Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work
arXiv:2203.11085 · doi:10.1145/3491102.3517615
Abstract
Creating presentation slides is a critical but time-consuming task for data scientists. While researchers have proposed many AI techniques to lift data scientists' burden on data preparation and model selection, few have targeted the presentation creation task. Based on the needs identified from a formative study, this paper presents NB2Slides, an AI system that facilitates users to compose presentations of their data science work. NB2Slides uses deep learning methods as well as example-based prompts to generate slides from computational notebooks, and take users' input (e.g., audience background) to structure the slides. NB2Slides also provides an interactive visualization that links the slides with the notebook to help users further edit the slides. A follow-up user evaluation with 12 data scientists shows that participants believed NB2Slides can improve efficiency and reduces the complexity of creating slides. Yet, participants questioned the future of full automation and suggested a human-AI collaboration paradigm.
Accepted at CHI'2022
References in corpus (8)
- Calliope: Automatic Visual Data Story Generation from a Spreadsheet
- How AI Developers Overcome Communication Challenges in a Multidisciplinary Team: A Case Study
- Trust in AutoML: Exploring Information Needs for Establishing Trust in Automated Machine Learning Systems
- Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs
- AutoDS: Towards Human-Centered Automation of Data Science
- How Much Automation Does a Data Scientist Want?
- NBSearch: Semantic Search and Visual Exploration of Computational Notebooks
- CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing
Cited by in corpus (13)
- How Knowledge Workers Think Generative AI Will (Not) Transform Their Industries
- Notable: On-the-fly Assistant for Data Storytelling in Computational Notebooks
- Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making
- LessonPlanner: Assisting Novice Teachers to Prepare Pedagogy-Driven Lesson Plans with Large Language Models
- CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Models
- Causalvis: Visualizations for Causal Inference
- Matcha: An IDE Plugin for Creating Accurate Privacy Nutrition Labels
- Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytelling
- ChainBuddy: An AI Agent System for Generating LLM Pipelines
- The AI-DEC: A Card-based Design Method for User-centered AI Explanations
- NotePlayer: Engaging Jupyter Notebooks for Dynamic Presentation of Analytical Processes
- Planar or Spatial: Exploring Design Aspects and Challenges for Presentations in Virtual Reality with No-coding Interface
- DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration