Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Intelligent Canvas: Enabling Design-Like Exploratory Visual Data Analysis with Generative AI through Rapid Prototyping, Iteration and Curation

Zijian Ding, Joel Chan

TL;DR

This work introduces a "design-like" intelligent canvas environment integrating generative AI into data analysis, offering rapid prototyping, iteration, and comparative visualization management.

Abstract

Complex data analysis inherently seeks unexpected insights through exploratory visual analysis methods, transcending logical, step-by-step processing. However, existing interfaces such as notebooks and dashboards have limitations in exploration and comparison for visual data analysis. Addressing these limitations, we introduce a "design-like" intelligent canvas environment integrating generative AI into data analysis, offering rapid prototyping, iteration, and comparative visualization management. Our dual contributions include the integration of generative AI components into a canvas interface, and empirical findings from a user study (N=10) evaluating the effectiveness of the canvas interface.

Intelligent Canvas: Enabling Design-Like Exploratory Visual Data Analysis with Generative AI through Rapid Prototyping, Iteration and Curation

TL;DR

This work introduces a "design-like" intelligent canvas environment integrating generative AI into data analysis, offering rapid prototyping, iteration, and comparative visualization management.

Abstract

Complex data analysis inherently seeks unexpected insights through exploratory visual analysis methods, transcending logical, step-by-step processing. However, existing interfaces such as notebooks and dashboards have limitations in exploration and comparison for visual data analysis. Addressing these limitations, we introduce a "design-like" intelligent canvas environment integrating generative AI into data analysis, offering rapid prototyping, iteration, and comparative visualization management. Our dual contributions include the integration of generative AI components into a canvas interface, and empirical findings from a user study (N=10) evaluating the effectiveness of the canvas interface.
Paper Structure (25 sections, 4 figures)

This paper contains 25 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Design
  4. Methods
  5. Participants Recruitment
  6. Dataset and Analysis Task
  7. Study Procedure
  8. Semi-structured interview questions
  9. Results
  10. Hypothesis 1: Rapid Prototyping of Hypotheses
  11. Parallel Exploration by Participants with Extensive Data Analysis Experience
  12. Reducing Exploratory Costs and Expanding Analysis Capabilities for Participants with Less Data Analysis Experience
  13. Hypothesis 2: Rapid Iteration of Visualization
  14. Enhancing Data Visualization Through Iteration
  15. Facilitating Comparative Analysis Through Iterative Visualization Retention
  16. ...and 10 more sections

Figures (4)

  • Figure 1: Iteration of interaction of the intelligent canvas corresponding to design hypotheses.
  • Figure 2: Rapid prototyping of P9 on the relationships between country calling codes and birth rates / GDP / GDP per capita / infant mortality rate / minimum wage / armed forces size.
  • Figure 3: P1, generating an overview with correlation matrix (left) and then scatterplots for relationships with high correlations (right).
  • Figure 4: P4, comparing (1) birth rate and life expectancy and (2) 3D plot of labor force participation, infant mortality and life expectancy.