AI-Driven Assessment in TESOL: Adaptive Feedback for Personalized Learning
Umme Habiba · 2025
Artificial Intelligence (AI) has significantly reshaped the landscape of language education, particularly in Teaching English to Speakers of Other Languages (TESOL). Traditional assessment strategies often fail to capture learner-specific progress, provide timely feedback, or adapt to diverse linguistic backgrounds. This paper proposes an AI-driven adaptive assessment model that leverages Natural Language Processing (NLP), machine learning, and deep learning to provide real-time, personalized feedback to learners. The approach focuses on adaptive diagnostic assessments, formative evaluation, and continuous feedback loops to enhance language fluency and learner autonomy. Through a system architecture comprising speech recognition, grammar error detection, and semantic analysis, the model dynamically adjusts assessment difficulty and provides scaffolded guidance tailored to each learner's proficiency. Experimental evaluation with ESL learners demonstrated improved engagement, increased accuracy in language use, and higher satisfaction compared to conventional assessment methods. The results suggest that AI-driven adaptive feedback can foster learner motivation, improve performance, and align with modern personalized learning paradigms. This research contributes to the integration of AI technologies in TESOL by bridging the gap between automated assessment and individualized learning needs, offering scalable solutions for global ESL classrooms.