cs.HCSep 25, 2026

Vibe Analysis: Exploring LLM Adoption by Data Visualization Practitioners

Authors: Shani C Spivak, Aditi Krishna, Mahsan Nourani, Melanie Tory

Organizations: Northeastern University, Boston, MA 02125, USA · Northeastern University, Portland, ME 04101, USA · Northeastern University, Oakland, CA 94613, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

Figure 1: LLM tools our participants reported using
Figure 2: Conceptual model of vibe analysis with portions inspired by the data storytelling lifecycle [ 17 ] and the vibe coding cycle [ 5 ] . This is an author-developed synthesis informed by the interview analysis and these existing models.
Higher-order processesLower-order processesCount of participants using LLMsP4P7P14P6P10P11P17P5P3P9P15P12P16P18P1P2P8P13
Planning & IdeationPlanning2/18   ✓\checkmark ✓\checkmark            
 Ideation11/18✓\checkmark ✓\checkmark✓\checkmark✓\checkmark✓\checkmark✓\checkmark✓\checkmark✓\checkmark ✓\checkmark✓\checkmark ✓\checkmark    
Data Collection & PrepDefinitions1/18✓\checkmark                 
 Data Collection4/18 ✓\checkmark✓\checkmark✓\checkmark      ✓\checkmark       
 Data Generation1/18    ✓\checkmark             
 Data Labeling2/18         ✓\checkmark       ✓\checkmark
Table 1: Parts of the Vis pipeline for which participants mentioned using LLMs. We distinguish between processes which are mostly technical (in blue) and those which are mostly creative (in orange) . Participants are ordered from the left with those using LLMs across more processes to those using them for fewer on the right.
StrategyCommon pitfallsSocietal impactsModel quirksSystem limitsUser concerns
 CP1CP2CP3CP4CP5SI1SI2SI3SI4SI5SI6SI7MQ1MQ2SL1SL2SL3UC1UC2UC3UC4UC5
Ask for alternatives    ∙\bullet                 
Ask for code instead of chart∙\bullet           ∙\bullet∙\bullet        
Ask for explanations     ∙\bullet   ∙\bullet∙\bullet∙\bullet          
Ask for pseudocode∙\bullet           ∙\bullet∙\bullet        
Be specific∙\bullet ∙\bullet        ∙\bullet  ∙\bullet       
Table 2: Strategies for handling LLM responses mapped to applicable challenges. Column codes are expanded below.
More in this topic

Data Visualization

Data visualization studies how visual representations help people explore, interpret, communicate, and reason about data.

See all 121 papers

Explore similar work

CardsList

  1. Do Large Language Models Understand Data Visualization Principles?

    Feb 23, 2026Martin Sinnona, Valentin Bonas, Viviana Siless +1LLM EvaluationVLM Evaluation

    Universidad Torcuato Di Tella, Buenos Aires, Argentina · Universidad de Buenos Aires, Buenos Aires, Argentina · Consejo Nacional de Investigaciones Científicas y Técnicas, Buenos Aires, Argentina

  2. Do Large Language Models Understand Data Visualization Rules?

    Feb 23, 2026Martin Sinnona, Valentin Bonas, Emmanuel Iarussi +1Data VisualizationLLM Evaluation

    Universidad Torcuato Di Tella, Buenos Aires, Argentina · Universidad de Buenos Aires, Buenos Aires, Argentina · Consejo Nacional de Investigaciones Científicas y Técnicas, Buenos Aires, Argentina

  3. ChartDesign: Towards LLM Designer of Data Visualization

    Apr 6, 2026Mohammed Afaan Ansari, Aniruddh Bansal, Tianyi ZhouData Visualization

    University of Maryland, College Park College Park, MD, USA