https://github.com/zohaib-cheema/defacto
DeFacto is a machine learning-based tool that classifies fake news articles using a hybrid model built with Scikit-learn, TensorFlow, and Keras. The system analyzes social and political content to detect deception in news stories and social media posts, providing a reliable solution to address the growing issue of misinformation.
https://github.com/zohaib-cheema/defacto
flask git keras numpy pandas r scikit-learn tensorflow
Last synced: 11 months ago
JSON representation
DeFacto is a machine learning-based tool that classifies fake news articles using a hybrid model built with Scikit-learn, TensorFlow, and Keras. The system analyzes social and political content to detect deception in news stories and social media posts, providing a reliable solution to address the growing issue of misinformation.
- Host: GitHub
- URL: https://github.com/zohaib-cheema/defacto
- Owner: zohaib-cheema
- Created: 2025-03-22T05:38:47.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2025-03-22T05:54:19.000Z (11 months ago)
- Last Synced: 2025-03-22T06:25:59.569Z (11 months ago)
- Topics: flask, git, keras, numpy, pandas, r, scikit-learn, tensorflow
- Language: R
- Homepage:
- Size: 0 Bytes
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# DeFacto: Fake News Detection System
**DeFacto** is a machine learning-based tool that classifies fake news articles using a hybrid model built with **Scikit-learn**, **TensorFlow**, and **Keras**. The system analyzes social and political content to detect deception in news stories and social media posts, providing a reliable solution to address the growing issue of misinformation.
## Features
- **Fake News Detection:** Classifies news articles and social media posts as real or fake based on the content.
- **Model Training:** Built using **Scikit-learn**, **TensorFlow**, and **Keras** for high accuracy in detection.
- **Data Preprocessing:** Data is preprocessed and features are engineered using **R**, **Pandas**, and **NumPy**, optimizing model performance and reliability.
- **Real-Time Classification:** Users can input articles or posts for immediate classification.
- **User-Friendly Interface:** Simple interface for quick and easy analysis of content.
## Tech Stack
- **Machine Learning Libraries:** **Scikit-learn**, **TensorFlow**, **Keras** for model building and training.
- **Data Science Tools:** **R**, **Pandas**, **NumPy** for feature engineering and preprocessing.
- **Frontend (optional):** Flask (if you want to create a web interface for the app).
- **Version Control:** Git for collaboration and code management.