Calliope: A System for Automatic Visual Data Story Generation from a Spreadsheet

Danqing Shi, Xinyue Xu, Fuling Sun, Yang Shi, Nan Cao

View presentation: 2020-10-29T18:15:00Z GMT-0600 Change your timezone on the schedule page
2020-10-29T18:15:00Z
Exemplar figure
A full-automatically generated visual data story about COVID-19 virus propagation in March 2020 in China. The whole story consists of six data facts shown in the storyline mode. The story first illustrates an overall trend of the total death followed by the elaborations of data details in Hubei, which is the most influenced province in China. Finally, the story is summarized by the total death and recovered in March, showing the improved situation in China.
Fast forward

Direct link to video on YouTube: https://youtu.be/OufOfRXtGzk

Keywords

Information Visualization, Visual Storytelling, Data Story

Abstract

Visual data stories shown in the form of narrative visualizations such as a poster or a data video, are frequently used in data-oriented storytelling to facilitate the understanding and memorization of the story content. Although useful, technique barriers, such as data analysis, visualization, and scripting, make the generation of a visual data story difficult. Existing authoring tools rely on users' skills and experiences, which are usually inefficient and still difficult. In this paper, we introduce a novel visual data story generating system, Calliope, which creates visual data stories from an input spreadsheet through an automatic process and facilities the easy revision of the generated story based on an online story editor. Particularly, Calliope incorporates a new logic-oriented Monte Carlo tree search algorithm that explores the data space given by the input spreadsheet to progressively generate story pieces (i.e., data facts) and organize them in a logical order. The importance of data facts is measured based on information theory, and each data fact is visualized in a chart and captioned by an automatically generated description. We evaluate the proposed technique through three example stories, two controlled experiments, and a series of interviews with 10 domain experts. Our evaluation shows that Calliope is beneficial to efficient visual data story generation.