<?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/"
	xmlns:georss="http://www.georss.org/georss" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:media="http://search.yahoo.com/mrss/"
		>
<channel>
	<title>Comments on: Predicting movie ratings hereby declared dead</title>
	<atom:link href="http://mendicantbug.com/2009/07/11/predicting-movie-ratings-hereby-declared-dead/feed/" rel="self" type="application/rss+xml" />
	<link>http://mendicantbug.com/2009/07/11/predicting-movie-ratings-hereby-declared-dead/</link>
	<description>Wanderings into computational linguistics, science, social media and life...</description>
	<lastBuildDate>Tue, 17 Jan 2012 18:51:53 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.com/</generator>
	<item>
		<title>By: Melinda Weathers</title>
		<link>http://mendicantbug.com/2009/07/11/predicting-movie-ratings-hereby-declared-dead/#comment-1809</link>
		<dc:creator><![CDATA[Melinda Weathers]]></dc:creator>
		<pubDate>Sun, 12 Jul 2009 19:45:39 +0000</pubDate>
		<guid isPermaLink="false">http://mendicantbug.com/?p=1207#comment-1809</guid>
		<description><![CDATA[I like the idea of selection by mood.  I don&#039;t know about plain Netflix since your mood will change by the time the thing arrives, but it would be cool for Tivo and the Netlix Instant Queue.  There could be a top-level menu on the Tivo for &quot;Help Me Decide&quot; where it randomly selects from a bank of questions to ask you about what mood you&#039;re in, and each answer narrows the list of possibilities from your current Tivo list, shows starting within the next 15 minutes, and the Netflix Instant Queue.  That would be pretty sweet.]]></description>
		<content:encoded><![CDATA[<p>I like the idea of selection by mood.  I don&#8217;t know about plain Netflix since your mood will change by the time the thing arrives, but it would be cool for Tivo and the Netlix Instant Queue.  There could be a top-level menu on the Tivo for &#8220;Help Me Decide&#8221; where it randomly selects from a bank of questions to ask you about what mood you&#8217;re in, and each answer narrows the list of possibilities from your current Tivo list, shows starting within the next 15 minutes, and the Netflix Instant Queue.  That would be pretty sweet.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jason Adams</title>
		<link>http://mendicantbug.com/2009/07/11/predicting-movie-ratings-hereby-declared-dead/#comment-1806</link>
		<dc:creator><![CDATA[Jason Adams]]></dc:creator>
		<pubDate>Sun, 12 Jul 2009 14:42:51 +0000</pubDate>
		<guid isPermaLink="false">http://mendicantbug.com/?p=1207#comment-1806</guid>
		<description><![CDATA[Ah, I see -- cool.  Sounds like it&#039;d be fun to work on!]]></description>
		<content:encoded><![CDATA[<p>Ah, I see &#8212; cool.  Sounds like it&#8217;d be fun to work on!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Neal Richter</title>
		<link>http://mendicantbug.com/2009/07/11/predicting-movie-ratings-hereby-declared-dead/#comment-1805</link>
		<dc:creator><![CDATA[Neal Richter]]></dc:creator>
		<pubDate>Sun, 12 Jul 2009 07:10:50 +0000</pubDate>
		<guid isPermaLink="false">http://mendicantbug.com/?p=1207#comment-1805</guid>
		<description><![CDATA[Might be going on too much of a tangent here... But here goes.

Customers with questions about products, accessories etc often use some kind of &#039;tech support&#039; link off the corp website or techsupport email address to seek assistance.

IMO the best versions of the software systems responding to these customers act like an RS with a nice browsable UI.  Why?  A search box let&#039;s people filter info, and Google has that down..  Yet in this setting the questions are highly repetative and very self similar w.r.t. language/vocab... Simple search falls down.  Add an RS to learn from the many past interactions with customers and a faceting or othe adv UI and the ingredients are there for a system that predicts common customer questions and short cuts them to a solution.

This is mostly unsolved and plenty hard.  See any tech support link on the web for examples of how badly it works now and what the possibilities are ..]]></description>
		<content:encoded><![CDATA[<p>Might be going on too much of a tangent here&#8230; But here goes.</p>
<p>Customers with questions about products, accessories etc often use some kind of &#8216;tech support&#8217; link off the corp website or techsupport email address to seek assistance.</p>
<p>IMO the best versions of the software systems responding to these customers act like an RS with a nice browsable UI.  Why?  A search box let&#8217;s people filter info, and Google has that down..  Yet in this setting the questions are highly repetative and very self similar w.r.t. language/vocab&#8230; Simple search falls down.  Add an RS to learn from the many past interactions with customers and a faceting or othe adv UI and the ingredients are there for a system that predicts common customer questions and short cuts them to a solution.</p>
<p>This is mostly unsolved and plenty hard.  See any tech support link on the web for examples of how badly it works now and what the possibilities are ..</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jason Adams</title>
		<link>http://mendicantbug.com/2009/07/11/predicting-movie-ratings-hereby-declared-dead/#comment-1803</link>
		<dc:creator><![CDATA[Jason Adams]]></dc:creator>
		<pubDate>Sun, 12 Jul 2009 05:06:22 +0000</pubDate>
		<guid isPermaLink="false">http://mendicantbug.com/?p=1207#comment-1803</guid>
		<description><![CDATA[Not sure I understand what that RS you were working on for customer service portals is supposed to do..  Can you elaborate or is it an industrial secret kind of thing?  Maybe my missing ingredient is that I don&#039;t know what customer service portals are. :)]]></description>
		<content:encoded><![CDATA[<p>Not sure I understand what that RS you were working on for customer service portals is supposed to do..  Can you elaborate or is it an industrial secret kind of thing?  Maybe my missing ingredient is that I don&#8217;t know what customer service portals are. :)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Neal Richter</title>
		<link>http://mendicantbug.com/2009/07/11/predicting-movie-ratings-hereby-declared-dead/#comment-1802</link>
		<dc:creator><![CDATA[Neal Richter]]></dc:creator>
		<pubDate>Sun, 12 Jul 2009 04:24:45 +0000</pubDate>
		<guid isPermaLink="false">http://mendicantbug.com/?p=1207#comment-1802</guid>
		<description><![CDATA[Agreed.  It will become a second tier task within recommender systems rather than the prize driving interest in R.S. I think  a primary reason to have stong commercial apps to retail, crm, advertising etc. Movie listings is too niche in comparison.

I like the idea of having a side effect of the RS being better indexes and an interactive app, worked toward such a system at a CRM vendor for customer service portals.  Sounds niche as well... Yet the market opportunity is measured in billions.

I do wish that amazons RS was a bit more interactive and could be directly searched against.]]></description>
		<content:encoded><![CDATA[<p>Agreed.  It will become a second tier task within recommender systems rather than the prize driving interest in R.S. I think  a primary reason to have stong commercial apps to retail, crm, advertising etc. Movie listings is too niche in comparison.</p>
<p>I like the idea of having a side effect of the RS being better indexes and an interactive app, worked toward such a system at a CRM vendor for customer service portals.  Sounds niche as well&#8230; Yet the market opportunity is measured in billions.</p>
<p>I do wish that amazons RS was a bit more interactive and could be directly searched against.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

