joshchang0111/EMNLP2023-RumorDAS

Original PyTorch Implementation for the EMNLP 2023 Paper "Beyond Detection: A Defend-and-Summarize Strategy for Robust and Interpretable Rumor Analysis on Social Media"

14
/ 100
Experimental

This project helps social media analysts and misinformation researchers identify and understand rumors more effectively. It takes social media conversation threads, like those from Twitter, and not only detects if a rumor is present but also provides a concise summary of the key messages, even when the information is deliberately misleading. The output is a robust rumor analysis and an interpretable summary, enabling users to grasp the core of a potentially false narrative.

No commits in the last 6 months.

Use this if you need to go beyond just flagging rumors to also understand the essence of how they spread and what information they contain, especially when dealing with intentionally obscured content.

Not ideal if you're looking for a simple, off-the-shelf application or a front-end tool for rumor analysis, as this project is a research implementation requiring technical setup.

social-media-analysis misinformation-detection rumor-analysis content-summarization online-trust-and-safety
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

Last pushed

Dec 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/joshchang0111/EMNLP2023-RumorDAS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.