I have been working with text mining and NLP for 20+ years but I bought this tutorial this morning because it looked interesting. I watched just the 20 minute introduction during lunch, and it framed machine learning in an interesting way. The video production itself is also well done.
Another positive comment: I find myself stopping the video to set up tools that she is using (e.g., the JSONview Chrome plugin, Peter Skomoroch's dataset bookmarks, and I just signed signed up for several New York Times APIs).
Also good advice from the video: ask politely for data. About 12 years ago, I wanted access to a large corpus of news stories and none of the national news web sites I contacted would respond to my requests for legal access to their data (i.e., scraping their sites). I then contacted a local paper we subscribed to (Arizona Republic), told them I was a customer, exactly what I was going to use the data for, etc. I received a permission letter fairly quickly.
