This repo contains an IPython notebook to topic model every speech made by a President of the United States. The purpose of this project is to be able to quickly identify trending issues of their time using GENSIM's LDA model.
The corpus contains a total of 962 speeches organized into directories from President Washington to President Obama. No public data currently exists for President Trump, so we included a different corpus of the speeches he made during his Presidential Campaign in 2016.
You can view our data products in the VisualizeTopics.ipynb
and SentimentAnalysis.ipynb
files.