Nice, but isn't Steve Jobs something of a statistical outlier due to his recent death? Also, I'd be curious to see the results after common words like "my, I, do, etc.." were removed.
The words they ranked are also some of the most common words in the English language (Who, What, Why, How), words that get used in posts by theme (Ask, Developer), or pronouns (I, me).
What they should have done is to exclude these extremely common words and then rank what was left, like Google, Facebook, Steve Jobs. Those would have been far more valuable, but much noisier data.
I would love to see an analysis that measures hotness in a different way: The ratio of the word making it to the front page to the word being used in any submission.
e.g. "Coffeescript" made it to the front page 90% of the time it was submitted. v.s. "ASK" which only made it 3%
16 comments
[ 2.4 ms ] story [ 58.0 ms ] threadWhat they should have done is to exclude these extremely common words and then rank what was left, like Google, Facebook, Steve Jobs. Those would have been far more valuable, but much noisier data.
"Ask HN: Why doesn't Google make Python run on Android? And what you can you do about it? (Jonathan Ive)"
e.g. "Coffeescript" made it to the front page 90% of the time it was submitted. v.s. "ASK" which only made it 3%
There is no mention of "Dropbox" anywhere. Are you kidding me?