Designing a Leveled Conversational Teachable Agent for English Language Learners

Given the considerable importance of English language as a common method global communication, supporting and engaging learning environments for studying second are essential. In this study, we propose an interactive agent that considers differences in learners’ skill levels to help motivate learners support independent study. The proposed is AI chatbot can vary complexity its natural interactions skills improve engage unstructured conversations with users. We first collected dataset among children then acquired data on utterances words sentences using interface evaluation. Based these datasets, generated set personalized conversational agents by algorithms evaluate speakers’ pronunciation sentences. Finally, expert evaluated system ensure it could different proficiency application may be expected students learn. results showed teachable who not otherwise interested more approach tailored their level.