Skip to content

README.md

Latest commit

 

History

History
96 lines (62 loc) · 4.65 KB

README.md

File metadata and controls

96 lines (62 loc) · 4.65 KB
Raw

Data Storytelling @ eScience Center

License Research Software Directory DOI

Welcome to the repository for our Tech Focus Project 2025: Data Storytelling, part of the NLeSC initiative to enhance communication and accessibility of research software through compelling, AI-powered narratives.

This repository gathers all deliverables, research, tools, and demos created during the project.

Goal: Help Research Software Engineers (RSEs) and scientists present complex research outputs using storytelling techniques, combining narrative design, data visualization, and AI tooling.

Ideation board

./README.excalidraw.png

(You can edit this board with the Excalidraw plugin for VSCode)

Project Highlights (Deliverables & Milestones)

Below is the planned list of project deliverables, based on the proposal and current progress. We aim to complete these by December 2025 unless noted otherwise (In progress...).

  • ✅ Literature Review: Systematic overview of data storytelling across domains
  • ✅ Working AI Pipelines: Modular storytelling pipeline using small LLMs
  • ✅ Interactive Web Application: 3D visualization platform with AI story generator (webapp/)
  • Training Guide: Work-in-progress handbook for data storytelling in RSE
    • Best use of LLMs, RAG model quality analysis, etc.
    • Story generation quality metrics: structure, factual accuracy, engagement, etc.
  • Use Case Application: Storytelling applied to eScience evaluation project(s)
  • Showcase Outputs: Poster, website, and internal presentation planned for December

Web Application

The webapp/ directory contains an interactive 3D visualization platform for exploring eScience Center research software projects.

Key Features

  • 3D Domain Exploration: Navigate through four research domains with unique 3D visualizations
  • Software Catalog Search: Search the full RSD software catalog beyond pre-loaded domain items
  • AI Story Generator: Generate audience-specific narratives using Google Gemini
  • Context Enrichment: Include related software and uploaded documents for richer stories
  • Export Options: Download stories as Markdown or PDF

See the full feature list and webapp README for details.

Awesome Resources

🧾 Core Documents

  • Student Literature Review (2025) — Theoretical background across journalism, finance, education, and medicine
  • MSc Thesis: Educational Data Storytelling with SLMs (Ye, 2025) — Modular AI pipeline using RAG + SLMs
  • Project Proposal (TFP25) — Official eScience Center project definition

Project Structure

📁 /docs           → Literature review, thesis, and guidelines
📁 /training       → Training materials for RSEs
📁 /examples       → Use cases and storytelling demos
📁 /tools          → Prompt templates, workflows, and helper scripts
📁 /slides         → Presentation materials for internal sharing
📁 /poster         → Visual assets for eScience Center showcase

See also:

📁 sharepoint (Requires login, members only)

Team

  • Kody Moodley - Research Software Engineer
  • Pablo Rodríguez - Research Software Engineer
  • Stefan Verhoeven - Research Software Engineer
  • Peter Kalverla - Research Software Engineer
  • Jesse Gonzalez - Project Lead - Research Software Engineer
  • Adam Belloum - Tech Lead
  • Junming Ye - Student Researcher

⸻

Contributing

This repository is for internal use at the eScience Center. However, if you’re interested in contributing examples, feedback, or tools, please contact the team.

🚀 Let’s make scientific data accessible, impactful, and memorable through better storytelling.