<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	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/"
		>
<channel>
	<title>Comments on: As We May Rant</title>
	<atom:link href="http://battellemedia.com/archives/2004/07/as_we_may_rant.php/feed" rel="self" type="application/rss+xml" />
	<link>http://battellemedia.com/archives/2004/07/as_we_may_rant.php?utm_source=rss&#038;utm_medium=rss&#038;utm_campaign=as_we_may_rant</link>
	<description>Thoughts on the intersection of search, media, technology, and more.</description>
	<lastBuildDate>Thu, 16 May 2013 04:38:00 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.4.1</generator>
	<item>
		<title>By: Avi Rappoport</title>
		<link>http://battellemedia.com/archives/2004/07/as_we_may_rant.php#comment-23779</link>
		<dc:creator>Avi Rappoport</dc:creator>
		<pubDate>Thu, 22 Jul 2004 18:07:20 +0000</pubDate>
		<guid isPermaLink="false">http://battellemedia.com/archives/2004/07/as_we_may_rant.php#comment-23779</guid>
		<description>&lt;p&gt;I tend to be skeptical of personalization, especially when it&#039;s done using machine learning or other algorithms.  On the other hand, there are so many results pages with the same relevance ranking, so it makes sense to try and distinguish among them.&lt;/p&gt;

&lt;p&gt;But even something as seemingly simple as location is iffy.  If I search for &quot;chicago pizza&quot;, I may be looking for chicago-style pizza in Berkeley (Zachary&#039;s is the best), not necessarily pizza *in* Chicago.  &lt;/p&gt;

&lt;p&gt;I think this may work if the interface is transparent enough -- if it&#039;s able to explain *why* you got a certain result or set of results, and allow you to override the adjustments.&lt;/p&gt;

&lt;p&gt;Avi&lt;/p&gt;</description>
		<content:encoded><![CDATA[<p>I tend to be skeptical of personalization, especially when it&#8217;s done using machine learning or other algorithms.  On the other hand, there are so many results pages with the same relevance ranking, so it makes sense to try and distinguish among them.</p>
<p>But even something as seemingly simple as location is iffy.  If I search for &#8220;chicago pizza&#8221;, I may be looking for chicago-style pizza in Berkeley (Zachary&#8217;s is the best), not necessarily pizza *in* Chicago.  </p>
<p>I think this may work if the interface is transparent enough &#8212; if it&#8217;s able to explain *why* you got a certain result or set of results, and allow you to override the adjustments.</p>
<p>Avi</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Craig Pfeifer</title>
		<link>http://battellemedia.com/archives/2004/07/as_we_may_rant.php#comment-23778</link>
		<dc:creator>Craig Pfeifer</dc:creator>
		<pubDate>Mon, 19 Jul 2004 18:36:15 +0000</pubDate>
		<guid isPermaLink="false">http://battellemedia.com/archives/2004/07/as_we_may_rant.php#comment-23778</guid>
		<description>&lt;p&gt;Another great example of inappropriate adwords:&lt;br /&gt;
&lt;a href=&quot;http://www.thezeroboss.com/archives/000653.html&quot; rel=&quot;nofollow&quot;&gt;http://www.thezeroboss.com/archives/000653.html&lt;/a&gt;&lt;/p&gt;</description>
		<content:encoded><![CDATA[<p>Another great example of inappropriate adwords:<br />
<a href="http://www.thezeroboss.com/archives/000653.html" rel="nofollow">http://www.thezeroboss.com/archives/000653.html</a></p>
]]></content:encoded>
	</item>
</channel>
</rss>
