Launched this week is a new search engine that performs a task the developers call ‘fact extraction’ – that is, it gets the facts for you, instead of you having to hunt through the links provided in traditional search results. It’s called Factery Labs and it’s been generating a lot of talk this week.
It extracts facts by using its FactRank technology (bet you can guess how they came up with that name), which mines real-time feeds and web content in order to provide simple, short answers to user queries. In other words, it will save you time if you just want the facts.
The ‘facts’ found by FactRank are small pieces of information from the source pages, which are organized into order of importance by an advanced algorithm.
The process goes like this: the user enters their query, and then Factery’s search bots get to work. They call the Twitter Search and Yahoo Boss’ APIs to request link sources. The bots go to the source pages, extract the content you’re looking for, and assemble them for you.
So, let’s give it a try. This reporter typed in “Australia Day” (which it happens to be on January 26th) into the search bar. The results don’t seem particularly informative on the Twitter side, where none of the facts suggested have anything to do with Australia Day. To the right of the page are facts from Yahoo, which are significantly better, explaining what Australia Day is, what it commemorates, how it has evolved, and the like.
A second try, using the keyword “Nexus One” delivers better results. We learn from Twitter the problems users are already experiencing with the new Google phone, and complaints about the fact that Google is censoring certain words in text messages. From Yahoo, we learn more practical facts, like the size of the phone, the applications that come with it, and where it is manufactured.
Overall, the search results seem to need some work. It’s a great idea, but not everything listed in the results is a fact, many of the results are repetitive, and significant facts are missing. That being said, it is an interesting concept and could have a bright future, with some tweaking.
Another problem the search engine seems to have is that it doesn’t fit the screen of all computers. On this reporter’s Asus netbook, the search page requires horizontal scrolling – not an attractive feature.
The site has been much buzzed about lately, with articles proclaiming its uniqueness popping up on CNet, TechCrunch, BusinessWeek, and Search Engine Land.
According to CNet’s report on the new engine on the block, developers are soon likely to make use of the FactRank technology in third-party search engines or on Web pages to very quickly deliver reading summaries, cutting out most of the unimportant information, and getting straight to the meat of the matter.
The company was founded by two men named Paul Pedersen and Sean Gaddis, both of whom have previous experience working for the likes of Google, Skype, and eBay.
The program is still in Alpha. They’re looking for feedback on the search engine, so best to send them your comments here. Give it a try! You might learn something.
Kaila Krayewski is a freelance journalist with a passion for all things internet. Having worked for nearly two years as the public relations manager for an internation search engine optimization company, and publishing hundreds of articles (how-to, informational, and otherwise) on SEO, she knows a thing or two about the field. Furthermore, having just started up her own website blondetraveler.com, she is doing her best to keep one step ahead of the search engines in order to keep the traffic flowing.
Read other articles by Kaila Krayewski
