This is a very good article which would those who are more interested in the technical side of how search works. The article is based on an interview with Googler Peter Norvig, Director of Research and the previous Director of Search Quality . The most intriguing point, usage data is not a good metric for the quality of search results:
Peter confirmed that Google does collect such data, and has scads of it
stashed away on their clusters. However -- and here's the shocker --
these metrics are not very sensitive to new ranking models! When Google
tries new ranking models, these metrics sometimes move, sometimes not,
and never by much. In fact Google does not use such real usage data to
tune their search ranking algorithm. What they really use is a blast
from the past. They employ armies of "raters" who rate search results
for randomly selected "panels" of queries using different ranking
algorithms. These manual ratings form the gold-standard against which
ranking algorithms are measured -- and eventually released into service.
No comments:
Post a Comment