In my last post, I described the process to retrieve PDFs of Federal Reserve speeches from the Bank for International Settlements website. This post describes my process for extracting plain text from the PDFs so I can work with it more easily.
As a first step in my analysis of Federal Reserve speeches using Natural Language Processing (NLP) techniques, I document the process of gathering Federal Reserve speeches from the Bank for International Settlements website using Python.
This post describes my experience using Hugo to create this site, as someone without experience using Hugo. Additionally, I recommend some other resources that helped me create a Hugo site from scratch.