Surprise! Google's relevancy system isn't all algorithm based -- the search giant randomly hires contractors to test their results. Peter Norvig, a director of research at Google, revealed part of the
relevancy team's strategy in the newest issue of
Technology Review.
"[We] randomly select specific queries and hire people to say how good our results are. These are just
contractors that we hire who give their judgment. We train them on how to identify spam and other bad sites, and then we record their judgments and track against that," said Norvig.
Google then can use the human input in one of two ways, either by factoring it in to raise or lower a site's rankings manually based on the user's "thumbs up" or "thumbs down" in terms of relevancy,
or to help shape the algorithm so that it ranks better on its own.
Read the whole story at Pandia Search News »