Text Analytics

For this project my group and I web scrapped 2,000 articles from the news site, 'The Hill'. We performed topic clustering using machine learning models to group similar articles and conducted sentiment analysis to identify whether each article was positive, negative, or neutral. Lastly, we plotted the occurrences and correlation of the most common words throughout all the articles. 

*Google Drive sites does not support .ipynb files so I copied our code into .doc files.