Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

The Human-Data-Model Interaction Canvas for Visual Analytics

Jürgen Bernard

TL;DR

The paper presents the HDMI Canvas as a new, actor-centered perspective on Visual Analytics, integrating Humans, Data, and Models via the Externalization–Exploration–Explanation (EEE) framework. It synthesizes insights from 16 existing VA process models, introduces a structured 3×2 flow canvas, and emphasizes external stakeholder communication and collaboration. Through two preliminary case studies (iPCA and BMW engine analysis), the authors illustrate how HDMI supports diverse contributions and benefits across actors, guiding both analysis and design of VA systems. While offering strong descriptive and generative potential, the work also notes limitations, including incomplete empirical validation and debates about data as an autonomous actor, suggesting directions for future refinement and outreach.

Abstract

Visual Analytics (VA) integrates humans, data, and models as key actors in insight generation and data-driven decision-making. This position paper values and reflects on 16 VA process models and frameworks and makes nine high-level observations that motivate a fresh perspective on VA. The contribution is the HDMI Canvas, a perspective to VA that complements the strengths of existing VA process models and frameworks. It systematically characterizes diverse roles of humans, data, and models, and how these actors benefit from and contribute to VA processes. The descriptive power of the HDMI Canvas eases the differentiation between a series of VA building blocks, rather than describing general VA principles only. The canvas includes modern human-centered methodologies, including human knowledge externalization and forms of feedback loops, while interpretable and explainable AI highlight model contributions beyond their conventional outputs. The HDMI Canvas has generative power, guiding the design of new VA processes and is optimized for external stakeholders, improving VA outreach, interdisciplinary collaboration, and user-centered design. The utility of the HDMI Canvas is demonstrated through two preliminary case studies.

The Human-Data-Model Interaction Canvas for Visual Analytics

TL;DR

The paper presents the HDMI Canvas as a new, actor-centered perspective on Visual Analytics, integrating Humans, Data, and Models via the Externalization–Exploration–Explanation (EEE) framework. It synthesizes insights from 16 existing VA process models, introduces a structured 3×2 flow canvas, and emphasizes external stakeholder communication and collaboration. Through two preliminary case studies (iPCA and BMW engine analysis), the authors illustrate how HDMI supports diverse contributions and benefits across actors, guiding both analysis and design of VA systems. While offering strong descriptive and generative potential, the work also notes limitations, including incomplete empirical validation and debates about data as an autonomous actor, suggesting directions for future refinement and outreach.

Abstract

Visual Analytics (VA) integrates humans, data, and models as key actors in insight generation and data-driven decision-making. This position paper values and reflects on 16 VA process models and frameworks and makes nine high-level observations that motivate a fresh perspective on VA. The contribution is the HDMI Canvas, a perspective to VA that complements the strengths of existing VA process models and frameworks. It systematically characterizes diverse roles of humans, data, and models, and how these actors benefit from and contribute to VA processes. The descriptive power of the HDMI Canvas eases the differentiation between a series of VA building blocks, rather than describing general VA principles only. The canvas includes modern human-centered methodologies, including human knowledge externalization and forms of feedback loops, while interpretable and explainable AI highlight model contributions beyond their conventional outputs. The HDMI Canvas has generative power, guiding the design of new VA processes and is optimized for external stakeholders, improving VA outreach, interdisciplinary collaboration, and user-centered design. The utility of the HDMI Canvas is demonstrated through two preliminary case studies.
Paper Structure (14 sections, 4 figures)

This paper contains 14 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Related Process Models, Frameworks, and Design Spaces
  3. Roles of Humans, Data, and Models in VA Processes
  4. How Actors Benefit from Visual Analytics Processes
  5. How Entities Contribute to VA -- The EEE Framework
  6. The Interactive Visual Data Analysis (IVDA) Canvas
  7. Requirements
  8. Interactive Visual Data Analysis Canvas Overview
  9. HDMI Canvas Usage with External Stakeholders
  10. Case Studies
  11. iPCA: Opening the Black Box of PCA Projections
  12. Analyzing Correlation Patterns of Electrical Engines
  13. Discussion and Limitations
  14. Conclusions

Figures (4)

  • Figure 1: The iPCA jeongZFRC09 white box approach leverages five out of six key information flows to enable performing both exploratory data analysis and model analysis (PCA).
  • Figure 2: The IRVINE tvcg2022eirich VA system has "Supertool" complexity: to solve the analysis goal of the experts, all three actors want to benefit from and contribute to the VA workflow (steps 1-6).
  • Figure :
  • Figure :