CoChat
Sign Up
Cited by 290English Language Learning and TeachingEFL/ESL Teaching and LearningNatural Language Processing Techniques

Grammarly as AI-powered English Writing Assistant: Students' Alternative for Writing English

Open access
Fitria, Tira Nur·2021·Metathesis: Journal of English Language, Literature, and Teaching
DOI 10.31002/metathesis.v5i1.3519
Open this paper in CoChat — free accountOpen PDF

Abstract

The presence of ‘Grammarly’ as one of the online grammar checkers as the impact of technology development. This paper aims to reveal an overview of ‘Grammarly’ as an AI-powered English Writing Assistant for EFL students in Writing English. This research applies descriptive qualitative research. Based on the analysis, using Grammarly software shows the performance increased. Before using Grammarly, the performance of the test score is 34 out of 100. After using Grammarly, the performance text score is 77 out of 100. This score shows the quality of writing in this text increased. The performance can be increased based on Grammarly's suggestions in a Premium account. The researcher recommends the students to use Grammarly. Grammarly is a web tool to perform grammar checks well, starting from the spelling of words, sentence structure to standard grammar. Grammarly is free, so it is recommended for students who want to check various documents or articles in English. Grammarly helps check the grammatical rule, the spelling rule in English structure, also correct errors in writing such as punctuation and capitalization. Grammarly runs on an Artificial Intelligence (AI) system, which is built to analyze English sentences relying on a set of rules. Grammarly takes context when showing corrections or suggestions, and inform the students quickly but still precisely. For accuracy, two service options available both free and paid features. Of course, the Grammarly free version still has limitations and in-service features, unlike the paid version (premium) which has full advantages and benefits, many features, and complete.

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 · 10.31002/metathesis.v5i1.3519

Cites

23 of 24 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?

  • Digital Writing Assistants (DWAs) such as Grammarly, WordTune and Perusall use Artificial Intelligence (AI) to improve student writing.

    “Digital Writing Assistants (DWAs) such as Grammarly, WordTune and Perusall, use Artificial Intelligence (AI) to improve student writing (Fitria, 2021)”

    From Academic Integrity considerations of AI Large Language Models in the post-pandemic era: ChatGPT and beyond (2023) · cites this paper as Fitria, 2021

    The Abstract (page not specified) describes Grammarly as an AI-powered writing assistant and reports improved writing performance after its use. The paper supports that part of the claim, but the passages found for WordTune and Perusall do not address either tool, so it does not substantiate the claim about all three. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

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

Research works printed but not linked: 6

  1. Dewi, N. A. (2019, July 10). The Effectiveness of Grammarly Checker Toward Student's Writing Quality of English Departement Students At IAIN Tulungagung [Skripsi]. IAIN Tulungagung. https://doi.org/10/CHAPTER%20I.pdf
  2. Fadhilah, U. (2018). Effectiveness of Grammarly Application for Writing English Abstract. 8(12), 4.
  3. Fitria, T. N. (2018). Error analysis found in students' writing composition of simple future tense. Available at SSRN 3527851.
  4. Gitsaki, C., & Coombe, C. (2016). Current Issues in Language Evaluation, Assessment and Testing: Research and Practice. Cambridge Scholars Publishing.
  5. LornaMarie. (2018). How to Write a Good Dissertation A guide for University Undergraduate Students. Lulu.com.
  6. Smith, F. (2013). Writing and the Writer. Routledge.

Cited by

Sorted by citations

Related

Authors
Fitria, T. N.
Affiliations
Institut Teknologi Bisnis AAS Indonesia (ID)
Corresponding author
Fitria, Tira Nur
ORCID
Fitria, Tira Nur
Venue
Metathesis: Journal of English Language, Literature, and Teaching
Publisher
Universitas Tidar
Published
2021-05-18
Volume
5
Issue
1
Pages
65
ISSN
  • 2580-2712 (ISSN-L)
  • 2580-2720
DOI
10.31002/metathesis.v5i1.3519
OpenAlex
W3163701888
Cited by
221
References
23
Citations by year
2026: 19 · 2025: 73 · 2024: 59 · 2023: 58 · 2022: 9 · 2021: 3
FWCI
29.16
Type
journal article
Language
en
Open access
Licence
Locations
Metathesis Journal of English Language Literature and Teaching (publishedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Information Systems › English Language Learning and Teaching
  • Social Sciences › Arts and Humanities › Language and Linguistics › EFL/ESL Teaching and Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
Grammarly, EFL writing, English as a foreign language, grammar checking, spelling correction, punctuation correction, writing performance

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