AutoClips: An Automatic Approach to Video Generation from Data Facts

Abstract

Data videos, a storytelling genre that visualizes data facts with motion graphics, are gaining increasing popularity among data journalists, non‐profits, and marketers to communicate data to broad audiences. However, crafting a data video is often time‐consuming and asks for various domain knowledge such as data visualization, animation design, and screenwriting. Existing authoring tools usually enable users to edit and compose a set of templates manually, which still cost a lot of human effort. To further lower the barrier of creating data videos, this work introduces a new approach, AutoClips, which can automatically generate data videos given the input of a sequence of data facts. We built AutoClips through two stages. First, we constructed a fact‐driven clip library where we mapped ten data facts to potential animated visualizations respectively by analyzing 230 online data videos and conducting interviews. Next, we constructed an algorithm that generates data videos from data facts through three steps: selecting and identifying the optimal clip for each of the data facts, arranging the clips into a coherent video, and optimizing the duration of the video. The results from two user studies indicated that the data videos generated by AutoClips are comprehensible, engaging, and have comparable quality with human‐made videos.

Erato: Cooperative Data Story Editing via Fact Interpolation

“…Sometimes, the process is cumbersome, tedious, and inefficient. To address this issue, recent studies have been focusing on automatic data story generation based on intelligent algorithms [8,42,43,61]. For example, Chen et al [8] proposed a framework and automatic workflow to bridge the gap between data analysis and communication.…”

“…For example, Chen et al [8] proposed a framework and automatic workflow to bridge the gap between data analysis and communication. AutoClips [42] optimally organizes data facts in a parallel structure to create data videos. Calliope [43] automatically generates data stories from a spreadsheet.…”

How Does Automation Shape the Process of Narrative Visualization: A Survey on Tools

“…It can divide complex animations into segments by layering keyframes and use data properties to stagger the start time and change the speed of animated objects through the timeline view [119]. (4) AI-generator tool: Autoclips automatically generates keyframes for data video based on a series of data facts [123].…”

“…AI-Generator Tool: While the tools mentioned above simplify the design process, creating a data video is still not easy because users must decide what visualizations and animations they should use and how to compose a coherent video. The above problem is solved by the emergence of AutoClips [123], a tool that automatically generates a data video after entering a sequence of data facts. This tool saves users the time of analyzing the data and the obstacles of creating animations through video motion software, significantly reducing the complexity of creating data videos.…”

“…First, existing automatic tools for creating data videos are still limited to a few visualization types and input formats. For example, AutoClips [123] only support tabular data that limits the potential visual representation of data video. More tools are needed to support diverse data types, such as spatial-temporal data and textual data, which are important for creating a comprehensive data story.…”