We employ a Long Short-Term Memory (LSTM) network trained on two datasets, the Politifact fact-check dataset (https://www.kaggle.com/datasets/rmisra/politifact-fact-check-dataset/data) and
the WELFake fake news dataset(https://www.kaggle.com/datasets/saurabhshahane/fake-news-classification/data). The Politifact dataset contains texts from news articles, social media, speeches, etc.
which have been labelled as varying degrees of true or false: pants-fire, false, mostly-false, half-true, mostly-true and true.
The WELFake dataset is a larger corpus of text containing both fake and true news articles to classify whether a given
news item is genuine or fabricated.