Enhancing Students' Oral Proficiency with LEARN (Language automated Evaluation by generating Answers/questions from caRtooNs)

Author : Suryani Binte Atan

Abstract :This paper examines the reading aloud and speaking competencies of Malay Language students aged seven and eight in Singapore primary schools. Key aspects such as pronunciation, grammar, and lexical diversity were analysed to understand students' oral proficiency. These findings informed the development of LEARN: Language automated Evaluation by generating Answers/questions from caRtooNs, an AI-powered conversational chatbot collaboratively created by the National Institute of Education (NIE) – Nanyang Technological University (NTU) and the Singapore Institute of Technology (SIT). LEARN engages students in short, guided conversations based on picture description tasks, providing an interactive platform for practising oral skills in their mother tongue. Designed with scaffolding principles, LEARN supports the gradual development of oral proficiency. This presentation will highlight the chatbot's key features, educational affordances, and iterative learning loops that enhance students' language acquisition, specifically in striving to increase their oral proficiency.

Keywords :oral proficiency, AI-powered chatbot, learning loops, Malay Language, mother tongue languages.

Conference Name :International Conference on Educational and Instructional Technology (ICEIT-25)

Conference Place Melbourne, Australia

Conference Date 18th Jun 2025