Automated writing evaluation use in second language classrooms: A research synthesis
Open accessAbstract
Traditionally used solely for assessment purposes, automated writing evaluation technologies have increased their popularity as an aid in the second language (L2) writing classrooms, especially in the last decade. In addition to the feedback capabilities of AWE and its effect on L2 writing quality, an increasing number of naturalistic, classroom-based studies have demonstrated that L2 students’ engagement with these systems is complex and multi-layered, requiring an in-depth understanding. In this regard, a critical interpretative synthesis of existing literature on student engagement with AWE in L2 classrooms is warranted. Adopting grounded theory (Glaser & Strauss, 1967) as the guiding methodology, this study surveys and synthesizes the findings of 40 focal studies, published primarily between 2013 and 2021 in the context of second and foreign language. The prominent emergent themes that this synthesis yielded are a) impact of AWE on L2 students’ writing practices, (b) impact of individual and contextual factors on students’ AWE engagement, (c) impact of AWE on teacher feedback in L2 writing classrooms, and (d) limitations elicited in AWE classroom research. Based on this synthesis, the study provides a possible research agenda and suggests practical implications for AWE.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Revision traces reveal learners' attention allocation and cognitive processing.
“Writing process research emphasizes that revision traces reveal learners' attention allocation and cognitive processing, especially because keystroke records, timestamps, and version comparison can capture revision frequency, pause duration, and repeated modification points [5].”
From Semantic Response Mechanisms of L2 Writing Revision Behavior under Generative AI Feedback (2026) · cites this paper as [5]
Cites
Student engagement with teacher and automated feedback on L2 writing
Zhang, Z. (., & Hyland, K. (2018) · Assessing Writing · doi:10.1016/j.asw.2018.02.004 · Cited by 546 · see citing works
Koltovskaia, S. (2020) · Assessing Writing · doi:10.1016/j.asw.2020.100450 · Cited by 447 · see citing works
A framework for evaluation and use of automated scoring
Williamson, D. M., Xi, X., & Breyer, F. J. (2012) · Educational Measurement: Issues and Practice · doi:10.1111/j.1745-3992.2011.00223.x · Cited by 430 · see citing works
Warschauer, M., Tseng, W., Yim, S., Webster, T., Jacob, S., Du, Q., & Tate, T. (2023) · doi:10.2139/ssrn.4404380 · Cited by 425 · see citing works
Link, S., Mehrzad, M., & Rahimi, M. (2022) · Computer Assisted Language Learning · doi:10.1080/09588221.2020.1743323 · Cited by 275 · see citing works
Barrot, J. S. (2023) · Computer Assisted Language Learning · doi:10.1080/09588221.2021.1936071 · Cited by 248 · see citing works
Automated written corrective feedback: how well can students make use of it?
Ranalli, J. (2018) · Computer Assisted Language Learning · doi:10.1080/09588221.2018.1428994 · Cited by 228 · cited 3× · see citing works
“Despite calls for research (e.g., Chen & Cheng, 2008; Li et al., 2014; Link et al., 2014; Ranalli, 2018; Rimrott & Heift, 2008; Stevenson & Phakiti, 2019; Warschauer, 2010), existing literature has not fully addressed how AWE systems are implemented in L2 writing classrooms.”
L2 student engagement with automated feedback on writing: Potential for learning and issues of trust
Ranalli, J. (2021) · Journal of Second Language Writing · doi:10.1016/j.jslw.2021.100816 · Cited by 184 · cited 4× · see citing works
“Lastly, the synthesis revealed that certain variables, such as social and personal factors influencing AWE engagement (e.g., Bru-dermann et al., 2021) and the effect of writing task or text genre on AWE engagement (e.g., Ranalli, 2021), were not systematically considered in the reviewed studies.”
InfluentialAI-writing tools in education: If you can’t beat them, join them
Tseng, W., & Warschauer, M. (2023) · Journal of China Computer-Assisted Language Learning · doi:10.1515/jccall-2023-0008 · Cited by 119 · cited 3× · see citing works
“The emergence of AI tools such as ChatGPT has led to reflection on the impact of AI in education, evoking both optimism and concerns, particularly in L2 writing instruction (Tseng & Warschauer, 2023).”
Flagged first, then by citations
Cited by
Sorted by citations
Shi, H., Chai, C. S., Zhou, S., & Aubrey, S. (2026) · Computer Assisted Language Learning · doi:10.1080/09588221.2025.2454541 · Cited by 109 · see citing works
Semantic Response Mechanisms of L2 Writing Revision Behavior under Generative AI Feedback
Shi, Y. (2026) · Applied and Computational Engineering · doi:10.54254/2755-2721/2026.36194
- Authors
- Karatay, Y., & Karatay, L.
- Affiliations
- Cambridge University Press (GB)
- Iowa State University (US)
- Corresponding author
- Karatay, Yasin
- Venue
- System
- Publisher
- Elsevier BV
- Published
- 2024-07
- Volume
- 123
- Pages
- 103332
- ISSN
- 0346-251X (ISSN-L)
- OpenAlex
- W4396687678
- Cited by
- 49
- References
- 9
- Citations by year
- 2026: 35 · 2025: 13 · 2024: 1
- FWCI
- 77.07
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- System (publishedVersion, cc-by-nc-nd)
- Apollo (University of Cambridge) (submittedVersion, cc-by-nc-nd)
- 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
- automated writing evaluation, second language writing, writing feedback, teacher feedback, writing practices, foreign language writing, classroom technology use
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