Text Analytics 

Asset Management NLP Project

Use the data set from the Dow Jones Newswires Machine Text Feed and Archive database for this problem set. Column Article is the cleaned words of each article.

​

Use all articles to run Latent Dirichlet Allocation (LDA) with 20 topics, then output
each topic’s top 10 keywords based on the keyword calculation in Bybee, Kelly, Manela, and Xiu (2022, “Business News and Business Cycles”)