I have a question. I believe that there may be several linguistic threads that exist side by side that are cross cultural. It's difficult to explain, but in essence, I believe that there are groups of books that are read by certain cultural groups regardless of language or genre. Each of these cohorts of books have differing language within them, which themselves may alter the way people think (to the extent that free will is governed by the language we use). It may be possible to catalog and document what these cultural book strains are using a neural networks and language clustering, but I don't know the amount of work that would be needed to make a project useful and falsifiable. I think this could have several useful applications. Here's a bit of what I'm describing -
https://www.facebook.com/permalink.php?story_fbid=pfbid02hn6WjzLmdKNjPxzPwJjfGVZdNPHE6cJ4kB6MMYMW8UVChB59UFuSroMBxCnbFu68l&id=1923611
If anyone has any input please let me know. Thanks!