<?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: Google Improves Personalization</title>
	<atom:link href="http://thenoisychannel.com/2009/01/18/google-improves-personalization/feed/" rel="self" type="application/rss+xml" />
	<link>http://thenoisychannel.com/2009/01/18/google-improves-personalization/</link>
	<description></description>
	<lastBuildDate>Mon, 21 May 2012 05:21:00 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.2</generator>
	<item>
		<title>By: Daniel Tunkelang</title>
		<link>http://thenoisychannel.com/2009/01/18/google-improves-personalization/comment-page-1/#comment-1524</link>
		<dc:creator>Daniel Tunkelang</dc:creator>
		<pubDate>Tue, 20 Jan 2009 22:49:03 +0000</pubDate>
		<guid isPermaLink="false">http://thenoisychannel.com/?p=1242#comment-1524</guid>
		<description>Well, I thought I&#039;d try to be fair and balanced. Given how critical I am of Google, I&#039;m amazed they let me into the building the other day!

I think that&#039;s what they&#039;re doing. I&#039;d be more confident if I could try it out. I have to think that someone here got a &quot;lucky cookie&quot; and can tell us more about it!

As for the Kerne and the CombinFormation work, this the first I&#039;ve heard of it. It&#039;s interesting, but I think this is closer to what Yahoo BOSS is doing, or maybe even what Google is offering in the way of custom search engines.

What is interesting here--at least to me--is that this feature, as I understand it,  is handing more control to users. That, if Google is really doing it, would be a big step in the right direction.</description>
		<content:encoded><![CDATA[<p>Well, I thought I&#8217;d try to be fair and balanced. Given how critical I am of Google, I&#8217;m amazed they let me into the building the other day!</p>
<p>I think that&#8217;s what they&#8217;re doing. I&#8217;d be more confident if I could try it out. I have to think that someone here got a &#8220;lucky cookie&#8221; and can tell us more about it!</p>
<p>As for the Kerne and the CombinFormation work, this the first I&#8217;ve heard of it. It&#8217;s interesting, but I think this is closer to what Yahoo BOSS is doing, or maybe even what Google is offering in the way of custom search engines.</p>
<p>What is interesting here&#8211;at least to me&#8211;is that this feature, as I understand it,  is handing more control to users. That, if Google is really doing it, would be a big step in the right direction.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: jeremy</title>
		<link>http://thenoisychannel.com/2009/01/18/google-improves-personalization/comment-page-1/#comment-1521</link>
		<dc:creator>jeremy</dc:creator>
		<pubDate>Tue, 20 Jan 2009 21:31:34 +0000</pubDate>
		<guid isPermaLink="false">http://thenoisychannel.com/?p=1242#comment-1521</guid>
		<description>Sorry, I didn&#039;t mean to impinge on any Google niceties.  I will give due credit: Yay Google!

I just didn&#039;t get it, at first.

So you are saying that it&#039;s more like seed-based source-biasing?  That does make more sense.  

It reminds me, though, of some of Andruid Kerne&#039;s work.  Are you familiar with CombinFormation?  I first came across it in 2003.. here&#039;s a good 2008 writeup:

http://ecologylab.cs.tamu.edu/research/publications/combinFormationTOIS2008.pdf</description>
		<content:encoded><![CDATA[<p>Sorry, I didn&#8217;t mean to impinge on any Google niceties.  I will give due credit: Yay Google!</p>
<p>I just didn&#8217;t get it, at first.</p>
<p>So you are saying that it&#8217;s more like seed-based source-biasing?  That does make more sense.  </p>
<p>It reminds me, though, of some of Andruid Kerne&#8217;s work.  Are you familiar with CombinFormation?  I first came across it in 2003.. here&#8217;s a good 2008 writeup:</p>
<p><a href="http://ecologylab.cs.tamu.edu/research/publications/combinFormationTOIS2008.pdf" rel="nofollow">http://ecologylab.cs.tamu.edu/research/publications/combinFormationTOIS2008.pdf</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Daniel Tunkelang</title>
		<link>http://thenoisychannel.com/2009/01/18/google-improves-personalization/comment-page-1/#comment-1514</link>
		<dc:creator>Daniel Tunkelang</dc:creator>
		<pubDate>Tue, 20 Jan 2009 04:37:33 +0000</pubDate>
		<guid isPermaLink="false">http://thenoisychannel.com/?p=1242#comment-1514</guid>
		<description>I should have known that no one would let me get away with saying something nice about Google!

Maybe I&#039;m misunderstanding the feature, but I thought it allowed you to specify a set of sites, not just a set of pages. Let&#039;s say I include my favorite shopping, news, and travel sites. Then Google effectively implements source selection, routing my queries to the appropriate site.

It may be primitive, but it&#039;s more than bookmarking. And the granularity is much more useful than SearchWiki--you&#039;re not tuning results for specific queries, but rather you&#039;re modifying the way all of your searches are performed.

Am I misunderstanding the feature? As I said, I haven&#039;t had the opportunity to try it out myself.</description>
		<content:encoded><![CDATA[<p>I should have known that no one would let me get away with saying something nice about Google!</p>
<p>Maybe I&#8217;m misunderstanding the feature, but I thought it allowed you to specify a set of sites, not just a set of pages. Let&#8217;s say I include my favorite shopping, news, and travel sites. Then Google effectively implements source selection, routing my queries to the appropriate site.</p>
<p>It may be primitive, but it&#8217;s more than bookmarking. And the granularity is much more useful than SearchWiki&#8211;you&#8217;re not tuning results for specific queries, but rather you&#8217;re modifying the way all of your searches are performed.</p>
<p>Am I misunderstanding the feature? As I said, I haven&#8217;t had the opportunity to try it out myself.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: jeremy</title>
		<link>http://thenoisychannel.com/2009/01/18/google-improves-personalization/comment-page-1/#comment-1512</link>
		<dc:creator>jeremy</dc:creator>
		<pubDate>Mon, 19 Jan 2009 18:28:32 +0000</pubDate>
		<guid isPermaLink="false">http://thenoisychannel.com/?p=1242#comment-1512</guid>
		<description>Hasn&#039;t Google Enterprise search had this functionality for quite some time now?

Either way, I really don&#039;t get it.  If there is a site that you&#039;ve already found, Google Personalization is letting you bookmark it, so that when you do that same search again, your bookmark will appear at the top of the list, above the regular search results?  

How is this transparency?   How is this IR?  To me, it just looks like bookmarking.

The transparency that is more interesting is the transparency that is needed when you&#039;ve *never* come across a particular website before, and are only discovering it, via search, for the first time.  Getting transparent explanations as to why those pages are showing up is, for me at least, the main reason transparency is so important.

But bookmarking?  Why do we even need Google for that?  A simple firefox plugin could accomplish the same thing.</description>
		<content:encoded><![CDATA[<p>Hasn&#8217;t Google Enterprise search had this functionality for quite some time now?</p>
<p>Either way, I really don&#8217;t get it.  If there is a site that you&#8217;ve already found, Google Personalization is letting you bookmark it, so that when you do that same search again, your bookmark will appear at the top of the list, above the regular search results?  </p>
<p>How is this transparency?   How is this IR?  To me, it just looks like bookmarking.</p>
<p>The transparency that is more interesting is the transparency that is needed when you&#8217;ve *never* come across a particular website before, and are only discovering it, via search, for the first time.  Getting transparent explanations as to why those pages are showing up is, for me at least, the main reason transparency is so important.</p>
<p>But bookmarking?  Why do we even need Google for that?  A simple firefox plugin could accomplish the same thing.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Phoebe</title>
		<link>http://thenoisychannel.com/2009/01/18/google-improves-personalization/comment-page-1/#comment-1511</link>
		<dc:creator>Phoebe</dc:creator>
		<pubDate>Mon, 19 Jan 2009 10:22:19 +0000</pubDate>
		<guid isPermaLink="false">http://thenoisychannel.com/?p=1242#comment-1511</guid>
		<description>Interesting. I see Google needing to shift a lot of focus back to its core service of search in order to keep up with external changes - expectations of personalization, social experience, maybe even semantic.</description>
		<content:encoded><![CDATA[<p>Interesting. I see Google needing to shift a lot of focus back to its core service of search in order to keep up with external changes &#8211; expectations of personalization, social experience, maybe even semantic.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

