Computational Newsroom: Analyze Crisis Information Flow on Social Platforms
Overview
What this challenge is about.
Receive an anonymized 72-hour dataset of posts, reposts, quotes, and replies (10M events) tagged to the public-health alert. Build a temporal repost-and-reply network at minute granularity. Identify: super-spreaders (high out-degree, high reach), bridges (cross-community brokers), and dampeners (high-credibility accounts that quoted corrections). Visualize the diffusion as an interactive Sigma.js or D3 timeline. Write a 12-page publication-ready piece following ICFJ (International Center for Journalists) data-journalism standards (methodology section + uncertainty disclosure). Deliver: model + Jupyter analysis, interactive visualization, and the publication piece.
The Brief
What you'll do, and what you'll demonstrate.
Reconstruct and publish the 72-hour temporal information flow of a public-health alert, identifying structural roles in propagation.
Earning criteria — what you'll demonstrate
- Build temporal repost networks at minute granularity from raw events
- Identify super-spreaders, bridges, and dampeners structurally
- Design diffusion visualizations that don't overclaim causation
- Write data journalism that meets ICFJ uncertainty-disclosure standards
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Product Manager
Product managers who understand temporal information flow can scope integrity features that target structural roles, not just content.
This challenge sharpens
- computational-journalism
- network-science
- data-analysis