A "key key-word" is one which is "key" in more than one of a number of related texts. The more texts it is "key" in, the more "key key" it is. This will depend a lot on the topic homogeneity of the corpus being investigated. In a corpus of City news texts, items like bank, profit, companies are key key-words, while computer will not be, though computer might be a key word in a few City news stories about IBM or Microsoft share dealings.
To discover "key key words" you need a lot of text files (say 500 or more), ideally fairly related in their topics, which you make word-lists of (it's much faster doing that in a batch), and then you have to compute key word-lists of each of those, all of which go into a database. It is all explained under creating a keywords database.