Cuil.com Gets Better
March 30, 2009
I did a fly over of the Cuil.com Web site. What triggered an overflight was a Google patent; specifically, US20090070312, “Integrating External Related Phrase Information into a Phrase-Based Indexing Information Retrieval System”. Filed in September 2007, the USPTO spit it out on March 12, 2009. I discussed a chain of Dr. Patterson’s inventions in my 2007 study Google Version 2.0 here. Dr. Patterson is no longer a full-time Googler, the tendrils of her research from Xift to Cuil pass through the GOOG. When I looked at Cuil.com today (March 29, 2007), I ran my suite of test queries. Most of them returned more useful and accurate results than my first look at the system in July 2008 here.
Several points I noticed:
- The mismatching of images to hits has mostly been connected. The use of my logo for another company, which was in the search engine optimization business was annoying. No more. That part of the algorithm soup has been filtered.
- The gratuitous pornography did not pester me again. I ran my favorites such as pr0n and similar code words. There were some slips which some of my more young at heart readers will eagerly attempt to locate.
- The suggested queries feature has become more useful.
- My old chestnut “enterprise search” flopped. The hits were to sources that are not particularly useful in my experience. The Fast Forward conference is no more, but there’s a link to the now absorbed user group. The link to the enterprise search summit surprised me. The conference has been promoting like crazy despite the somewhat shocking turn out last year in San Jose, so it’s obvious that flooding information into sites fools the Cuil.com relevancy engine.
- The Explore by Category is now quite useful. One can argue if it is better than the “improved” Endeca. I think Cuil.com’s automated and high-speed method may be more economical to operate. Dr. Patterson and her team deserve a happy quack.
I am delighted to see that the improvements in Cuil.com are coming along nicely. Is the system better than Google’s or Microsoft’s Web search system? Without more testing, I don’t think I can make a definitive statement. I am certain that there will be PhD candidates or ASIS members who will rise to fill this gap in my understanding.
I have, however, added the Cuil.com system to my list of services to ping when I am looking for information.
Stephen Arnold, March 30, 2009
Comments
6 Responses to “Cuil.com Gets Better”
-
- Subscribe to Beyond Search
Feature archive
News archive
-
Thanks for getting me to take a look at Cuil again; I’ll admit that their over-hyped / under-delivered launch made me think I’d never try it again. They’ve definitely stepped up their game. But now I’d say the bar has gone up too. I’d say that they should be compared to Kosmix as their closest comparable in terms of interface goals. Both have warts; I’ll need to play with both for a while to decide which I like better.
As for the comparison with Endeca, I’d say it’s apples and oranges. The web is pretty different from the enterprise. Still, I commend them for trying to offer an Endeca-like experience on the open web–that’s ambitious. Or, as the folks at Microsoft would put it, “challenging”.
http://research.microsoft.com/en-us/um/people/sdumais/HCIR08-TeevanEtAl-Final.pdf
Daniel Tunkelang,
Perhaps Dr. Patterson has solved part of the problem. My information suggests that the Cuil.com index is Google scale.
Stephen Arnold, March 30, 2009
Scale was never their problem–when they launched last July, they (including Dr. Patterson) claimed a Google-scale index but had terrible recall:
http://thenoisychannel.com/2008/07/28/not-as-cuil-as-i-expected/
Clearly they’ve used the intervening time to focus on improve the site rather than hyping it, and I’d say it now offers an experience that is at least competitive with Kosmix.
http://www.cuil.com/search?q=beyond+search
http://www.kosmix.com/topic/beyond_search
From an architecture point of view, it may not be fair to compare Cuil, which does its own crawling and indexing, with Kosmix, which federates results from other services. But they seem to be aiming for similar experiences, which is all that users care about. Though one advantage Cuil has is that, because it uses its own index, it is much faster than Kosmix.
In any case, I’m happy to see more attention going to exploratory search, and glad that a few companies are bold enough to try to make it work on the web. These are early efforts, but they are promising.
[…] of the world–ignored it. And, just the other day, Stephen Arnold wrote a post entitled “Cuil.com Gets Better” that inspired me to take another look, even before seeing today’s post on Search […]
I found another niche search engine….
Gezzmo Search
Its the end of a good search engine.