/FakeNewsDetection

A Benchmark Study on Machine Learning Methods for Fake News Detection

Primary LanguagePython

Basic Info

This repo contains the implementation of a benchmark study on machine learning methods for fake news detection.

Requirements

  • Python
  • Numpy
  • Pandas
  • Keras
  • tqdm

Materials Used

  • Liar Dataset
  • Fake-or-real news Dataset
  • Combined Corpus

Models Evaluated

  • Traditional Machine Learning Models: SVM, LR, Decision Tree, AdaBoost, Naive Bayes, K-NN
  • Deep Learning Models: CNN, LSTM, Bi-LSTM, C-LSTM, HAN, Conv-HAN, Char-level C-LSTM
  • BERT-based Models: BERT, RoBERTa, DistilBERT

Code

You will find the codes of this project under the 'Codes' directory.