Summary Statistics for Text Analysis

[#1]

I am trying to get information on both a whole book and also by chapter. Is there a quick of doing that besides running the analysis twice? (For instance I would like to know how often a word occurs in a book and also in a chapter.)

I am also trying to find out if certain words occur in proximity to other words. Is there a quick test for this? (For instance does "work" occur within 7 words of "injury".)

[#2]

I suggest you add a new data column that identifies the chapter. I believe you have to run the analysis twice. I recommend starting with the entire book to curate the term list and develop your summaries. Save the script for the curated analysis. Click the red triangle to reveal the platform menu and select Redo > relaunch Analysis. Select the Chapter column and click By before clicking OK. This will then perform the same curated analysis separately for each chapter.

You could save the document term matrix with an appropriate transform and then perform a hierarchical clustering analysis to assess proximity.