Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 24 of its 57 references that are in the map. First posted on arXiv 21 Mar 2022.
Builds on
24 of 57 references.
References · 24
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
- 2018Datasheets for Datasetscited by 1,371
- 2018Model Cards for Model Reportingcited by 1,068
- 2019AutoML: A Survey of the State-of-the-Artcited by 388
- 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 251
- 2019Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Makingcited by 109
- 2019Human-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AIcited by 79
- 2020How do Data Science Workers Collaborate? Roles, Workflows, and Toolscited by 64
- 2021Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needscited by 64
- 2021D2S: Document-to-Slide Generation Via Query-Based Text Summarizationcited by 48
- 2019An ADMM Based Framework for AutoML Pipeline Configurationcited by 47
- 2020Trust in AutoML: Exploring Information Needs for Establishing Trust in Automated Machine Learning Systemscited by 36
12 more
- 2021AutoDS: Towards Human-Centered Automation of Data Sciencecited by 32
- 2019How Data Scientists Work Together With Domain Experts in Scientific Collaborations: To Find The Right Answer Or To Ask The Right Question?cited by 30
- 2020Calliope: Automatic Visual Data Story Generation from a Spreadsheetcited by 30
- 2021How AI Developers Overcome Communication Challenges in a Multidisciplinary Team: A Case Studycited by 29
- 2021CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computingcited by 28
- 2021Whither AutoML? Understanding the Role of Automation in Machine Learning Workflowscited by 22
- 2021How Much Automation Does a Data Scientist Want?cited by 20
- 2021MultiVision: Designing Analytical Dashboards with Deep Learning Based Recommendationcited by 11
- 2021Orienting, Framing, Bridging, Magic, and Counseling: How Data Scientists Navigate the Outer Loop of Client Collaborations in Industry and Academiacited by 10
- 2021HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebookscited by 6
- 2021NBSearch: Semantic Search and Visual Exploration of Computational Notebookscited by 5
- 2021From Jam Session to Recital: Synchronous Communication and Collaboration Around Data in Organizationscited by 3
Built on by
Citing papers per year: 2023: 5; 2024: 8; 2025: 2.
15 papers.
Sort:
By area:
- 2023Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Makingcited by 67
- 2024Cocoa: Co-Planning and Co-Execution with AI Agentscited by 38
- 2025Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentationscited by 18
- 2024The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biasescited by 16
- 2023Where Are We So Far? Understanding Data Storytelling Tools from the Perspective of Human-AI Collaborationcited by 13
- 2023Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Makingcited by 11
- 2023CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Modelscited by 10
- 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Explorationcited by 10
- 2024Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Studentscited by 8
- 2023Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytellingcited by 7
- 2024ChainBuddy: An AI Agent System for Generating LLM Pipelinescited by 6
- 2024Measuring Human Contribution in AI-Assisted Content Generationcited by 5
3 more
- 2025"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representationcited by 3
- 2024The AI-DEC: A Card-based Design Method for User-centered AI Explanationscited by 2
- 2024ARTiST: Automated Text Simplification for Task Guidance in Augmented Realitycited by 0
- 2025Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations14 Sep 2025
- 2025"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation21 Mar 2025
- 2024Cocoa: Co-Planning and Co-Execution with AI Agents14 Dec 2024
- 2024ChainBuddy: An AI Agent System for Generating LLM Pipelines20 Sep 2024
- 2024Measuring Human Contribution in AI-Assisted Content Generation27 Aug 2024
- 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration1 Aug 2024
- 2024The AI-DEC: A Card-based Design Method for User-centered AI Explanations26 May 2024
- 2024ARTiST: Automated Text Simplification for Task Guidance in Augmented Reality29 Feb 2024
- 2024Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Students26 Jan 2024
- 2024The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biases19 Jan 2024
- 2023Where Are We So Far? Understanding Data Storytelling Tools from the Perspective of Human-AI Collaboration27 Sep 2023
- 2023Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytelling17 Apr 2023
3 more
- 2023Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making17 Feb 2023
- 2023CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Models11 Feb 2023
- 2023Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making14 Jan 2023
- 2023Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Makingcited by 67
- 2024Cocoa: Co-Planning and Co-Execution with AI Agentscited by 38
- 2024The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biasescited by 16
- 2023Where Are We So Far? Understanding Data Storytelling Tools from the Perspective of Human-AI Collaborationcited by 13
- 2023Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Makingcited by 11
- 2023CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Modelscited by 10
- 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Explorationcited by 10
- 2024Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Studentscited by 8
- 2023Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytellingcited by 7
- 2024Measuring Human Contribution in AI-Assisted Content Generationcited by 5
- 2025"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representationcited by 3
- 2024The AI-DEC: A Card-based Design Method for User-centered AI Explanationscited by 2
12 most cited of 13 All 13 (JSON)
- 2025"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation21 Mar 2025
- 2024Cocoa: Co-Planning and Co-Execution with AI Agents14 Dec 2024
- 2024Measuring Human Contribution in AI-Assisted Content Generation27 Aug 2024
- 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration1 Aug 2024
- 2024The AI-DEC: A Card-based Design Method for User-centered AI Explanations26 May 2024
- 2024ARTiST: Automated Text Simplification for Task Guidance in Augmented Reality29 Feb 2024
- 2024Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Students26 Jan 2024
- 2024The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biases19 Jan 2024
- 2023Where Are We So Far? Understanding Data Storytelling Tools from the Perspective of Human-AI Collaboration27 Sep 2023
- 2023Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytelling17 Apr 2023
- 2023Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making17 Feb 2023
- 2023CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Models11 Feb 2023
12 newest of 13 All 13 (JSON)