The effect of fake news has increased exponentially in the recent past and something must be done to prevent this from continuing in the future. The main purpose of this project is to come up with a classifier which can differentiate fake news from the real news. To develop an ML application to help users get notified about dubious news sources using Natural Language Processing.
Dataset - We used real or fake news dataset from Kaggle.com in our project to evaluate the semantic feature.
Text pre-processing - we pre-process the raw text to extract semantic features for machine learning.
1). Tokenisation
2). Removing Stopwords
3). Lemmetisation
Trained the model.
Compared the models and their accuracy.
Worked on frontend and backend part.
- Python and several of its libraries like scikit-learn, matplotlib, numpy and pandas for building the model.
- Front-End: HTML, CSS and Javascript
- Back-End API : Flask