mihail911/fake-news
Building a fake news detector from initial ideation to model deployment
Implements dual classification approaches—a Scikit-learn random forest baseline and a RoBERTa transformer model via PyTorch Lightning—with experiment tracking through MLflow and data versioning via DVC. The pipeline includes SHAP-based model interpretability, Great Expectations data validation, and PyTest-driven testing, deployed as a FastAPI/Gunicorn REST service containerized with Docker and integrated into a Chrome extension for end-user interaction.
167 stars.
Stars
167
Forks
64
Language
Jupyter Notebook
License
AGPL-3.0
Category
Last pushed
Feb 15, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/mihail911/fake-news"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
palewire/storysniffer
Inspect a URL and estimate if it contains a news story
FakeNewsChallenge/fnc-1-baseline
A baseline implementation for FNC-1
google-research/fool-me-twice
Game code and data for Fool Me Twice: Entailment from Wikipedia Gamification...
pmacinec/fake-news-datasets
This repository contains list of available fake news datasets for data mining.
ICTMCG/fake-news-detection
This repo is a collection of AWESOME things about fake news detection, including papers, code, etc.