I'm not sure if you're mocking me or giving me too much credit here.. Really I was hoping to be more rigorous and go more in depth but at some point it just felt silly to hammer a website, scrape the page and never have access to the whole data. Doing this got me thinking about issues like "time of day" though as there must be a way to take into account the rate of new posts and make old posts more 'sticky' when the rate accelerates, in the morning for instance.

I feel like starting my own social news website just to have a play with different algorithms!