The Impact of Using Grammarly on Complexity, Accuracy, Fluency, and Self-Efficacy in Iranian EFL Learners’ Argumentative Essay Writing

Artificial intelligence (AI) is reshaping language education by offering real-time, personalized writing feedback. This study assessed the impact of Grammarly, an AI-powered writing assistant that utilizes advanced natural language processing and generative AI, on the complexity, accuracy, fluency (CAF), and self-efficacy of Iranian EFL students’ argumentative writing. A total of ۱۲۰ high-intermediate learners from intact classes were screened for proficiency level via the Oxford Quick Placement Test and then randomly divided into an experimental group (Grammarly, n=۶۰) and a control group (conventional teacher feedback, n=۶۰). Over ۱۲ weeks, a period deemed necessary for the development of complex writing skills, the experimental group used Grammarly for automated feedback on grammar, vocabulary, and style during weekly writing tasks, while the control group received conventional teacher feedback. ANCOVA analysis, controlling for pretest results and conducted after confirming key statistical assumptions, showed significant gains for the Grammarly group in complexity (F=۱۲۷۷.۰۰۹, p <.۰۰۱), accuracy (F=۲۱۱۸.۸۳۸, p< .۰۰۱), fluency (F=۴۹.۵۳۵, p<.۰۰۱), and self-efficacy (F=۴۰۹.۲۳۷, p<.۰۰۱), with the largest improvements in accuracy. These results align with the CAF framework, indicating that AI tools excel most in rule-based domains (e.g., grammar) rather than procedural fluency. The findings underscore Grammarly’s value in scaffolding grammatical competence and learner confidence, specifying that the tool is most effective for grammatical scaffolding.

کلیدواژه ها:

AI-assisted Education ، Grammarly ، Complexity ، Accuracy ، Fluency ، self-efficacy ، Argumentative Writing