Vibe Analysis: Exploring LLM Adoption by Data Visualization Practitioners

2026-09-25

AI Summary

This study investigates the current adoption of large language models (LLMs) in data visualization practice, addressing barriers arising from their error-proneness and lack of domain-specific design. Through semi-structured interviews with visualization designers, we employ qualitative methods to analyze behavioral patterns in leveraging LLMs for both creative and technical tasks. We introduce the novel concept of "vibe analysis" workflows and identify visualization-specific challenges and knowledge gaps, such as chart verification, demonstrating that LLMs are already deeply integrated into visualization pipelines. This work fills a critical gap in the literature and provides key directions for developing LLM-assisted visualization tools that incorporate established best practices.

Abstract

Large language models (LLMs) are enticing in their promise to support data visualization (Vis) through faster and simpler workflows for data prep, analysis, and visualization creation. Yet LLMs are notoriously error-prone and not built for data visualization tasks. Few studies have explored LLM adoption among Vis practitioners. To fill this gap, we conducted semi-structured interviews with members of the Data Visualization Society, a global community of data visualization designers. Our findings show that Vis designers actively use LLMs for both creative and technical aspects of the visualization process. A new visualization workflow is emerging, a process we call vibe analysis, analogous to vibe coding. Some key challenges raised by participants parallel those of vibe coding, while others are Vis-specific, like gaps in Vis knowledge and chart verification. This work opens up opportunities for research combining LLM-mediated work with Vis tools that incorporate data visualization guidance, constraints, and best practices.

Problem

• Large Language Models
• Data Visualization
• LLM Adoption
• Vibe Analysis
• Practitioner Challenges

Innovation

• Large Language Models
• Data Visualization
• Vibe Analysis
• Visualization Workflow
• Human-AI Interaction