Fake news has become one of the major problems in the existing society, it has a high potential to change opinions, facts and it can be the most dangerous weapon in influencing society. With the current usage of social media platforms, consumers are creating and sharing more information than ever before, some of which are misleading with no relevance to reality, so the public is unable to detect all these fake news.
To address this issue, we propose a mobile application with a simple interface where you can paste the news you found on a website or social media, and test if it is real or fake. We used NLP techniques for preprocessing the corpus and Logistic Regression model to predict if the news is fake or not.
Our model is trained on two datasets, 'True.csv' and 'Fake.csv', and has achieved an accuracy of up to 98% in testing. To use our mobile application, simply copy and paste the news you want to verify into the app's input field. The app will then process the text using NLP techniques to prepare it for analysis, and feed it into the Logistic Regression model to determine its authenticity.
Our Fake News Detector Mobile Application is built using the following technologies:
- NLP (Natural Language Processing): for preprocessing the corpus.
- Machine learning: for predicting if the news is fake or not.
- KivyMD: for launching the model in the mobile application.
In the future, we plan to improve the model's accuracy by training it on more diverse and extensive datasets. Additionally, we plan to expand the mobile application's functionality by integrating more features such as voice input and real-time news analysis.
We welcome contributions from anyone who is interested in improving our Fake News Detector Mobile Application. To contribute, please fork the repository, make your changes, and submit a pull request.
By :
- Oussama QOUTI
- El Mehdi DAOUDI