[SSteffin]

You are starting backwards. To do any analysis of a text document, you have to begin by determining the question(s) for which you are seeking answers.

This is true in any kind of research. Defining the question(s) is the first step. Next, you determine, acquire, and format the data which will provide the basis for answering your question(s).


If you give me a sample of the text you are analyzing (just do an attachment in your reply), and the analysis you are trying to perform, I’ll suggest some possible statistical approaches which may be useful.