Precision and Recall

Tim Bray posts his third in the series on Search. This one is on Precision and Recall. Here are a few good quotes:

“While precision and recall are very helpful in talking about how good search systems are, they are nightmarishly difficult to actually use, quantitatively. First of all, the notion of “relevance” is definitely in the eye of the beholder, and not, in the real world, a mechanical yes/no decision. Secondly, any information base big enough to make search engines interesting is going to be too big to actually compute recall ….”

“…while Microsoft is not, at the moment, a real force in the search community, that may change.”