I have a number of interview transcriptions that I am hoping to run text mining analyses on. Basically trying to automate the qualitative coding procedure.
I've been reading up on tidytext text mining, but it only seems to use already imported datasets! How do I actually import a .docx file into R to start using tidytext functions?
I found a package from Github (textreadr) that says it can import transcripts, but I can't quite follow the commands used to load the data.