<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Surf Canyon &#187; Recommendations</title>
	<atom:link href="http://blog.surfcanyon.com/category/recommendations/feed/" rel="self" type="application/rss+xml" />
	<link>http://blog.surfcanyon.com</link>
	<description>Unleash the Power of Search</description>
	<lastBuildDate>Wed, 25 Jan 2012 21:45:20 +0000</lastBuildDate>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.1</generator>
		<item>
		<title>UCD Paper on Recommender System Approach to Enhance Web Search</title>
		<link>http://blog.surfcanyon.com/2010/10/18/ucd-paper-on-recommender-system-approach-to-enhance-web-search/</link>
		<comments>http://blog.surfcanyon.com/2010/10/18/ucd-paper-on-recommender-system-approach-to-enhance-web-search/#comments</comments>
		<pubDate>Mon, 18 Oct 2010 22:31:36 +0000</pubDate>
		<dc:creator>Surf Canyon</dc:creator>
				<category><![CDATA[Recommendations]]></category>
		<category><![CDATA[Research]]></category>
		<category><![CDATA[Testimonials]]></category>

		<guid isPermaLink="false">http://blog.surfcanyon.com/?p=405</guid>
		<description><![CDATA[At the 19th Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2008), researchers from the School of Computer Science and Informatics at the University College Dublin, Ireland, published a fascinating research paper entitled &#8220;A recommender system approach to enhance web search and query formulation.&#8221; They begin by observing that &#8220;the traditional search interface has [...]]]></description>
			<content:encoded><![CDATA[<p><img class="alignleft size-full wp-image-408" title="UCD Logo" src="http://blog.surfcanyon.com/wp-content/uploads/2010/10/UCD-Logo.jpg" alt="" width="112" height="112" align="left" />At the 19th Irish Conference on Artificial Intelligence and  Cognitive Science (<a href="http://www.cs.ucc.ie/aics08" target="_blank">AICS 2008</a>), researchers from the School of Computer Science and Informatics at the University College Dublin, Ireland, published a fascinating <strong><a href="http://irserver.ucd.ie/dspace/handle/10197/1205" target="_blank">research paper</a></strong> entitled &#8220;A recommender system approach to enhance web search and query formulation.&#8221;</p>
<p>They begin by observing that &#8220;the traditional search interface has remained relatively static&#8221; before going on to describe &#8220;a recommender system approach to Web search which allows users to dynamically interact with the result-space that is of interest to them,&#8221; which they see as &#8220;an <em>overlay interface</em> as a complement to an existing search engine.&#8221;  This will sound familiar to anyone who has used <a href="http://www.SurfCanyon.com" target="_blank">Surf Canyon</a>, which the researchers acknowledge (emphasis added):</p>
<blockquote><p>&#8220;&#8230; <strong>Surf Canyon is an excellent example of a next-generation approach</strong>, and allows users to interact with results returned by existing engines; in short, users can select a result and receive recommendations drawn  from related results that appear further down a result list. Surf Canyon launched in the latter stages of our own research and presents an interface similar to what is proposed here.&#8221;</p></blockquote>
<p>While there are significant differences in terms or implementation, their results are similar to what Surf Canyon has <a href="http://blog.surfcanyon.com/2008/12/01/evaluating-surf-canyon’s-technology-part-2/" target="_blank">demonstrated</a>:</p>
<blockquote><p>&#8220;A key question is whether the resulting recommendations were found to be relevant. In fact&#8230; at least one of the 3 recommended results was selected approximately 25% of the time, a very significant indicator of relevance&#8230;&#8221;</p></blockquote>
]]></content:encoded>
			<wfw:commentRss>http://js-kit.com/rss/blog.surfcanyon.com/p=405</wfw:commentRss>
		<slash:comments>2</slash:comments>
		</item>
		<item>
		<title>Discovering Discovery</title>
		<link>http://blog.surfcanyon.com/2007/10/11/discovering-discovery/</link>
		<comments>http://blog.surfcanyon.com/2007/10/11/discovering-discovery/#comments</comments>
		<pubDate>Thu, 11 Oct 2007 17:43:51 +0000</pubDate>
		<dc:creator>Surf Canyon</dc:creator>
				<category><![CDATA[Discovery]]></category>
		<category><![CDATA[Recommendations]]></category>
		<category><![CDATA[Tutorials]]></category>

		<guid isPermaLink="false">http://blog.surfcanyon.com/2007/10/11/discovering-discovery/</guid>
		<description><![CDATA[Here&#8217;s a quick 1, 2, 3 to help you get the most out of Surf Canyon&#8217;s Discovery Engine for Search™. Step 1: Enter you query at search.SurfCanyon.com or, if you like, download our add-on and then go to your favorite search engine (Google, Yahoo! or Bing), just like you always do, and enter your keywords. [...]]]></description>
			<content:encoded><![CDATA[<p>Here&#8217;s a quick 1, 2, 3 to help you get the most out of Surf Canyon&#8217;s Discovery Engine for Search™.</p>
<p><strong>Step 1:</strong> Enter you query at <a href="http://search.SurfCanyon.com" target="_blank">search.SurfCanyon.com</a> or, if you like, <a href="http://www.surfcanyon.com/extension.jsp" target="_blank">download our add-on</a> and then go to your favorite search engine (Google, Yahoo! or Bing), just like you always do, and enter your keywords.</p>
<p>Our example will use a search for the term “dolphins” since it is often used to illustrate one of the classic problems with information retrieval. No matter how much information is gathered about the subject, the individual, or all the individuals who have ever searched for “dolphins”, it is impossible to know <em>a priori</em> whether or not the searcher’s intent is related to the animal or to the football team. While search engines may suggest alternate queries or reformulations through the use of keyword suggestions or clusters, the search results produced will always be a mix of the animal and the football team.</p>
<p><a href="http://blog.surfcanyon.com/wp-content/uploads/2008/02/discovering-discovery-_1.jpg" title="Football and animal mixed together on results page"><img src="http://blog.surfcanyon.com/wp-content/uploads/2008/02/discovering-discovery-_1.jpg" title="Football and animal mixed together on results page" alt="Football and animal mixed together on results page" align="middle" height="400" width="500" /></a></p>
<p><a href="http://blog.surfcanyon.com/?attachment_id=8" rel="attachment wp-att-8" title="Screen Shot of Query for “Dolphins”"></a><a href="http://blog.surfcanyon.com/wp-content/uploads/2007/10/dolphins-screen-shot.jpg" title="Screen Shot of Query for “Dolphins”"></a></p>
<p><a href="http://blog.surfcanyon.com/wp-content/uploads/2007/10/dolphins-screen-shot.jpg" title="Screen Shot of Query for “Dolphins”"></a></p>
<p><strong>Step 2:</strong> Review the results and select the one that corresponds to your interests. If it&#8217;s the Miami Dolphins that you like, click #2: MiamiDolphins.com. If your search is satisfied, great! If not, return to the search results and Surf Canyon will provide you with some &#8220;Recommendations&#8221;. You may, if you like, also get the &#8220;instant&#8221; Recommendations by simply clicking the bull&#8217;s eye next to the particular link of your choice.</p>
<p><a href="http://blog.surfcanyon.com/wp-content/uploads/2008/02/discovering-discovery-_2.jpg" title="Recommended search results for MiamiDolphins.com"><img src="http://blog.surfcanyon.com/wp-content/uploads/2008/02/discovering-discovery-_2.jpg" title="Recommended search results for MiamiDolphins.com" alt="Recommended search results for MiamiDolphins.com" align="middle" height="400" width="500" /></a></p>
<p>Recommendations are <em>dug out</em> of the search results based on the Discovery Engine&#8217;s inference of our real-time intent. Put another way, Surf Canyon figures out what you want and then goes past the first page of the results and fetches it for you.</p>
<p><strong>Step 3:</strong> The process is cumulative, so continue clicking on links and bull&#8217;s eyes that are of interest to you. The longer you work on the result set, the better Surf Canyon understands your intent and the more accurate are the Recommendations. The Recommendations can nest to three levels, enabling you to &#8220;drill down&#8221; on not just your high-level intent, but your sub-intents as well, such as &#8220;Miami Dolphins news.&#8221;</p>
<p><a href="http://blog.surfcanyon.com/wp-content/uploads/2008/02/discovering-discovery-_3.jpg" title="Second level of Recommendations for Miami Dolphins news"><img src="http://blog.surfcanyon.com/wp-content/uploads/2008/02/discovering-discovery-_3.jpg" title="Second level of Recommendations for Miami Dolphins news" alt="Second level of Recommendations for Miami Dolphins news" align="middle" height="400" width="500" /></a><a href="http://blog.surfcanyon.com/wp-content/uploads/2008/02/discovering-discovery-_1.jpg" title="Football and animal mixed together on results page"> </a></p>
<p>Click on &#8220;More Results&#8221; and you&#8217;ll get a second page of results automatically customized to your intent. In this case, they are naturally all related to the Miami Dolphins football team and are geared towards news.</p>
<p><a href="http://blog.surfcanyon.com/wp-content/uploads/2008/02/discovering-discovery-_4.jpg" title="Subsequent pages of results are customized in real-time"><img src="http://blog.surfcanyon.com/wp-content/uploads/2008/02/discovering-discovery-_4.jpg" title="Subsequent pages of results are customized in real-time" alt="Subsequent pages of results are customized in real-time" align="middle" height="400" width="500" /></a></p>
<p>Keep going and Surf Canyon will keep working to help you find what you need.</p>
<p>That&#8217;s Discovery!</p>
<p>Lastly, don&#8217;t worry about &#8216;mistakes&#8217;: clicking the links that are perhaps not of interest. Surf Canyon is smart enough to handle it.</p>
]]></content:encoded>
			<wfw:commentRss>http://js-kit.com/rss/blog.surfcanyon.com/p=7</wfw:commentRss>
		<slash:comments>15</slash:comments>
		</item>
		<item>
		<title>Recommendations are not &#8220;Similar Pages&#8221;</title>
		<link>http://blog.surfcanyon.com/2007/09/28/recommendations-are-not-similar-pages/</link>
		<comments>http://blog.surfcanyon.com/2007/09/28/recommendations-are-not-similar-pages/#comments</comments>
		<pubDate>Sat, 29 Sep 2007 00:30:33 +0000</pubDate>
		<dc:creator>Surf Canyon</dc:creator>
				<category><![CDATA[Recommendations]]></category>

		<guid isPermaLink="false">http://blog.surfcanyon.com/2007/09/28/recommendations-are-not-similar-pages/</guid>
		<description><![CDATA[For people familiar with Google&#8217;s &#8220;similar pages&#8221; links, it is important to note that they are not at all related to Surf Canyon&#8217;s Recommendations. The &#8220;similar pages&#8221; links on Google give users a sampling of websites that are linked to by the same websites linking to that particular result. Confusing? For example, if website A [...]]]></description>
			<content:encoded><![CDATA[<p>For people familiar with Google&#8217;s &#8220;similar pages&#8221; links, it is important to note that they are not at all related to Surf Canyon&#8217;s Recommendations.</p>
<p>The &#8220;similar pages&#8221; links on Google give users a sampling of websites that are linked to by the same websites linking to that particular result. Confusing? For example, if website A is one of the results and website B links to website A, then clicking on &#8220;similar pages&#8221; for website A will give you other websites that are linked to by website B. The theory is that if website B is linked to website A then other websites linked to by website B will be &#8220;similar&#8221; to website A. This is, of course, not necessarily the case and is, perhaps, rarely the case. The <a target="_blank" href="http://forums.searchenginewatch.com/showpost.php?p=64904&amp;postcount=4">Search Engine Watch Forum</a> has a good description of &#8220;similar pages&#8221;.</p>
<p>Surf Canyon&#8217;s Recommendations, on the other hand, are based on implict intent inferred from user behavior and, as a result, are considerably more valuable. Query Discovery<font size="4" face="Times New Roman">™</font> technology provides the power that enables users to unlock mountains of search results in order to find relevant information buried deep within.</p>
]]></content:encoded>
			<wfw:commentRss>http://js-kit.com/rss/blog.surfcanyon.com/p=4</wfw:commentRss>
		<slash:comments>1</slash:comments>
		</item>
	</channel>
</rss>

