The python notebook includes code to extract the text of the op-eds/editorials written by people affiliated with UChicago. The final output is in the form of a dataframe that includes the name of the author, the author's byline, the text of the article, the link to the article and the type of the article (op-ed, editorial etc.).
- topic modeling (LDA, NMF etc.) to get a sense of what topics people commonly write on.
- sentiment analysis using a pretrained Sentiment Analyzer.
- counting word frequencies.
- part-of-speech tagging using a pretrained POS tagger, etc.