LEARN: Improving Young Learners’ Oral Performance Through AI-Guided Picture Conversations

James Alexander Gordon on 27th February 2025



Author Information

Kartini Anwar, National Institute of Education, Singapore

Abstract

Oral language development is a foundational skill in early literacy, yet traditional classroom interactions often provide limited opportunities for structured, interactive, and individualized oral practice. Research has shown that AI-powered language tools can enhance oral performance by providing adaptive, interactive, and real-time feedback, as well as sustained engagement. AI-driven conversation depends on pedagogically sound content design, particularly in how picture-based prompts are selected and structured. LEARN (Language automated Evaluation by generating Answers/questions from caRtooNs) is an AI-powered chatbot designed to improve the oral performance of young children in their mother tongue language (MTL). Jointly developed by the Singapore Institute of Technology (SIT) and the National Institute of Education, Nanyang Technological University (NIE-NTU), LEARN facilitates curriculum-aligned picture conversations for young learners, providing visual and verbal stimuli. The key component of its AI-driven conversation is the thematic picture selection based on (i) curriculum alignment, (ii) dynamic and action-based imagery, (iii) diversity and inclusion, and (iv) integration of progressive questioning. This paper presentation discusses the creation of picture-based prompts and pedagogical considerations for leveraging LEARN to facilitate oral performance in mother tongue language learning.


Paper Information

Conference: ECE2025
Stream: Learning Experiences

This paper is part of the ECE2025 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window

To cite this article:
Anwar K. (2025) LEARN: Improving Young Learners’ Oral Performance Through AI-Guided Picture Conversations ISSN: 2188-1162 The European Conference on Education 2025: Official Conference Proceedings (pp. 433-442) https://doi.org/10.22492/issn.2188-1162.2025.35
To link to this article: https://doi.org/10.22492/issn.2188-1162.2025.35

Comments & Feedback

Place a comment using your LinkedIn profile

Comments

Share on activity feed

Powered by WP LinkPress

Share this Research

Posted by James Alexander Gordon

All Posts