Vibe Coding for Visualization Implementation: An Empirical Study of Practices and Challenges
For visualization tool designers and researchers, this work provides empirical insights into user practices and challenges with AI-assisted visualization, though the findings are preliminary and based on a small sample.
This study investigates how users employ AI-driven 'vibe coding' tools for data visualization implementation through an empirical study with 16 participants. It characterizes user practices across prompting, evaluation, and iteration, and identifies challenges in aligning user intent with visual representation.
Data visualization is essential for data analysis and communication, yet creating expressive visualizations remains labor-intensive. Recent AI-driven ``vibe coding'' tools enable users to generate visualizations through natural language interaction, lowering the barrier to entry. However, visualization implementation requires precise alignment between user intent and visual representation, which may differ from general software development practices. We present an empirical study with 16 participants of varying expertise to examine how users employ vibe coding tools for visualization implementation. Participants completed two visualization tasks and a semi-structured interview. Our findings characterize the diverse practices users adopt across prompting, evaluation, and iteration, and surface the challenges they encounter throughout the process.