Word Cloud for SEC Data

The Securities and Exchange Commission requires U.S. stock-issuing, or publicly listed companies to file a large number of reports. These reports contain financial data annotated with text of varying lengths. In this shiny app, we have collected a small sample of recent annotations contained in the financial reports of three companies with different types of operations, and different styles of text annotation. Apple is here as an example of terse language, and GE is here as an example of verbose text. Walmart is included here to show a large retailer.

The shiny app is located here:

https://rubiera.shinyapps.io/shiny/

The text is transformed using the tm_map function of the tm packages, one of the NLP (Natural Language Processing) packages. After turning the text into a VCorpus in tm, we:

• Make all text lower case
• Remove punctuation
• Remove numbers
• Remove common words such as “the” and “and,” referred to in NLP as “stopwords.” We also removed the word “company.”
• We do not stem the text because stemming, which is the process of generalizing a word from it's various conjugations, would make the word clouds less redable.