This dataset consists of about 40000 articles consisting of fake as well as real news. Our aim is train our model so that it can correctly predict whether a given piece of news is real or fake.The fake and real news data is given in two separate datasets with each dataset consisting around 20000 articles each.
Dataset :https://www.kaggle.com/clmentbisaillon/fake-and-real-news-dataset
- Pandas
- Numpy
- Matplotlib
- Texthero
- Nltk
- Scikit-learn