Skip to content

Latest commit

 

History

History
88 lines (58 loc) · 2.61 KB

README.md

File metadata and controls

88 lines (58 loc) · 2.61 KB

📰 Fake News Detector 🚫📰

Welcome to the Fake News Detector! This project is all about separating the truth from the lies in the world of news. Using powerful machine learning models, we're here to help you identify whether a news article is true or fake. Get ready to dive into the fascinating world of news classification! 🚀

🌟 Features

  • News Classification: Automatically classifies news articles as true or fake.
  • Data Preprocessing: Cleans and prepares text data for machine learning.
  • Model Training: Utilizes Logistic Regression and Decision Tree models.
  • Manual Testing: Allows users to input news text and get predictions in real-time.
  • Visualizations: Includes bar charts and pie charts for data insights.

📂 Dataset

🚀 Getting Started

Follow these steps to get your Fake News Detector up and running!

Prerequisites

  • Python 3.x
  • Pandas
  • NumPy
  • Scikit-learn
  • Matplotlib

Installation

  1. Clone the repository:

    git clone https://github.com/yourusername/fake-news-detector.git
cd fake-news-detector

  2. Install the required libraries:

    pip install pandas numpy scikit-learn matplotlib

  3. Download the dataset files:

    • Place True.csv and Fake.csv in the project directory.

Running the Project

  1. Execute the script:

    python fake_news_detector.py

  2. Manual Testing:

    • After running the script, you can enter any news text to see if it's true or fake.

🎉 Fun Features

  • Interactive Predictions: Enter your own news text and see the magic happen!
  • Engaging Visuals: Enjoy bar charts and pie charts that make data insights fun.

📊 Data Insights

  • Article Counts by Subject: Bar Chart

  • Fake vs. True News Distribution: Pie Chart

🛠️ Project Structure

  • fake_news_detector.py: The main script containing all functionalities.
  • True.csv: Dataset of true news articles.
  • Fake.csv: Dataset of fake news articles.

📞 Contact

Feel free to reach out if you have any questions or suggestions!

🎊 Acknowledgements

  • Thanks to the open-source community for providing the datasets and tools used in this project.

Happy news classifying! Stay informed and stay skeptical! 🚀📰