📰 QuickFactChecker – Fake News Detection

🚀 Live Demo

Try it now: https://quickfactchecker.onrender.com/

📌 Project Overview

QuickFactChecker is a machine learning–based web app that helps detect whether a news article is real or fake. It uses different models (e.g., Naive Bayes, LSTM) trained on the LIAR dataset to evaluate credibility and assist users in identifying potentially misleading information.

---

🌟GSSoc

🌟 Exciting News...

🚀 This project is now an official part of GirlScript Summer of Code – GSSoC'25! 💻 We're thrilled to welcome contributors from all over India and beyond to collaborate, build, and grow QuickFactChecker! Let’s make learning and career development smarter – together! 🌟

👩‍💻 GSSoC is one of India’s largest 3-month-long open-source programs that encourages developers of all levels to contribute to real-world projects 🌍 while learning, collaborating, and growing together. 🌱

🌈 With mentorship, community support, and collaborative coding, it's the perfect platform for developers to:

• ✨ Improve their skills
• 🤝 Contribute to impactful projects
• 🏆 Get recognized for their work
• 📜 Receive certificates and swag!

🎉 I can’t wait to welcome new contributors from GSSoC 2025 to this QuickFactChecker project family! Let's build, learn, and grow together — one commit at a time. 🔥

---

✨ Features

• ✅ Fake news classification using ML models (Naive Bayes, Logistic Regression, Random Forest, and LSTM).
• ✅ Interactive web app built with Flask and HTML templates.
• ✅ Automated NLTK Setup to prevent missing resource errors.
• ✅ Preprocessed dataset included (train.tsv, test.tsv, valid.tsv).
• ✅ Notebooks for data analysis & experimentation (liar-data-analysis.ipynb, dataset.ipynb).
• ✅ Easy setup with requirements.txt.

---

📂 Project Structure

dataset/liar
   ├── README.md   ##Dataset description
   ├── train.tsv   ##Training data
   ├── test.tsv    ##Testing data
   ├── valid.tsv   ##Validation data

module/
   ├── dataset.ipynb
   ├── fake-news-detection-using-lstm.ipynb
   ├── fake-news-detection-using-nb.ipynb
   ├── liar-data-analysis.ipynb

templates/
   ├── index.html

scripts/
   ├── setup_nltk.py          
   └── fake_news_logreg_rf.py     ## Train & evaluate Naive Bayes, Logistic Regression, Random Forest
results/
   ├── model_comparison.md        ## Generated baseline comparison table (markdown)
   └── comparison.png             ## Generated accuracy bar chart

.gitattributes
app.py
hero_img.svg
LICENSE
Readme.md
requirements.txt

⚙️ Installation & Setup

1. Clone the repository and navigate into it:

   git clone https://github.com/Deepika14145/QuickFactChecker.git
   cd QuickFactChecker

2. Create virtual environment (optional but recommended)

      python -m venv venv

3. Activate the virtual environment:

      source venv/bin/activate   # for Linux/Mac
      venv\Scripts\activate      # for Windows

4. Install the required dependencies:

   pip install -r requirements.txt

5. Download NLTK Corpora:

python scripts/setup_nltk.py

📊 Baseline Model Comparison

We evaluated three models on the LIAR dataset using TF-IDF features. Example results (accuracy & precision): example:

Model	Accuracy	Precision
Naive Bayes	0.XXXX	0.XXXX
Logistic Regression	0.XXXX	0.XXXX
Random Forest	0.XXXX	0.XXXX

Logistic Regression achieved the highest accuracy among the tested baselines.

🔧 Run the comparison script

To reproduce these results, run:

scripts/fake_news_logreg_rf.py

▶️ Usage

1. Run the following command to start the application:

   python app.py

2. The app will provide predictions on whether a news article is real or fake based on the input.

🛠️ Model Training

To retrain or experiment with the models, run the provided Jupyter notebooks. Ensure your virtual environment is activated and all dependencies are installed.

Naive Bayes

Run the notebook:

jupyter notebook fake-news-detection-using-nb.ipynb

LSTM

Run the notebook:

jupyter notebook fake-news-detection-using-lstm.ipynb

Dataset Analysis

jupyter notebook liar-data-analysis.ipynb

🤝 Contributing

Contributions are welcome! Whether you’re fixing typos, improving docs, or adding new features — every PR helps. Follow these steps:

1. Fork the repository
2. Create a new branch (git checkout -b feature-name)
3. Make your changes
4. Commit your changes (git commit -m 'description of your feature/fix')
5. Push to the branch (git push origin feature-name)
6. Create a Pull Request

Please read CONTRIBUTING.md and follow our Code of Conduct.

📦 Deployment

The application is deployed on Render and accessible at: https://quickfactchecker.onrender.com/

Deployment Features:

• ✅ Free hosting on Render
• ✅ Auto-deployment from GitHub commits
• ✅ Production-ready with Gunicorn server
• ✅ HTTPS enabled by default
• ✅ Optimized requirements for faster build times

Technical Stack:

• Backend: Flask (Python)
• Server: Gunicorn
• Platform: Render
• CI/CD: GitHub integration

📧 Contact

For queries, feedback, or guidance regarding this project, you can contact the mentor assigned to the issue:

• 📩 GitHub (Owner): Deepika14145
• 💬 By commit/PR comments: Please tag the mentor in your commit or pull request discussion for direct feedback.

Original Repository: QuickFactChecker

Contributor

A heartfelt thank you to all the contributors who have dedicated their time and effort to make this project a success.
Your contributions—whether it’s code, design, testing, or documentation—are truly appreciated! 🚀

Thanks to all the wonderful contributors 💖

See full list of contribution from contributor Contributor Graph

📄 License

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

---

If you find this project useful, please give it a ⭐️! Your support is appreciated!

Feel free to contribute or suggest new features!🙏