This repository contains my Capstone project for the Data Science Immersive course at General Assembly in NYC, July 2018, titled Classifying Political News Media Text with Natural Language Processing. In this repo you will find:
- The full technical notebook of this project
- A notebook for scraping data from News API
- A notebook for scraping data from RSS feeds
- A notebook with a simple Keras RNN model on the text data
- A folder of all the datasets I used
Import Libraries Used:
- Pandas
- NumPy
- Matplotlib
- Seaborn
- WordCloud
- NLTK
- TextBlob
- SciKitLearn
- Keras
Additional posts about this project can be found on my blog, here.
Source Credits:
- News API (Fox, Breitbart, National Review, MSNBC, CNN, Huffington Post, Vice News)
- Infowars RSS Feed
- Democracy Now! RSS Feed
Thank you for reading, and please feel free to contact me if you have any questions or comments.