Aptly: Making Mobile Apps from Natural Language

📅 2024-04-30
🏛️ CHI Extended Abstracts
📈 Citations: 1
Influential: 0
📄 PDF
🤖 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.

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

Democratizing mobile app development for young learners
Translating natural language into visual programming blocks
Assessing usability and AI's role in programming accessibility
Innovation

Methods, ideas, or system contributions that make the work stand out.

LLM integrated with App Inventor
Natural language to visual blocks
Democratizing app development for learners
🔎 Similar Papers
No similar papers found.
E
Evan W Patton
MIT Computer Science and Artificial Intelligence Laboratory
D
David Y.J. Kim
MIT Computer Science and Artificial Intelligence Laboratory
A
Ashley Granquist
MIT Electrical Engineering and Computer Science
R
Robin Liu
MIT Electrical Engineering and Computer Science
A
Arianna Scott
MIT Electrical Engineering and Computer Science
J
Jennet Zamanova
MIT Electrical Engineering and Computer Science
H
Harold Abelson
MIT Computer Science and Artificial Intelligence Laboratory, MIT Electrical Engineering and Computer Science