Artificial Intelligence in EFL Writing Enhancement: A Study on Chatbot Feedback and Learner Autonomy

Abstract

Writing is a challenging aspect of second language acquisition, especially among English as a Foreign Language learners. This paper examines an online AI chatbot application that offers learners context-sensitive feedback on writing tasks, making it a valuable component of scalable online learning environments that promote learner autonomy. A transformer-based NLP system, using essays of the International Corpus of Learner English (ICLE), produced context-based and multi-layered feedback on grammar, vocabulary, and discourse-level characteristics. Changes in lexical diversity (MTLD), syntactic complexity (C/T), and cohesion were measured using a model of a simulated revision task. Findings indicated significant language gains and increased self-reliance among high-level learners through self-directed revisions. The results suggest the potential of chatbots as writing partners in blended and asynchronous learning settings. The following trends are anticipated for the future: classroom testing, provision of assistance to lower-level students, and hybrid AI-teacher feedback systems.