<?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: Asimov&#8217;s 4th law: A robot will not tweet.</title>
	<atom:link href="http://chrisscott.org/software/cms/asimovs-4th-law-a-robot-will-not-tweet/feed" rel="self" type="application/rss+xml" />
	<link>http://chrisscott.org/software/cms/asimovs-4th-law-a-robot-will-not-tweet</link>
	<description>Tech blog</description>
	<lastBuildDate>Tue, 19 Jul 2011 11:03:32 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.1.3</generator>
	<item>
		<title>By: chris</title>
		<link>http://chrisscott.org/software/cms/asimovs-4th-law-a-robot-will-not-tweet/comment-page-1#comment-8</link>
		<dc:creator>chris</dc:creator>
		<pubDate>Fri, 24 Apr 2009 17:44:21 +0000</pubDate>
		<guid isPermaLink="false">http://chrisscott.org/?p=4#comment-8</guid>
		<description>Thanks everyone for the feedback. I&#039;ve had a bit of a fine tune and played with a few more articles (thank &lt;a href=&quot;http://twitter.com/sarahebourne&quot; rel=&quot;nofollow&quot;&gt;@sarahbourne&lt;/a&gt;). See the new post &lt;a href=&quot;http://chrisscott.org/?p=13&quot; rel=&quot;nofollow&quot;&gt;here&lt;/a&gt;. I&#039;m still only taking conceptually but it addresses some of the points raised.</description>
		<content:encoded><![CDATA[<p>Thanks everyone for the feedback. I&#8217;ve had a bit of a fine tune and played with a few more articles (thank <a href="http://twitter.com/sarahebourne" rel="nofollow">@sarahbourne</a>). See the new post <a href="http://chrisscott.org/?p=13" rel="nofollow">here</a>. I&#8217;m still only taking conceptually but it addresses some of the points raised.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: OlegR</title>
		<link>http://chrisscott.org/software/cms/asimovs-4th-law-a-robot-will-not-tweet/comment-page-1#comment-7</link>
		<dc:creator>OlegR</dc:creator>
		<pubDate>Thu, 23 Apr 2009 19:30:51 +0000</pubDate>
		<guid isPermaLink="false">http://chrisscott.org/?p=4#comment-7</guid>
		<description>Do you think we can have this bot work as a private API? 
I&#039;m sure cmswire, foliomag and others would love to try it out :) and see the power of text mining</description>
		<content:encoded><![CDATA[<p>Do you think we can have this bot work as a private API?<br />
I&#8217;m sure cmswire, foliomag and others would love to try it out :) and see the power of text mining</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Sarah Bourne</title>
		<link>http://chrisscott.org/software/cms/asimovs-4th-law-a-robot-will-not-tweet/comment-page-1#comment-6</link>
		<dc:creator>Sarah Bourne</dc:creator>
		<pubDate>Thu, 23 Apr 2009 15:56:27 +0000</pubDate>
		<guid isPermaLink="false">http://chrisscott.org/?p=4#comment-6</guid>
		<description>Brilliant! Please feel free to test your clever bot on the @massgov twitter feed. I&#039;d love to see the results.</description>
		<content:encoded><![CDATA[<p>Brilliant! Please feel free to test your clever bot on the @massgov twitter feed. I&#8217;d love to see the results.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: chris</title>
		<link>http://chrisscott.org/software/cms/asimovs-4th-law-a-robot-will-not-tweet/comment-page-1#comment-5</link>
		<dc:creator>chris</dc:creator>
		<pubDate>Thu, 23 Apr 2009 13:49:07 +0000</pubDate>
		<guid isPermaLink="false">http://chrisscott.org/?p=4#comment-5</guid>
		<description>I&#039;ve done a number of things. First off, NSummarizer is being asked for a single sentence fragment. Usually this is small enough to fit in. In the cases were it is still to long I do some progressively aggressive shortening techniques: reduce conjunctives (&quot;and&quot; to &quot;&amp;&quot;, for example); removing punctuation; etc.

It&#039;s true that you will always faced with the programmatic problem that a 140 character restriction presents but by using a more concise and relevant string you can minimize the need for brute force truncation.</description>
		<content:encoded><![CDATA[<p>I&#8217;ve done a number of things. First off, NSummarizer is being asked for a single sentence fragment. Usually this is small enough to fit in. In the cases were it is still to long I do some progressively aggressive shortening techniques: reduce conjunctives (&#8220;and&#8221; to &#8220;&amp;&#8221;, for example); removing punctuation; etc.</p>
<p>It&#8217;s true that you will always faced with the programmatic problem that a 140 character restriction presents but by using a more concise and relevant string you can minimize the need for brute force truncation.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Rob</title>
		<link>http://chrisscott.org/software/cms/asimovs-4th-law-a-robot-will-not-tweet/comment-page-1#comment-4</link>
		<dc:creator>Rob</dc:creator>
		<pubDate>Thu, 23 Apr 2009 12:41:12 +0000</pubDate>
		<guid isPermaLink="false">http://chrisscott.org/?p=4#comment-4</guid>
		<description>How are you assuring NSummarizer keeps the Tweet within the specific character limit of Twitter? Are you relying on Twitter to change a long URL into a TinyURL</description>
		<content:encoded><![CDATA[<p>How are you assuring NSummarizer keeps the Tweet within the specific character limit of Twitter? Are you relying on Twitter to change a long URL into a TinyURL</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Chris</title>
		<link>http://chrisscott.org/software/cms/asimovs-4th-law-a-robot-will-not-tweet/comment-page-1#comment-3</link>
		<dc:creator>Chris</dc:creator>
		<pubDate>Thu, 23 Apr 2009 08:31:09 +0000</pubDate>
		<guid isPermaLink="false">http://chrisscott.org/?p=4#comment-3</guid>
		<description>Thanks for the comment Avi. I&#039;m not sure about getting Pepsi blog posts but I can certainly republish some copylefted content (probably Wikipedia). Watch this space.</description>
		<content:encoded><![CDATA[<p>Thanks for the comment Avi. I&#8217;m not sure about getting Pepsi blog posts but I can certainly republish some copylefted content (probably Wikipedia). Watch this space.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Avi Rappoport</title>
		<link>http://chrisscott.org/software/cms/asimovs-4th-law-a-robot-will-not-tweet/comment-page-1#comment-2</link>
		<dc:creator>Avi Rappoport</dc:creator>
		<pubDate>Wed, 22 Apr 2009 20:26:47 +0000</pubDate>
		<guid isPermaLink="false">http://chrisscott.org/?p=4#comment-2</guid>
		<description>Promising, but too small a data sample.  Could you do 25 pepsi blog posts and see what happens?</description>
		<content:encoded><![CDATA[<p>Promising, but too small a data sample.  Could you do 25 pepsi blog posts and see what happens?</p>
]]></content:encoded>
	</item>
</channel>
</rss>

