EFL LEARNERS’ PERCEIVED GRAMMAR ACCURACY: AI FEEDBACK TOOLS ASSESSMENT IN FOCUS

Abstract

This study explores English as a Foreign Language (EFL) learners' perceptions of grammar accuracy and the impact of AI-driven feedback tools on their self-assessment and improvement. Utilizing a mixed-methods approach, data were collected from 54 EFL students majoring in English Language Teaching at Universitas Pancasakti Tegal through quantitative surveys. The findings indicate that a significant majority of participants perceive AI feedback as accurate (57.4% finding it accurate; 29.6% very accurate), useful (53.7% rating it helpful), and satisfying (66.7% satisfied). Furthermore, learners reported that AI tools effectively identify missed errors and enhance their understanding of grammar rules. Despite the positive perceptions, a portion of participants still values traditional feedback, suggesting a potential benefit in a blended approach that combines AI and human interaction. This research underscores the growing importance of integrating AI-driven tools in language education, highlighting their role in enhancing learner engagement and grammar proficiency. Future studies should investigate the long-term effects of AI feedback on language learning outcomes and explore specific features that maximize its effectiveness.