Skip to content

A project on detecting fake news from text and graph data features. Using combinations of simple unsupervised and supervised learning methods we obtain performances comparable to advanced SOTA models. See uploaded pdf for further details.

License

Notifications You must be signed in to change notification settings

albertkjoller/FakeNewsDetection

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

81 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FAKE NEWS DETECTION - FakeNewsNet

Setup

First, create an environment

conda create -n 02807 python=3.11
conda activate 02807

Now, install the requirements:

pip install -r requirements.txt

Data

Go to this webpage and download the dataset. Create a folder namesd ./data/raw/FakeNewsNet and copy all the downloaded files to this location.

About

A project on detecting fake news from text and graph data features. Using combinations of simple unsupervised and supervised learning methods we obtain performances comparable to advanced SOTA models. See uploaded pdf for further details.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 99.9%
  • Other 0.1%