Submission + - Indexing the Social Signal: Search & Social Me (oreilly.com)
blackbearnh writes: Search engines have gotten pretty good at indexing the semi-static web, but new information sources such as Twitter and Facebook are starting to change the game. How do you find the meaningful tweets about protests in Egypt, when they're being drowned out by a thousand times as many retweets, not to mention stuff about Justin Bieber.
Social Media guru Charlene Li thinks that finding search value in 140 character tweets requires an entirely new approach to ranking the value of information, and in a new interview, she talks about why PageRank doesn't work for this kind of real-time information, as well as how the increasing searchability of social media is changing how people use it. "With PageRank, the more links that came into a piece of content the more meaningful and important it was. That works in a static web, and it tends to lean toward things that have better longevity. When things are coming in real-time, how do you determine whether content is important or relevant to a particular search query? How do you understand the social signal and all of the metadata that surrounds it? There's very little metadata associated with a 140-character tweet."
Social Media guru Charlene Li thinks that finding search value in 140 character tweets requires an entirely new approach to ranking the value of information, and in a new interview, she talks about why PageRank doesn't work for this kind of real-time information, as well as how the increasing searchability of social media is changing how people use it. "With PageRank, the more links that came into a piece of content the more meaningful and important it was. That works in a static web, and it tends to lean toward things that have better longevity. When things are coming in real-time, how do you determine whether content is important or relevant to a particular search query? How do you understand the social signal and all of the metadata that surrounds it? There's very little metadata associated with a 140-character tweet."