<?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: Semantic ad targeting</title>
	<atom:link href="http://blog.yieldbuild.com/2009/08/18/semantic-ad-targeting/feed/" rel="self" type="application/rss+xml" />
	<link>http://blog.yieldbuild.com/2009/08/18/semantic-ad-targeting/</link>
	<description>Internet Ad Optimization Blog</description>
	<lastBuildDate>Mon, 22 Feb 2010 21:58:17 -0800</lastBuildDate>
	<generator>http://wordpress.org/?v=2.8.6</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: Sami Linnanvuo</title>
		<link>http://blog.yieldbuild.com/2009/08/18/semantic-ad-targeting/comment-page-1/#comment-2311</link>
		<dc:creator>Sami Linnanvuo</dc:creator>
		<pubDate>Thu, 20 Aug 2009 10:02:05 +0000</pubDate>
		<guid isPermaLink="false">http://blog.yieldbuild.com/?p=598#comment-2311</guid>
		<description>We at Leiki have been developing semantic ad targeting technology since the year 2000. We use a hand-crafted ontology of about 100k concepts to analyze the contents of the page the user is currently viewing and to build a behavioral profile of each user which can be used in recommending content and targeting ads. It&#039;s all automatic - all a publisher needs to do is to put our tag on their site. 

I agree with you that there&#039;s a big difference between semantic analysis of the topics in a page vs. simple keyword matching. You need a powerful disambiguation techniques to figure out the actual meaning of a word in a given context to be able to avoid bad placements. 

You can find more info at &lt;a href=&quot;http://www.leiki.com&quot; rel=&quot;nofollow&quot;&gt;www.leiki.com&lt;/a&gt;.</description>
		<content:encoded><![CDATA[<p>We at Leiki have been developing semantic ad targeting technology since the year 2000. We use a hand-crafted ontology of about 100k concepts to analyze the contents of the page the user is currently viewing and to build a behavioral profile of each user which can be used in recommending content and targeting ads. It&#8217;s all automatic &#8211; all a publisher needs to do is to put our tag on their site. </p>
<p>I agree with you that there&#8217;s a big difference between semantic analysis of the topics in a page vs. simple keyword matching. You need a powerful disambiguation techniques to figure out the actual meaning of a word in a given context to be able to avoid bad placements. </p>
<p>You can find more info at <a href="http://www.leiki.com" rel="nofollow">http://www.leiki.com</a>.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Paul Knegten</title>
		<link>http://blog.yieldbuild.com/2009/08/18/semantic-ad-targeting/comment-page-1/#comment-2307</link>
		<dc:creator>Paul Knegten</dc:creator>
		<pubDate>Wed, 19 Aug 2009 15:39:48 +0000</pubDate>
		<guid isPermaLink="false">http://blog.yieldbuild.com/?p=598#comment-2307</guid>
		<description>Dapper&#039;s MashupAds has simply been renamed to Dapper Ads -- you can get more information at www.dapper.net.</description>
		<content:encoded><![CDATA[<p>Dapper&#8217;s MashupAds has simply been renamed to Dapper Ads &#8212; you can get more information at <a href="http://www.dapper.net" rel="nofollow">http://www.dapper.net</a>.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
