<?xml version="1.0" encoding="UTF-8"?><!-- generator="wordpress/2.3.1" -->
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	>
<channel>
	<title>Comments for SentimentMetrics -</title>
	<link>http://www.sentimentmetrics.com/blog</link>
	<description>Blog and Media monitoring</description>
	<pubDate>Wed, 20 Aug 2008 09:17:29 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.3.1</generator>
		<item>
		<title>Comment on Sentiment analysis and Sentiment mining by Leon</title>
		<link>http://www.sentimentmetrics.com/blog/2007/12/10/sentiment-analysis-and-sentiment-mining/#comment-4</link>
		<dc:creator>Leon</dc:creator>
		<pubDate>Mon, 10 Dec 2007 19:41:44 +0000</pubDate>
		<guid>http://www.sentimentmetrics.com/blog/2007/12/10/sentiment-analysis-and-sentiment-mining/#comment-4</guid>
		<description>Hi Matt,
Thanks, really with our service we want to be as open as possible. We don't want anything to be a surprise when people decide they want us to take care of their social media monitoring, hence we offer free trials.

It's an interesting debate Automated vs Human sentiment analysis and its got a long way to go yet.

However I would argue against this statement "Customers are more comfortable with human error than computer error". Thats not something we have found or seen evidence on, and seems rather an arbitrary statement.

Thanks

Leon</description>
		<content:encoded><![CDATA[<p>Hi Matt,<br />
Thanks, really with our service we want to be as open as possible. We don&#8217;t want anything to be a surprise when people decide they want us to take care of their social media monitoring, hence we offer free trials.</p>
<p>It&#8217;s an interesting debate Automated vs Human sentiment analysis and its got a long way to go yet.</p>
<p>However I would argue against this statement &#8220;Customers are more comfortable with human error than computer error&#8221;. Thats not something we have found or seen evidence on, and seems rather an arbitrary statement.</p>
<p>Thanks</p>
<p>Leon</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Sentiment analysis and Sentiment mining by Matthew Hurst</title>
		<link>http://www.sentimentmetrics.com/blog/2007/12/10/sentiment-analysis-and-sentiment-mining/#comment-3</link>
		<dc:creator>Matthew Hurst</dc:creator>
		<pubDate>Mon, 10 Dec 2007 18:15:24 +0000</pubDate>
		<guid>http://www.sentimentmetrics.com/blog/2007/12/10/sentiment-analysis-and-sentiment-mining/#comment-3</guid>
		<description>Great to see you bringing this discussion out in the open. One of the interesting issues is the different types of errors computers make compared with human labelers. Customers are more comfortable with human error than computer error even if the error rates are similar.

Are you thinking of coming up to Seattle for ICWSM? We have a tutorial on sentiment and I expect there will be a good body of papers on the subject.

http://www.icwsm.org</description>
		<content:encoded><![CDATA[<p>Great to see you bringing this discussion out in the open. One of the interesting issues is the different types of errors computers make compared with human labelers. Customers are more comfortable with human error than computer error even if the error rates are similar.</p>
<p>Are you thinking of coming up to Seattle for ICWSM? We have a tutorial on sentiment and I expect there will be a good body of papers on the subject.</p>
<p><a href="http://www.icwsm.org" rel="nofollow">http://www.icwsm.org</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Monitoring buzz is great for trend analysis! by Nathan Gilliatt</title>
		<link>http://www.sentimentmetrics.com/blog/2007/11/15/monitoring-buzz-is-great-for-trend-analysis/#comment-2</link>
		<dc:creator>Nathan Gilliatt</dc:creator>
		<pubDate>Fri, 16 Nov 2007 22:47:32 +0000</pubDate>
		<guid>http://www.sentimentmetrics.com/blog/2007/11/15/monitoring-buzz-is-great-for-trend-analysis/#comment-2</guid>
		<description>Hi. I'd send a direct email, but I don't see one on your blog.

I cover the market for social media analysis services worldwide. We should talk some time. I publish a buyers guide that you'll want to be in.

   - Nathan</description>
		<content:encoded><![CDATA[<p>Hi. I&#8217;d send a direct email, but I don&#8217;t see one on your blog.</p>
<p>I cover the market for social media analysis services worldwide. We should talk some time. I publish a buyers guide that you&#8217;ll want to be in.</p>
<p>   - Nathan</p>
]]></content:encoded>
	</item>
</channel>
</rss>
