DataTales: Investigating the use of Large Language Models for Authoring Data-Driven Articles
This work addresses the challenge of authoring data-driven articles for professionals, but it is incremental as it focuses on feasibility and perceived value rather than a major breakthrough.
The authors investigated using large language models to assist in writing data-driven articles by developing a prototype system called DataTales, which generates narratives for charts, and conducted a qualitative study with 11 professionals to identify affordances and opportunities for integration.
Authoring data-driven articles is a complex process requiring authors to not only analyze data for insights but also craft a cohesive narrative that effectively communicates the insights. Text generation capabilities of contemporary large language models (LLMs) present an opportunity to assist the authoring of data-driven articles and expedite the writing process. In this work, we investigate the feasibility and perceived value of leveraging LLMs to support authors of data-driven articles. We designed a prototype system, DataTales, that leverages a LLM to generate textual narratives accompanying a given chart. Using DataTales as a design probe, we conducted a qualitative study with 11 professionals to evaluate the concept, from which we distilled affordances and opportunities to further integrate LLMs as valuable data-driven article authoring assistants.