text mining and words counting problem
I'm new to rapidminer and I have an analysis now with several txt document. Let's say I have get the most 20 frequently appear words and I want to know (and only know) how many times they show up in each document, can some one give me some ideas?
Also I have a problem that I find "united", "states" and "united_states" all appear in my result but I can't just replace them because not all "united" are related to "united states". How can I drag those "united_states" out without counting on "united" and "states"?