This project uses the twitter api to automatically generate tweets based on what is commonly tweeted. It
listens to the general tweetstream and captures fragments. By randomly recombining those fragments something
that reads almost like real tweets appears. It also gives an interesting insight into what the average user
uses twitter for.
You can checkout the code of the bot from Github. The
basic strategy is not complicated. First the program samples starts of tweets and picks a common start of two
words. Then based on that start of a tweet it searches twitter for the most common next word in the recent
There's a blog post that goes into some the observations around the generated stream.