Fake-News-Detection Using Machine Learning

The objective of this project is to create a machine learning model that can determine whether a specific news story is authentic or not. The model applies machine learning algorithms to categorise the article as legitimate or fraudulent after extracting features from the article's text using natural language processing techniques.

Dataset :

The project makes use of the Kaggle false News Dataset, which is made up of over 20,000 items classified as "real" or "fake" news. A training set and a testing set are created from the dataset.

Dependencies :

1. Python
2. Numpy
3. Pandas
4. Matplotlib
5. Seaborn
6. Scikit-learn
7. NLP

Installation:

1. Git clone https://github.com/Soubhik2002/Fake-News-Detection.git to copy the repository.

Usage :

1. Open fake_news_ detection.ipynb in Jupyter Notebook or any other Python environment.
2. To prepare the data, extract features, train the model, and assess its effectiveness, according to the notebook's instructions.
3. To predict the labels of new articles, you may also utilise the pre-trained model fake_news_model.pkl.

License :

This project is licensed under the MIT License. See the LICENSE file for details.