Tuesday: May 18, 2010
Brand new computer algorithm actually capable of detecting sarcasm....the team scanned 66,000 Amazon.com product reviews, with three different human annotators tagging sentences for sarcasm. The team then identified certain sarcastic patterns that emerged in the reviews and created a classification algorithm that puts each statement into a sarcastic class.
Thursday: March 4, 2010
Google would like you to know that they think PageRank is a tad over-hyped.PageRank has a catchy name and the name recognition. But we've always looked at all the things that are available when ranking search results. We look at where do things come from, what are the words used, how do they interact with each other, how do people interact with them,' he said.
Monday: November 23, 2009
Some lessons regarding pinball economics that you may not have previously known about.The early versions of this algorithm were crude, essentially targeting a weighted moving average. But later implementations were more sophisticated. The goal was to ensure that a fixed percentage, say the top 5% of all scores would win a free game.
Tuesday: September 22, 2009
Everything you always wanted to know about the Netflix prize was won.There's a lot of nerdy love goes into the kind of movie reccomendations you get out of Neflix.
Tuesday: September 1, 2009
How to build a popularity algorithm that you can be proud of.After reading this article I am not so proud of my lame 'recently popular' list over on the right side of the page.
Thursday: July 2, 2009
Algorithm changes to Facebook's friend suggestions leave some inappropriate results.Now, instead of just those inappropriate ads offering to help you with that “muffin top” or “Christian Singles” for your agnostic self, you’re also getting friend suggestions from someone’s long forgotten e-mail contacts — whether you’re still friends with that person or not.
Monday: June 29, 2009
Teams join up to qualify for million dollar Netflix prize.Two front runners in the contest, Team Pragmatic Theory and Team Bellkor in Chaos, joined forces and submitted an algorithm that was 10.05 percent better than the one Netflix uses to recommend movies to its subscribers. The result was published on the Netflix Prize leader board on Friday.