November 16, 2005

Hyper-Contextual Search Results with Swicki

Michael Arrington

24 comments »

Eurekster’s Swicki search service officially launches later today (November 16, 2005).

Eurekster, a twenty person company located in San Francisco and New Zealand, has a profitable business (called Search Publisher) that provides customized search results to a number of large websites. Steven Marder, Eurekster’s CEO, tells me Eurekster’s current products are generating 25+ million monthly searches.

With Swickis, they’ve taken the basic technology and added on a “do it yourself” interface to allow a much larger number of sites, particularly blogs, to also integrate search direclty into their content.

Swicki’s are “community powered” in a sense and their website focuses on this.

What is a swicki?

A swicki is new kind of search engine that allows anyone to create deep, focused searches on topics you care about. Unlike other search engines, you and your community have total control over the results and it uses the wisdom of crowds to improve search results. This search engine, or swicki, can be published on your site. Your swicki presents search results that you’re interested in, pulls in new relevant information as it is indexed, and organizes everything for you in a neat little customizable widget you can put on your web site or blog, complete with its very own buzz cloud that constantly updates to show you what are hot search terms in your community.

And certainly the community has a role in creating more relevant results. But what really interests me about their technology is that the tweaking by the publisher along with community actions combine to create extremely contextual, or hyper-contextual (my words, not theirs), search results.

Two somewhat different examples of live Swickis (they’ve been in private beta for a while): see our Web 2.0 Workgroup (scroll down a bit) and Jeff Clavier’s right sidebar.

Swicki’s are based on Yahoo’s search API for base results. The publisher customizes the search engine by adding keywords that are always added to the search results. And, in a similar way to Rollyo, Swickis allow for the publisher to name specific websites that have content relevant to the search. For instance, a gaming site may include other gaming website URLs as important, and Swicki will put results from those sites on the top. A publisher can also block results from certain blogs. For our Workgroup, we selected all participating site URLs as the most relevant content.

Swicki’s also have a related “buzzcloud”, which is a tagcloud of commonly searched terms. The buzzcould can also be edited by the publisher to add or remove terms, and a spam filter disallows any single IP from influencing the buzzcloud results too heavily.

Swickis are completely free. They will soon have contextual advertising served along with normal search results if the publisher chooses, but there will be no penalty or fee if they publisher wishes to keep advertising out. They are also adding analytics to allow publishers to monitor search statistics.

A press release should be out soon and I’ll link to it once it’s available. Check out their blog as well for a post.

Brian Benzinger posted a long review of Swickis last month when they first went into private beta. Thanks Susan for introducing me to the company.

  • Sphere It

Trackbacks/Pings (Trackback URL)

  1. Webmarketing
  2. KMS Blog » Blog Archive » Swicki search
  3. 2803, le blog
  4. Somewhat Frank
  5. 2803, le blog » Swicki, un nom à coucher dehors
  6. Dorine Rüter Weblog » Blog Archive » Swicki Search Engine
  7. transunion
  8. Búsqueda 2.0 versus búsqueda tradicional, Parte 1 » gabinetedeinformatica.net
  9. Techcrunch » Blog Archive » Google Custom Search Tomorrow
  10. Google Goes Co-operative « Ray-Deo
  11. TechCrunch Japanese アーカイブ » Google Co-op、スタート
  12. TechCrunch en français » Créez votre moteur de recherche avec Google Co-op
  13. PICnet Blog » Blog Archive » Build Your Own Search Engine through Google.
  14. Leading Information Technologies :: Search 2.0 vs Traditional Search :: November :: 2006
  15. low body temperature

Comments

RSS feed for comments on this post.

  1. Sylvain

    I’ve tried this solution. Not bad but development make me happy for the future … I am not happy to see only index of my blog in results.

  2. Tinus

    I can’t see why people would use this.

  3. Geof Harries

    At first glance, this sounds a lot like Rollyo - except Rollyo has a much nicer, simpler interface.

  4. Tinus

    I can’t see why people would use Rollyo either.

  5. Cool

    Interesting. Just went to the Web 2.0 Workgroup Swicki where you are a member and entered “TechCrunch” and “Yahoo” and you know what both became “Hot Searches”! So I don’t know where the 25 million number is coming from. What is it? Nobody cares about Web2.0 workgroup or somebody is being dishonest.

  6. Ethan

    Agree with comment 6.

    I tried to create one for “music news” and it ended up with search results that were a mess, and I lost interest in training it.

    The key problem is that it takes too much investment up front for me to tailor it to what I really want. I don’t know, just gave it another glance and something still doesn’t seem quite right.

  7. Geof Harries

    I actually find Rollyo quite useful. When I’m doing specific searches on product reviews, such as mountain bikes or laptops (2 of my actual rolls) - then it’s a great tool because the results are very focused and only come from MY trusted sources.

  8. Alexander

    When you create a specific search community, you’ll limit you yourself. Why don’t you use clustering search engines like vivisimo.com, a9.com or others?
    Another way to contextual searching is visul interface that shows only relatad terms and articles. Grokker or quintura.com for example

  9. ashish

    some search engine donot work properly