Where Are We So Far? Understanding Data Storytelling Tools from the Perspective of Human-AI Collaboration

TL;DR

This paper investigates existing tools with a framework from two perspectives: the stages in the storytelling workflow where a tool serves, including analysis, planning, implementation, and communication, and the roles of humans and AI in each stage, such as creators, assistants, optimizers, and reviewers.

Abstract

Data storytelling is powerful for communicating data insights, but it requires diverse skills and considerable effort from human creators. Recent research has widely explored the potential for artificial intelligence (AI) to support and augment humans in data storytelling. However, there lacks a systematic review to understand data storytelling tools from the perspective of human-AI collaboration, which hinders researchers from reflecting on the existing collaborative tool designs that promote humans' and AI's advantages and mitigate their shortcomings. This paper investigated existing tools with a framework from two perspectives: the stages in the storytelling workflow where a tool serves, including analysis, planning, implementation, and communication, and the roles of humans and AI in each stage, such as creators, assistants, optimizers, and reviewers. Through our analysis, we recognize the common collaboration patterns in existing tools, summarize lessons learned from these patterns, and further illustrate research opportunities for human-AI collaboration in data storytelling.

Figures (7)

• Figure 1: This figure shows an overview of our collected papers in venues and years. The venues with less than three papers are merged to "Others."
• Figure 2: This figure demonstrates four example tools, including Chartreuse cui2021mixed, DataShot wang2019datashot, Erato sun2022erato, and SketchStory lee2013sketchstory, assessed by our framework.
• Figure 3: This figure shows the development of data storytelling tools between 2010 and 2022 with the number of tools and collaboration between humans and AI. The year 2023 is excluded since we only collect tools up to June 2023.
• Figure 4: This figure shows the number of data storytelling tools covering four stages between 2010 and 2022.
• Figure 5: The figure shows the output of tools that cover the implementation stage between 2010 and 2022. The color hue encodes whether the output is animated or static. The color saturation represents whether the output includes single or multiple charts. The paper by Fu et al.fu2019visualization is excluded since it outputs the scores and ranks of visualization memorability and aesthetics.