Text mining introduces the term n-gram. An n-gram is a group of n words or characters which follow one another. The 2-grams in “I love Autumn” are: “# I”( # indicates the beginning), ‘I love” “love Autumn”, “Autumn #” (# is the end). The same can be done with groups of letters.
A TED video (https://lnkd.in/dJUmV9Q) shows the evolution of words in books. My favorite is the spelling of ‘argh’. It appears more often than ‘aargh’. ‘Aaaargh’ appears the least, but has a curious bump in popularity in the mid 1980s and early 2000s. ‘Argh’ has been used since at least the 18th century and is an onomatopeia expressing annoyance. In the movie Hoodwinked, an actor auditioning as a woodcutter in a bunyon cream commercial improvises his lines by adding ‘argh’. The director replies dryly: “Argh? What are you a pirate?” Were there more writings about annoyance in the mid 1980s and early 2000s, or about pirates?
Google’s Ngram application allows text mining their digitized books: ‘star trek’ occurs more often than ‘star wars’ finally settling that popularity question. But, an article in Wired warns that an obscure technical article appears once, just as ‘The Lord of the Rings’. Ngram doesn’t take into account how often each is read. Sorry Trekkies.