🤖 AI Summary
This study addresses the high entry barrier and weak programming foundations hindering adolescent beginners in mobile app development. We propose a novel natural language programming (NLP) approach that deeply integrates large language models (LLMs) with MIT App Inventor, enabling end-to-end generation of executable visual code blocks from natural language functional specifications. Our key contribution is the first implementation of bidirectional semantic mapping between LLMs and a visual programming environment—supporting contextual understanding, block-level code generation, and real-time feedback. In an empirical study with high school students, the method significantly improved usability (92% task completion rate) and reduced cognitive load. Participants reported enhanced accessibility and AI-augmented creative practice; notably, prior programming experience moderated interaction strategies. Results validate the feasibility and pedagogical value of natural language–driven visual programming in computing education.
📝 Abstract
This paper introduces Aptly, a platform designed to democratize mobile app development, particularly for young learners. Aptly integrates a Large Language Model (LLM) with App Inventor, enabling users to create apps using their natural language. User’s description is translated into a programming language that corresponds with App Inventor’s visual blocks. A preliminary study with high school students demonstrated the usability and potential of the platform. Prior programming experience influenced how users interact with Aptly. Participants identified areas for improvement and expressed a shift in perspective regarding programming accessibility and AI’s role in creative endeavors.