Kori: Interactive Synthesis of Text and Charts in Data Documents

TL;DR

Kori is an interactive system that facilitates the seamless integration of text and charts in data documents, enhancing comprehension and authoring efficiency through natural language processing and user interaction.

Contribution

It introduces a novel mixed-initiative interface that automatically suggests and allows manual construction of references between text and charts, supported by analysis of the design space.

Findings

The interface improves the efficiency of creating interactive data documents.

Users find it easier to establish and navigate references between text and charts.

System evaluation shows effective support for data document composition.

Abstract

Charts go hand in hand with text to communicate complex data and are widely adopted in news articles, online blogs, and academic papers. They provide graphical summaries of the data, while text explains the message and context. However, synthesizing information across text and charts is difficult; it requires readers to frequently shift their attention. We investigated ways to support the tight coupling of text and charts in data documents. To understand their interplay, we analyzed the design space of chart-text references through news articles and scientific papers. Informed by the analysis, we developed a mixed-initiative interface enabling users to construct interactive references between text and charts. It leverages natural language processing to automatically suggest references as well as allows users to manually construct other references effortlessly. A user study complemented with algorithmic evaluation of the system suggests that the interface provides an effective way to compose interactive data documents.