🤖 AI Summary
Existing AI-assisted visualization tools struggle to accurately align user intent with visual representation and face unique challenges in practice. This study addresses these limitations through an empirical investigation involving 16 interdisciplinary participants who completed visualization tasks using a natural language–driven vibe coding tool. Combining task-based experiments with semi-structured interviews, the work systematically characterizes user behavior patterns during prompt formulation, result evaluation, and iterative refinement. The findings reveal distinct practices in visualization contexts that diverge from general-purpose programming, identifying key barriers that impede effective output generation. These insights provide both theoretical grounding and practical guidance for the design of next-generation AI-powered visualization systems.
📝 Abstract
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.