Thursday, January 31, 2008

Personalizing Search Results Using Social Information

VentureBeat has an interview with Google's VP Marissa Mayer about social search. Marissa's definitions for social search is "any search aided by a social interaction or a social connection... Social search happens every day. When you ask a friend what movies are good to go see? or where should we go to dinner?, you are doing a verbal social search. You're trying to leverage that social connection to try and get a piece of information that would be better than what you'd come up with on your own."

She explains that Google tried to add a social layer by allowing its users to annotate search results in Google Co-op, but that didn't work very well. "There have been a few topical areas that have had a lot of traction, but overall the annotation model needs to evolve."


Marissa Mayer suggests that Google could show you the results labeled by the people you trust, for example your Facebook friends. Google could also personalize your search results by promoting web pages bookmarked by your friends. "PageRank itself relies on the link structure of the web to try to find the most authoritative pages. For example, it's clear that people would attribute more authority to the pages that their friends have visited."

Asked about the future of search, Marissa predicted that in ten years search engines will answer to queries like "what movies are good to see?", "where's the nearest sushi restaurant that's good?" by using information from the user's social context. Basically, the social data is just another way to personalize search results, along with your search history or your location.

Once your social data becomes portable (and OpenSocial could play an important role here), Google could use aggregate information from your friends to modify the weights in a personalized PageRank model.

Related:
Google and social search
Google's no-longer-existent Facebook app

No comments:

Post a Comment