Multimodal Analogy Generation in Programming Education

Yuri Noviello, Anastasiia Birillo, and Gosia Migut

July, 2025. Accepted to ITiCSE'25 (A).

Abstract. Engaging students with effective learning materials continues to be a significant challenge in programming education. Analogies are commonly used to simplify complex topics, enabling learners to relate unfamiliar concepts to familiar ones. Additionally, visual representations of these analogies can enhance engagement and improve the overall learning experience. This work presents a prototype of a novel AI tool that generates analogy-based explanations and corresponding video animations for programming education. The tool leverages Large Language Models (LLMs) for analogy generation and a structured animation workflow for visualization. This poster invites discussion on the effectiveness of AI-generated educational content and its implications for programming education.