The scripts that live here are meant to reproduce results from Social and Emotional Correlates of Capitalization on Twitter (Chan & Fyshe, 2018).
Our input is from Exploring Demographic Language Variations to Improve Multilingual Sentiment Analysis in Social Media (Volkova, Wilson, & Yarowsky, 2013) and can be downloaded here. See this link on how to fetch the tweets.
Tagging was done using TweeboParser, and Google Books English 1-grams were used to approximate true frequency distributions.