Representing Visualization Insights as a Dense Insight Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hoffswell, Jane, Bursztyn, Victor Soares, Guo, Shunan, Martinez, Jesse, Koh, Eunyee
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910795421450240
author Hoffswell, Jane
Bursztyn, Victor Soares
Guo, Shunan
Martinez, Jesse
Koh, Eunyee
author_facet Hoffswell, Jane
Bursztyn, Victor Soares
Guo, Shunan
Martinez, Jesse
Koh, Eunyee
contents We propose a dense insight network framework to encode the relationships between automatically generated insights from a complex dashboard based on their shared characteristics. Our insight network framework includes five high-level categories of relationships (e.g., type, topic, value, metadata, and compound scores). The goal of this insight network framework is to provide a foundation for implementing new insight interpretation and exploration strategies, including both user-driven and automated approaches. To illustrate the complexity and flexibility of our framework, we first describe a visualization playground to directly visualize key network characteristics; this playground also demonstrates potential interactive capabilities for decomposing the dense insight network. Then, we discuss a case study application for ranking insights based on the underlying network characteristics captured by our framework, before prompting a large language model to generate a concise, natural language summary. Finally, we reflect on next steps for leveraging our insight network framework to design and evaluate new systems.
format Preprint
id arxiv_https___arxiv_org_abs_2501_13309
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Representing Visualization Insights as a Dense Insight Network
Hoffswell, Jane
Bursztyn, Victor Soares
Guo, Shunan
Martinez, Jesse
Koh, Eunyee
Human-Computer Interaction
We propose a dense insight network framework to encode the relationships between automatically generated insights from a complex dashboard based on their shared characteristics. Our insight network framework includes five high-level categories of relationships (e.g., type, topic, value, metadata, and compound scores). The goal of this insight network framework is to provide a foundation for implementing new insight interpretation and exploration strategies, including both user-driven and automated approaches. To illustrate the complexity and flexibility of our framework, we first describe a visualization playground to directly visualize key network characteristics; this playground also demonstrates potential interactive capabilities for decomposing the dense insight network. Then, we discuss a case study application for ranking insights based on the underlying network characteristics captured by our framework, before prompting a large language model to generate a concise, natural language summary. Finally, we reflect on next steps for leveraging our insight network framework to design and evaluate new systems.
title Representing Visualization Insights as a Dense Insight Network
topic Human-Computer Interaction
url https://arxiv.org/abs/2501.13309