News Scraping and Sentiment Analysis
Newspaper Scraping and Sentiment Analysis
Summary
The goal of this project is to scrape newspaper websites for headlines and full articles and to perform sentiment analysis on the text.
Tools
- feedparser
- json
- newspaper
- nltk
- SentimentIntensityAnalyzer
Data
Headlines and full articles were scraped from newspaper and news websites, including New York Times, Los Angeles Times, USA Today, CNN, MSNBC, NPR, BBC, Huffington Post, Politico, The Guardian, Brietbart, Infowars, NBC News, and the Washington Post.
Results
Sentiment analysis of full text vs headlines:
