Glyphboard: Visual Exploration of High-Dimensional Data Combining Glyphs with Dimensionality Reduction

Area of Science:

• Data Science
• Information Visualization
• Human-Computer Interaction

Background:

• Data science requires interdisciplinary collaboration between data scientists and domain experts.
• Understanding high-dimensional data necessitates effective communication and visualization tools.

Purpose of the Study:

• To introduce Glyphboard, a novel visualization tool designed to facilitate dialogue between data scientists and domain experts.
• To present an integrated approach combining dimensionality reduction and glyph-based visualizations.

Main Methods:

• Development of an open-source prototype of Glyphboard.
• Creation of a general exchange format for high-dimensional data.
• Conducting a case study with nine data scientists and domain experts across four domains.

Main Results:

• Glyphboard integrates zoomable user interface, dimensionality reduction, and glyph-based visualizations.
• Dimensionality reduction provides a quick data overview, while glyphs highlight key dimensions.
• Evaluation of user interaction with Glyphboard's features by experts.

Conclusions:

• Glyphboard offers a seamless and integrated solution for visualizing and exploring high-dimensional data.
• The tool supports the crucial dialogue between data scientists and domain experts.
• The open-source prototype and case study provide a foundation for further research and application.