Think Customers: The 1to1 Blog

NewsSift is a search engine that combs news stories, but looks nothing like the traditional Google or Yahoo! Homepage. It organizes search results by topic, organization, place, person, and theme. Instead of getting 100 URL's with a short description of each in response to a query, NewsSift provides terms in the five categories to put the search in context. The contextual and relational technology from Endeca allows NewsSift to recognize the difference between Rolling Stone magazine and the Rolling Stones, for example.

Once users have selected their target from the five lists, they can narrow down the search by adding related topics, drilling down into more specific terms, or cross-referencing across multiple categories. For example, a user can search for "Ford," then add "China," to find articles written about Ford in China.

Essentially the site eliminates long search strings with quotes on some parts and not on others, which is often the most effective way to use Google. Google is slowly embracing the idea of semantic search, which puts terms into context. However, the algorithms necessary for semantic search don't currently scale to cover Google's billions of indexed pages. However, the world's #1 search provider recently announced that queries will contain better related terms (more than just different spellings or forms of the word searched, as is the case now), which signals that Google is moving toward what NewsSift has done.

Right now NewsSift.com is in beta testing, and Financial Times is seeking input from users into how it can improve the search engine's capabilities and interface. Check out the site and comment below.