In The Web gets Smarter, Gary Marcus writes:

Google’s algorithm doesn’t know a thing about doubled letters, transpositions, or the psychology of how humans type or spell, only what people tend to type after they make an error. The lesson, it seemed, was that with a big enough database and fast enough computers, human problems could be solved without much insight into the particulars of the human mind.

 I’ve always like the how more than the why anyway. More, here.