Slide4N: Creating Presentation Slides from Computational Notebooks with Human-AI Collaboration

Wang, Fengjie; Liu, Xuye; Liu, Oujing; Neshati, Ali; Ma, Tengfei; Zhu, Min; Zhao, Jian

doi:10.1145/3544548.3580753

Cited by 13 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Code Gathering Tools [15] help find, clean, recover, and compare versions of code and generate more readable, cleaner notebooks. However, code is still the main content of notebooks, which is hard to understand [49,57].…”

Section: Communication Support For Computational Notebooksmentioning

confidence: 99%

“…Furthermore, its demand for high-quality documentation is often impractical in real-world settings. Slide4N [57] mitigates these limitations by allowing users to select individual notebook cells for slide generation. However, this method demands users maintain a clear mental image of their presentation structure to make the selection, which can result in disorganized slides and additional effort in refining the organization.…”

Section: Communication Support For Computational Notebooksmentioning

confidence: 99%

“…G3: Automate slides creation from relevant cells. Presentation slides typically feature human-readable, self-explanatory, and concise content, such as titles, bullet points, and charts/tables [52,57,64]. Cells relevant to the outlines serve as the foundational materials for creating such slides, typically, the users need to manually extract and summarize the key information from them [27,50,66], and arrange them on slides.…”

Section: Design Goalsmentioning

confidence: 99%

“…Users have to utilize external presentation tools (e.g., Google Slides or Microsoft PowerPoint) to create slides for effective communication [8,46]. They have to put lots of effort into 1) conceiving the structure and content of their presentations from messy notebooks [46,66], 2) locating and retrieving relevant cells from notebooks to extract details [27,50,57], and 3) making slides that align with the intended presentation structure [6,66].…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, it requires the notebook to have a complete data science workflow and high-quality documentation, conditions that are seldom met in practice [50,55]. Slide4N [57] addresses these issues by permitting users to select cells of interest to generate and refine slides. However, it assumes that the users have a clear image of the organization and content of their slides and it asks users to begin directly with the process of selecting cells.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Wang,

Lin,

Yang

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

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 AIpowered 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. CCS CONCEPTS• Human-centered computing → Interactive systems and tools; Natural language interfaces; • Applied computing → Document preparation.

show abstract

Section: Communication Support For Computational Notebooksmentioning

confidence: 99%

Section: Communication Support For Computational Notebooksmentioning

confidence: 99%