by Julia Kułacz
This repository contains an application to detect fake news using three different approaches:
- Naive Bayes model
- LSTM recurrent neural network
- Transfer learning approach - BERT
Each of the above has a separate folder that contains python code to detect fake news and the performance of each approach.
All data was collected from Kaggle and divided into fake and real news datasets.
This project has been carried out as a part of an engineering thesis at AGH University of Science and Technology.