Techniators 💻 Fake News Detector 🗞️
This is a Streamlit web application that detects fake news articles using natural language processing (NLP) and machine learning (ML) algorithms.
📰 Demo
📊 Features
The Fake News Detector app can:
- ✅ Analyze the text of a news article and predict whether it is fake or real
- ✅ Show the client the prediction result of the article being fake or real
- ✅ Allow the client to input their own news article for analysis
- ✅ Display a word cloud and word frequency plot from the new article input
Technologies
This application was built using:
- Python
- Streamlit
- Scikit-learn
- Natural Language Toolkit (NLTK)
- AWS EC2
- AWS Sagemaker
- AWS S3
Installation
Local
To install and run the app locally, follow these steps:
Clone the repository: git clone https://github.com/UBC-MDS/Techniators.git
Install the required packages: pip install -r requirements.txt
Start the app: streamlit run streamlit_app.py
Docker
To install and launch the docker version of the streamlit application, follow the below steps:
docker pull caesarwongw/streamlit-docker1
docker run -p 8501:8501 caesarwongw/streamlit-docker1
For more details on the Docker Image, checkout the Docker Hub link.
Usage
Once the app is running, you can:
- Enter the text of a news article in the input area
- Click the "Submit" button to see whether the article is fake or real
- View the probability score to see how confident the model is in its prediction
- View the word cloud and frequency plot for more insights about your input news article
Contributing
Team Members: Sarah Abdelazim, Lisa Sequeira, Caesar Wong
If you'd like to contribute to the Techniators - Fake News Detector application, follow these steps:
- Read our Contributing document
- Fork the repository
- Create a new branch for your feature:
git checkout -b my-feature-branch - Make your changes and commit them:
git commit -m "Add new feature" - Push your changes to your forked repository:
git push origin my-feature-branch - Create a pull request from your branch to the main branch of the original repository
Special Thanks
We would like to extend our most sincere thanks to the HackHPC Hack the Threat hackathon organisers for providing us with the opportunity to participate part and showcase our project. We had a place to work together with people who shared our interests throughout the hackathon to accomplish a common objective. We appreciate the organisers' assistance and direction throughout the event.
License
This project is licensed under the MIT License. See the LICENSE file for details.