Apologies beforehand, this is outside my comfort zone.
I have a table in Excel with a list of ca. 100 items. Each of the items has a number of tags associated with it, indicated by a TRUE value in one or more of the 15 columns (which represent the tags).
There are 2 things I would like to explore and visualize:
- which tags are closely related, meaning they are often tagged to the same item
- which items are closely related, because they often share the same tags
- overlap and 'mutual exclusion' of items tagged P, items tagged Q, and items tagged P+Q – like in a Venn diagram.
My purpose is exploratory, trying to get some kind of 'clustering' of items. I'm aware that throwing data against the wall to see what sticks will probably not reveal meaningful statistically sound answers.
In case there's tooling involved other than Excel or Numbers, I'm using MacOS.
Thanks for bearing with me!
