Table of Contents
Fetching ...

OutlineSpark: Igniting AI-powered Presentation Slides Creation from Computational Notebooks through Outlines

Fengjie Wang, Yanna Lin, Leni Yang, Haotian Li, Mingyang Gu, Min Zhu, Huamin Qu

TL;DR

Inspired by the common and widely recommended slide creation practice: drafting outlines first and then adding concrete content, OutlineSpark is introduced, an AI-powered slide creation tool that generates slides from a slide outline written by the user.

Abstract

Computational notebooks are widely utilized for exploration and analysis. However, creating slides to communicate analysis results from these notebooks is quite tedious and time-consuming. Researchers have proposed automatic systems for generating slides from notebooks, which, however, often do not consider the process of users conceiving and organizing their messages from massive code cells. Those systems ask users to go directly into the slide creation process, which causes potentially ill-structured slides and burdens in further refinement. Inspired by the common and widely recommended slide creation practice: drafting outlines first and then adding concrete content, we introduce OutlineSpark, an AI-powered slide creation tool that generates slides from a slide outline written by the user. The tool automatically retrieves relevant notebook cells based on the outlines and converts them into slide content. We evaluated OutlineSpark with 12 users. Both the quantitative and qualitative feedback from the participants verify its effectiveness and usability.

OutlineSpark: Igniting AI-powered Presentation Slides Creation from Computational Notebooks through Outlines

TL;DR

Inspired by the common and widely recommended slide creation practice: drafting outlines first and then adding concrete content, OutlineSpark is introduced, an AI-powered slide creation tool that generates slides from a slide outline written by the user.

Abstract

Computational notebooks are widely utilized for exploration and analysis. However, creating slides to communicate analysis results from these notebooks is quite tedious and time-consuming. Researchers have proposed automatic systems for generating slides from notebooks, which, however, often do not consider the process of users conceiving and organizing their messages from massive code cells. Those systems ask users to go directly into the slide creation process, which causes potentially ill-structured slides and burdens in further refinement. Inspired by the common and widely recommended slide creation practice: drafting outlines first and then adding concrete content, we introduce OutlineSpark, an AI-powered slide creation tool that generates slides from a slide outline written by the user. The tool automatically retrieves relevant notebook cells based on the outlines and converts them into slide content. We evaluated OutlineSpark with 12 users. Both the quantitative and qualitative feedback from the participants verify its effectiveness and usability.
Paper Structure (26 sections, 9 figures)

This paper contains 26 sections, 9 figures.

Figures (9)

  • Figure 1: OutlineSpark is an interactive AI-powered JupyterLab plugin designed to facilitate the creation of presentation slides from computational notebooks using outlines. The user interface of OutlineSpark comprises three interconnected components: a Notebook Overview (A) that provides a visual summary of the notebook cells by relevant keywords, a Outline Panel (B) that enables users to craft outlines and initiate the generation of slides, and a Slides Panel (C) that renders the generated slides and offers users the flexibility to refine and customize them.
  • Figure 2: This figure illustrates the interactive components of OutlineSpark, including (A) Notebook Overview, (B) Outline Panel, and (C) Slides Panel. (A) explains the visual encodings of Notebook Overview. (b1)-(b7) allows users to generate slides, adjust slide generation options and parameters, edit outlines, and etc. (C) showcases the content of a slide, and (c1) enables users to refine the generated slides.
  • Figure 3: This figure illustrates a usage scenario in which an analyst, Andie, utilizes OutlineSpark to create slides from his computation notebook. In the process, Andie follows these steps: (A) Gain an overview of the notebooks, (B) Draft an outline to guide the slide generation, (C) Instruct OutlineSpark to generate the slides, and (D-H) Refine the generated slides.
  • Figure 4: This figure showcases three sample outlines crafted by participants (P1, P2 and P3) during the user study.
  • Figure 5: This figure shows participants' ratings on the effectiveness of OutlineSpark on a 7-point Likert Scale (1 = "strongly disagree" and 7 = "strongly agree").
  • ...and 4 more figures