The Center for the Study of Democratic Citizenship presents:
Friday, February 10th 2017
“Webscraping with R & Automated Content Analysis”
This workshop takes participants through a brief tour on how to use R to webscrape using two different methods: API webscraping. The API webscraping portion will focus on how to download twitter data (including scraping individual’s timeline as well as accessing braoder search terms) while the html portion will download State of the Union addresses.
Once we have downloaded data, we will then apply automated text analysis approaches. Specifically, this workshop focuses on dictionary-based sentiment analysis (using Lexicoder) and estimating latent policy positions from text (using Wordfish).