Capturing Visualization Design Rationale

TL;DR

This paper introduces a novel dataset and methodology for understanding visualization design rationale using natural language, leveraging student-created notebooks and large language models to extract and validate design rationales.

Contribution

It presents a new dataset derived from real-world student notebooks and a methodology employing large language models to extract and categorize visualization design rationales.

Findings

Curated dataset captures student visualization design rationales.

Large language models effectively generate and categorize rationale triples.

Validated triples ensure high-quality insights into visualization design choices.

Abstract

Prior natural language datasets for data visualization have focused on tasks such as visualization literacy assessment, insight generation, and visualization generation from natural language instructions. These studies often rely on controlled setups with purpose-built visualizations and artificially constructed questions. As a result, they tend to prioritize the interpretation of visualizations, focusing on decoding visualizations rather than understanding their encoding. In this paper, we present a new dataset and methodology for probing visualization design rationale through natural language. We leverage a unique source of real-world visualizations and natural language narratives: literate visualization notebooks created by students as part of a data visualization course. These notebooks combine visual artifacts with design exposition, in which students make explicit the rationale behind their design decisions. We also use large language models (LLMs) to generate and categorize question-answer-rationale triples from the narratives and articulations in the notebooks. We then carefully validate the triples and curate a dataset that captures and distills the visualization design choices and corresponding rationales of the students.