Automated Writing Evaluation: The Accuracy of Grammarly's Feedback on Form

Automated Writing Evaluation (AWE) is gaining more and more presence, with Grammarly being a prominent example of this kind of software, which provides automated feedback on essay writing. While the Grammarly advertisement is full of praise regarding its ability to give meaningful feedback at variou...

Full description

Bibliographic Details
Main Authors: Marina Dodigovic, Artak Tovmasyan
Format: Article
Language:English
Published: Cranmore Publishing 2021-06-01
Series:International Journal of TESOL Studies
Subjects:
Online Access:https://www.tesolunion.org/attachments/files/2ODFJ8N2ZMBOGFJAMJBL0NZUXAODC09ODGY3NTIZ4NWVMFYWNJ2NWFL0YWEZAODCYBNJYWBYTNLFODE40MZY48NDI22LJGY2MJEYFNZI01LMQX.pdf
_version_ 1818980770392309760
author Marina Dodigovic
Artak Tovmasyan
author_facet Marina Dodigovic
Artak Tovmasyan
author_sort Marina Dodigovic
collection DOAJ
description Automated Writing Evaluation (AWE) is gaining more and more presence, with Grammarly being a prominent example of this kind of software, which provides automated feedback on essay writing. While the Grammarly advertisement is full of praise regarding its ability to give meaningful feedback at various levels, including grammar or form, plagiarism, vocabulary and style, there has been little third party research to support these claims. Since Grammarly’s vocabulary feedback accuracy has already been examined to some extent (Dodigovic, Mlynarski & Wei, 2016), this study was designed to evaluate the accuracy of Grammarly’s grammar checker feedback. It did so by investigating the reports generated by Grammarly as a response to a small corpus of EFL writing, compiled from essays written by Armenian undergraduate students. The results were compared with those of human raters. In addition to Grammarly’s error detection power, the study also investigated the kind of remediation that Grammarly suggested. The comparisons revealed that on detected errors of form, Grammarly mostly provides accurate feedback, with occasional inconsistencies. It was also found to provide mainly adequate remediation for the correctly detected errors of form. However, it also left a number of errors undetected, which led to the omission of remediation. The study concluded that, despite its considerable usefulness, when using Grammarly, English learners should avoid relying solely on its feedback.
first_indexed 2024-12-20T17:20:42Z
format Article
id doaj.art-73a5b2b8a302460180d9e17bab969ace
institution Directory Open Access Journal
issn 2632-6779
2633-6898
language English
last_indexed 2024-12-20T17:20:42Z
publishDate 2021-06-01
publisher Cranmore Publishing
record_format Article
series International Journal of TESOL Studies
spelling doaj.art-73a5b2b8a302460180d9e17bab969ace2022-12-21T19:31:50ZengCranmore PublishingInternational Journal of TESOL Studies2632-67792633-68982021-06-0132718710.46451/ijts.2021.06.06Automated Writing Evaluation: The Accuracy of Grammarly's Feedback on FormMarina Dodigovic0Artak Tovmasyan1University of La Rioja, SpainAmerican University of Armenia, ArmeniaAutomated Writing Evaluation (AWE) is gaining more and more presence, with Grammarly being a prominent example of this kind of software, which provides automated feedback on essay writing. While the Grammarly advertisement is full of praise regarding its ability to give meaningful feedback at various levels, including grammar or form, plagiarism, vocabulary and style, there has been little third party research to support these claims. Since Grammarly’s vocabulary feedback accuracy has already been examined to some extent (Dodigovic, Mlynarski & Wei, 2016), this study was designed to evaluate the accuracy of Grammarly’s grammar checker feedback. It did so by investigating the reports generated by Grammarly as a response to a small corpus of EFL writing, compiled from essays written by Armenian undergraduate students. The results were compared with those of human raters. In addition to Grammarly’s error detection power, the study also investigated the kind of remediation that Grammarly suggested. The comparisons revealed that on detected errors of form, Grammarly mostly provides accurate feedback, with occasional inconsistencies. It was also found to provide mainly adequate remediation for the correctly detected errors of form. However, it also left a number of errors undetected, which led to the omission of remediation. The study concluded that, despite its considerable usefulness, when using Grammarly, English learners should avoid relying solely on its feedback.https://www.tesolunion.org/attachments/files/2ODFJ8N2ZMBOGFJAMJBL0NZUXAODC09ODGY3NTIZ4NWVMFYWNJ2NWFL0YWEZAODCYBNJYWBYTNLFODE40MZY48NDI22LJGY2MJEYFNZI01LMQX.pdfawegrammar checkersgrammarlyicallai
spellingShingle Marina Dodigovic
Artak Tovmasyan
Automated Writing Evaluation: The Accuracy of Grammarly's Feedback on Form
International Journal of TESOL Studies
awe
grammar checkers
grammarly
icall
ai
title Automated Writing Evaluation: The Accuracy of Grammarly's Feedback on Form
title_full Automated Writing Evaluation: The Accuracy of Grammarly's Feedback on Form
title_fullStr Automated Writing Evaluation: The Accuracy of Grammarly's Feedback on Form
title_full_unstemmed Automated Writing Evaluation: The Accuracy of Grammarly's Feedback on Form
title_short Automated Writing Evaluation: The Accuracy of Grammarly's Feedback on Form
title_sort automated writing evaluation the accuracy of grammarly s feedback on form
topic awe
grammar checkers
grammarly
icall
ai
url https://www.tesolunion.org/attachments/files/2ODFJ8N2ZMBOGFJAMJBL0NZUXAODC09ODGY3NTIZ4NWVMFYWNJ2NWFL0YWEZAODCYBNJYWBYTNLFODE40MZY48NDI22LJGY2MJEYFNZI01LMQX.pdf
work_keys_str_mv AT marinadodigovic automatedwritingevaluationtheaccuracyofgrammarlysfeedbackonform
AT artaktovmasyan automatedwritingevaluationtheaccuracyofgrammarlysfeedbackonform