Data Formulator: AI-powered Concept-driven Visualization Authoring

TL;DR

Data Formulator introduces a novel AI-powered visualization tool that simplifies data transformation by allowing users to define concepts in natural language, automating the process and enhancing accessibility for visualization creation.

Contribution

It proposes a new concept binding paradigm and implements it in Data Formulator, enabling intuitive, concept-driven visualization authoring without extensive data transformation expertise.

Findings

Participants successfully created complex visualizations using Data Formulator.

The tool improved understanding and inspection of data transformations.

User feedback indicated ease of use and effectiveness.

Abstract

With most modern visualization tools, authors need to transform their data into tidy formats to create visualizations they want. Because this requires experience with programming or separate data processing tools, data transformation remains a barrier in visualization authoring. To address this challenge, we present a new visualization paradigm, concept binding, that separates high-level visualization intents and low-level data transformation steps, leveraging an AI agent. We realize this paradigm in Data Formulator, an interactive visualization authoring tool. With Data Formulator, authors first define data concepts they plan to visualize using natural languages or examples, and then bind them to visual channels. Data Formulator then dispatches its AI-agent to automatically transform the input data to surface these concepts and generate desired visualizations. When presenting the results (transformed table and output visualizations) from the AI agent, Data Formulator provides feedback to help authors inspect and understand them. A user study with 10 participants shows that participants could learn and use Data Formulator to create visualizations that involve challenging data transformations, and presents interesting future research directions.