The supreme court is a very complex and difficult to understand topic for anyone without a law degree, which is why this is an interesting topic for natural language processing. The main question for this project was 'who will the current nominee be most like if they become a supreme court justice'. I applied NLP (t-FIDF) to a sample of 10,000 opinions over the course of 200 years of the court, in addition to Garland's constitutional law opinions, with a dataviz for helping communicate this information in mind.
The Jupyter Notebooks in this repo include the methods by which I gathered and modeled the data for my dataviz which is here.