I use various techniques for analyzing the Stanford Congressional Records.
Data: Congressional Record text documents, mainly from Stanford's repository which you can find here: https://exhibits.stanford.edu/data/catalog/md374tz9962
First I show how to build useful data structures from text documents such as: -Corpus -Document Frequency Matrix(DFM) -Dataframes -Keyword-In-Context(KWIC) Windows
Next I go over text analytic techniques such as: -Sentiment Analysis -Lexical Diversity -Readability -TF-IDF -Topic Modeling -More!