togelius writes "What makes games fun? Some (e.g. Raph Koster) claim that fun is learning — fun games are those which are easy to learn, but hard to master, with a long and smooth learning curve. I think we can create fun game rules automatically through measuring their learnability. In a recent experiment, we do this using evolutionary computation, and create some simple Pacman-like new games completely without human intervention! Perhaps this has a future in game design? The academic paper (PDF) is available as well."

GamerDNA is trying out what they call their Discovery Engine, a system that uses metadata from users to classify games and identify which have similar traits. Massively describes it thus: "Once the gamerDNA community continues to contribute to something like this, it builds up an enormous database of terminology based on actual player knowledge, not just shiny PR words thrown together to promote a game. These search terms can end up being unique to a specific genre, and ultimately lead gamers to exactly the types of games they're looking for." GamerDNA tested the system out on some of the popular MMOs, and they've posted the results. They look at how MMO players identify themselves within the game, how they describe the setting, and what basic descriptive phrases they use in reference to the games.