Yahoo Uses Twitter To Filter The News

When US Airways 1549 went down in the Hudson River yesterday, some of the first pictures of the event were posted via Twitter, the online and mobile messaging system that allows users to instantly post 140-character missives as well as hyperlinks to pictures and web pages. Twitter has, in effect, given anyone with a cell phone the ability to send immediate, eyewitness news updates out over a public wire.

Now, Yahoo is using the immediacy of Twitter to make its own news service better: the company’s researchers have launched a simple search engine called TweetNews that ranks Yahoo News stories by using information about the most recent, frequently-tweeted topics on Twitter.

This is an important move because automatic aggregators such as those used by Google News and Yahoo’s standard news site, tend to be slower than community-driven news sites like Digg.com or Twitter. (See “The Speed of Social News Sites.”)

Yahoo researcher Vik Singh explains in a blog post that normally, “recent” Yahoo News stories are ranked according to the time at which they are published–a measure that effectively ignores the wider relevance of a story. To get around this problem, Singh tapped BOSS, Yahoo’s open-source search engine, to built a specialized search engine that monitors recent tweets to determine breaking topics and select relevant stories from Yahoo News.

From Singh’s post:

Freshness (especially in the context of search) is a challenging problem. Traditional PageRank style algorithms don’t really work here as it takes time for a fresh URL to garner enough links to beat an older high ranking URL…I remember when I saw breaking Twitter messages describing the California Wildfires. When I searched Google/Yahoo/Microsoft right at that moment I barely got anything (< 5 results spanning 3 search results pages)….Specifically, the Twitter messages were providing incredible focus on the important subtopics that had yet to become popular in the traditional media and news search worlds.

What I found most interesting in both of these cases was that news articles did exist on these topics, but just weren’t valued highly enough yet or not focusing on the right stories (as the majority of tweets were). So why not just do that? Order these fresh news articles (which mostly provide authority and in-depth coverage) based on the number of related fresh tweets as well as show the tweets under each. That’s this service.