AI-Generated versus Teacher Feedback in EFL Argumentative Writing: A Comparative Synthesis of Empirical Evidence and a Research Protocol for Latin American Higher Education

Generative artificial intelligence has introduced new possibilities for providing individualized feedback on English as a Foreign Language (EFL) writing. Nevertheless, its effectiveness relative to teacher feedback remains contested, particularly for argumentative writing, which requires linguistic control, rhetorical organization, evidence evaluation, and critical reasoning. This article presents a structured comparative synthesis of published empirical research examining AI-generated, teacher-provided, and hybrid feedback in university EFL writing. The analysis draws on accessible scholarly publications released through October 2026 and considers writing performance, feedback characteristics, learner engagement, and revision practices. The reviewed evidence indicates that both AI-generated and teacher feedback can support writing improvement, although comparative outcomes vary across studies. Some investigations report no statistically significant differences between feedback conditions, whereas others identify advantages for particular AI-supported or hybrid approaches. Evidence also suggests that feedback effectiveness depends on proficiency, instructional mediation, task characteristics, and learners' capacity to interpret and implement comments. Findings from Ecuador caution against assuming that combining AI and teacher feedback necessarily improves grammatical accuracy. Drawing on sociocultural theory, formative assessment, feedback literacy, and self-regulated learning, the article proposes a comparative research protocol for future empirical validation at Universidad Estatal de Milagro. The synthesis supports a pedagogical approach that treats generative AI as a potential feedback resource rather than an automatic substitute for teacher judgment. Further controlled research is needed to establish whether improvements in revised essays transfer to independent argumentative writing.

Authors

Institutions

Publication Details

Journal
Revista JRG de Estudos Acadêmicos
Published
2026-11-13
DOI
https://doi.org/10.55892/jrg.v9i21.4109
Primary Topic
EFL/ESL Teaching and Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AI-Generated versus Teacher Feedback in EFL Argumentative Writing: A Comparative Synthesis of Empirical Evidence and a Research Protocol for Latin American Higher Education

Ketty Zoraida Vergara Mendoza, Mariana Marisol Briones Zambrano
3 links
Revista JRG de Estudos Acadêmicos
EFL/ESL Teaching and Learning
article

AI-Generated versus Teacher Feedback in EFL Argumentative Writing: A Comparative Synthesis of Empirical Evidence and a Research Protocol for Latin American Higher Education

Ketty Zoraida Vergara Mendoza, Mariana Marisol Briones Zambrano
article en

Abstract

Generative artificial intelligence has introduced new possibilities for providing individualized feedback on English as a Foreign Language (EFL) writing. Nevertheless, its effectiveness relative to teacher feedback remains contested, particularly for argumentative writing, which requires linguistic control, rhetorical organization, evidence evaluation, and critical reasoning. This article presents a structured comparative synthesis of published empirical research examining AI-generated, teacher-provided, and hybrid feedback in university EFL writing. The analysis draws on accessible scholarly publications released through October 2026 and considers writing performance, feedback characteristics, learner engagement, and revision practices. The reviewed evidence indicates that both AI-generated and teacher feedback can support writing improvement, although comparative outcomes vary across studies. Some investigations report no statistically significant differences between feedback conditions, whereas others identify advantages for particular AI-supported or hybrid approaches. Evidence also suggests that feedback effectiveness depends on proficiency, instructional mediation, task characteristics, and learners' capacity to interpret and implement comments. Findings from Ecuador caution against assuming that combining AI and teacher feedback necessarily improves grammatical accuracy. Drawing on sociocultural theory, formative assessment, feedback literacy, and self-regulated learning, the article proposes a comparative research protocol for future empirical validation at Universidad Estatal de Milagro. The synthesis supports a pedagogical approach that treats generative AI as a potential feedback resource rather than an automatic substitute for teacher judgment. Further controlled research is needed to establish whether improvements in revised essays transfer to independent argumentative writing.

Revista JRG de Estudos AcadêmicosVol. 9(21)
Universidad Estatal de Milagro (EC)
Quality education
EFL/ESL Teaching and Learning
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.

Laika access coming soon