Towards Effective Generation of Interactive Visualizations with Vibe Coding: An Empirical Study
Human-Computer Interaction
Summary
The authors studied a new way to create interactive visualizations using a method called vibe coding, which uses AI to write and change code from instructions in plain language. They ran a study with 78 people to see how well vibe coding works and how users feel about it. Their research looked at what vibe coding can do, how users experience it, and how people and AI can best work together. They found both benefits and challenges in using vibe coding and shared ideas to improve its use in making visualizations.
interactive visualizationvibe codingLarge Language Modelsnatural language programminguser studyhuman-agent collaborationcode generationprogramming paradigm
Authors
Yanshan Zeng, Ruixuan Tu, Zuo Xiang, Lijia Feng, Guozheng Li, Chi Harold Liu
Abstract
Constructing interactive visualizations has traditionally required substantial human effort, involving both technical implementation and design decision-making. Recently, vibe coding, a programming paradigm leveraging Large Language Models to generate, interpret, and refactor code from natural language specifications, has emerged as a promising approach to reduce the burden. However, the capabilities and limitations of vibe coding in building interactive visualizations remain unexplored. To address this gap, we conducted a user study with 78 participants that were tasked with constructing interactive visualizations using vibe coding. We further collected users feedback through questionnaires, interviews, and case analyses. Based on this study, we examine (1) the capabilities and (2) user experience of vibe coding in generating interactive visualizations, and (3) the practical human-agent collaboration strategies adopted. Our findings provide the first systematic assessment of vibe coding for interactive visualization construction, revealing both its strengths and limitations, explaining the shift in developer labor and identifying the hybrid collaboration strategies participants adopted. Furthermore, our study offers insights for more intuitive and robust vibe coding practices.