https://github.com/oren0e/fake-news

Using deep learning to train a model to distinguish between fake and real news
https://github.com/oren0e/fake-news

Last synced: 24 days ago
JSON representation

Using deep learning to train a model to distinguish between fake and real news

• Host: GitHub
• URL: https://github.com/oren0e/fake-news
• Owner: oren0e
• License: gpl-3.0
• Created: 2020-07-23T18:15:24.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2023-01-06T13:30:30.000Z (almost 2 years ago)
• Last Synced: 2024-01-26T14:58:13.112Z (10 months ago)
• Language: Jupyter Notebook
• Size: 2.58 MB
• Stars: 1
• Watchers: 2
• Forks: 1
• Open Issues: 20
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Fake News Classifier

## Overview

This is an LSTM RNN model that classifies news stories as fake or not.  

At this point, the answer is the probability of a given story to be fake.

The data for training this model is taken from: https://www.kaggle.com/clmentbisaillon/fake-and-real-news-dataset

The app uses Flask as the backend service. Model is stored on S3.

## Usage

Go to https://fake-news-ap.herokuapp.com/

![https://fake-news-ap.herokuapp.com/](demo/fake_news_gif.gif)

## TODO

1. Improve logging