Year: 2026
Type: article
Abstract: This narrative review synthesizes research on ChatGPT and English language learning published from November 2022 through the review’s stated early-2025 window. Google Scholar, Scopus, and Web of Science were the named search sources, but the original search log did not preserve database-level record totals, duplicate counts, the exact final search date, or stage-by-stage exclusion counts; these historical details cannot be reconstructed and no counts have been estimated. The core synthesis includes eight ChatGPT-specific primary studies and the directly relevant systematic review by Lo et al. (2024). Zhai et al. (2024), a broader systematic review of AI dialogue systems, and Fathi et al. (2024), which studied the Andy English Chatbot rather than ChatGPT, are used only as contextual sources and are not counted as direct ChatGPT-specific primary evidence. Full-text verification confirmed that Algaraady and Mahyoob (2023) is an empirical error-analysis study of 88 student texts, but it did not measure learner gains. Two studies published later in 2025 (Alnemrat et al., 2025; Behforouz et al., 2025) were checked to resolve the editor’s query and excluded from the core synthesis because they fall after the stated early-2025 window. No formal quality-appraisal instrument was applied; evidence judgments are provisional author assessments. The review examines writing, vocabulary and grammar, learner perceptions, and reported risks, while identifying a lack of eligible ChatGPT-specific speaking and listening evidence.
Author: Amna Mahar
Institution: Mehran University of Engineering and Technology
Language: English
Subfield: Language and Linguistics
Field: Arts and Humanities
Domain: Social Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W7225397606