A PyTorch implementation of the paper "CSI: a hybrid deep neural network for fake news detection"
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Pooya Moini 15f092b6b6 Merge branch 'master' of ssh:// 3 months ago
src clean code 4 months ago
README.md Update 'README.md' 3 months ago
data preprocessing.ipynb clean code 4 months ago
train.ipynb fix bug 3 months ago



This project is a pytorch implementation of the paper CSI: A Hybrid Deep Model for Fake News Detection”.

Several modifications have been made on the original code including:

  • minor bugs were fixed
  • code is cleaner, standard, organized, and more understandable
  • the main model is reimplemented using Pytorch and Pytorch_lightning
  • training is integrated with Ray Tune for the sake of hyperparameter tuning

Getting started

  1. First, use the data preprocessing notebook to prepare your data for the model. You should apply the code for different splits separately.

  2. Then, use the train notebook to train your model and see the results.