration and its effects on academic writing and digital critical thinking among Saudi EFL learners (2026) · cites this paper as Al-Mahmud, 2023

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 38 references couldn’t be matched to a known paper.

Research works printed but not linked: 3

  1. Azah, D. N. (2019). The effectiveness of Grammarly checker toward student's writing quality of the fourth semester of English Department at IAIN Tulungagung [Unpublished undergraduate thesis]. IAIN Tulungagung.
  2. Lin, C. J., & Mubarok, H. (2021). Learning analytics for investigating the mind map-guided AI chatbot approach in an EFL flipped speaking classroom. Educational Technology & Society, 24(4), 16-35. https://doi.org/10.30191/ETS.202110_24(4).0002 · DOI
  3. Mahammoda, S. A. (2016). Factors affecting the quality of undergraduate research work in Bahir Dar University, Ethiopia. International Journal of Innovative Research and Development, 5(12), 23-27. Retrieved from https://www.internationaljournalcorner.com/index.php/ijird_ojs/article/view/136671/95794

Cited by

Sorted by citations

Related

Authors
Mahmud, F. A.
Venue
Journal of Language Teaching and Research
Publisher
Academy Publication
Published
2023-09-01
Volume
14
Issue
5
Pages
1395-1404
ISSN
  • 1798-4769 (ISSN-L)
  • 2053-0684
DOI
10.17507/jltr.1405.28
OpenAlex
W4386371413
Cited by
45
References
38
Citations by year
2026: 15 · 2025: 23 · 2024: 5 · 2023: 2
FWCI
50.60
Type
journal article
Language
en
Open access
Locations
Journal of Language Teaching and Research (publishedVersion)
Funders
University of Jeddah
Topics
  • Social Sciences › Arts and Humanities › Language and Linguistics › EFL/ESL Teaching and Learning
  • Physical Sciences › Computer Science › Information Systems › English Language Learning and Teaching
  • Social Sciences › Psychology › Developmental and Educational Psychology › Second Language Acquisition and Learning
Keywords
AI-assisted writing, EFL writing, Saudi EFL learners, writing quality, lexical diversity, syntactic complexity, gender differences

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review