<?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: Gender Analyzer: did a man or woman write that&#160;blog?</title>
	<atom:link href="http://boingboing.net/2008/11/03/gender-analyzer-did.html/feed" rel="self" type="application/rss+xml" />
	<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html</link>
	<description>Brain candy for Happy Mutants</description>
	<lastBuildDate>Fri, 24 May 2013 02:22:00 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.4.1</generator>
	<item>
		<title>By: The Tensor</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-322053</link>
		<dc:creator>The Tensor</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-322053</guid>
		<description>Another data point: it thinks my blog was written by a woman (and I&#039;m a man).  Accuracy currently holding steady at 56%.</description>
		<content:encoded><![CDATA[<p>Another data point: it thinks my blog was written by a woman (and I&#8217;m a man).  Accuracy currently holding steady at 56%.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: John Mark Ockerbloom</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321801</link>
		<dc:creator>John Mark Ockerbloom</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321801</guid>
		<description>I fed in the URL for &lt;a href=&quot;http://digital.library.upenn.edu/women/&quot; rel=&quot;nofollow&quot;&gt;A Celebration of Women Writers&lt;/a&gt;, which is not only edited by a woman (my wife) but is all about women&#039;s writing.

As of the time I write this, &lt;a href=&quot;http://www.genderanalyzer.com/?url=digital.library.upenn.edu%2Fwomen%2F&quot; rel=&quot;nofollow&quot;&gt;Genderanalyzer says&lt;/a&gt; &quot;We think [this page] is written by a man.&quot;

Go figure.</description>
		<content:encoded><![CDATA[<p>I fed in the URL for <a href="http://digital.library.upenn.edu/women/" rel="nofollow">A Celebration of Women Writers</a>, which is not only edited by a woman (my wife) but is all about women&#8217;s writing.</p>
<p>As of the time I write this, <a href="http://www.genderanalyzer.com/?url=digital.library.upenn.edu%2Fwomen%2F" rel="nofollow">Genderanalyzer says</a> &#8220;We think [this page] is written by a man.&#8221;</p>
<p>Go figure.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Sekino</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-322580</link>
		<dc:creator>Sekino</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-322580</guid>
		<description>I&#039;m just unimpressed that their &#039;artificial intelligence&#039; is equally dependant on generalizations and prejudiced assumptions as the average human to make its call.  Actually, I&#039;d bet most people would probably have a greater rate of success guessing the blog writer&#039;s gender themselves.

Do we call it &#039;artificial ignorance&#039; then?

</description>
		<content:encoded><![CDATA[<p>I&#8217;m just unimpressed that their &#8216;artificial intelligence&#8217; is equally dependant on generalizations and prejudiced assumptions as the average human to make its call.  Actually, I&#8217;d bet most people would probably have a greater rate of success guessing the blog writer&#8217;s gender themselves.</p>
<p>Do we call it &#8216;artificial ignorance&#8217; then?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Zan</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321822</link>
		<dc:creator>Zan</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321822</guid>
		<description>It&#039;s accuracy is less than 60% now, which isn&#039;t much better than a coin toss.</description>
		<content:encoded><![CDATA[<p>It&#8217;s accuracy is less than 60% now, which isn&#8217;t much better than a coin toss.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Cool Products</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321834</link>
		<dc:creator>Cool Products</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321834</guid>
		<description>It surprises me a little that there is only a 68 percent probability that I am in fact a male.</description>
		<content:encoded><![CDATA[<p>It surprises me a little that there is only a 68 percent probability that I am in fact a male.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: arkizzle</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-322107</link>
		<dc:creator>arkizzle</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-322107</guid>
		<description>According to the other version of this over at http://bookblog.net/gender/genie.php (linked by ZIIB @ 11), some of the keywords involved are thus: (I can only presume they use a similar algorithm)

FEMALE:
[with]	
[if]	
[not]	
[where]	
[be]	
[when]	
[your]	
[her]	
[we]	
[should]
[she]	
[and]	
[me]	
[myself]
[hers]	
[was]	
[to]

MALE:
[around]
[what]	
[more]	
[are]	
[as]	
[who]	
[below]	
[is]	
[these]	
[the]	
[a]	3	
[at]	
[it]	
[many]	
[said]	
[above]	

(Teresa, &#039;scuse the verticals, BB ain&#039;t fixed-width)</description>
		<content:encoded><![CDATA[<p>According to the other version of this over at <a href="http://bookblog.net/gender/genie.php" rel="nofollow">http://bookblog.net/gender/genie.php</a> (linked by ZIIB @ 11), some of the keywords involved are thus: (I can only presume they use a similar algorithm)</p>
<p>FEMALE:<br />
[with]<br />
[if]<br />
[not]<br />
[where]<br />
[be]<br />
[when]<br />
[your]<br />
[her]<br />
[we]<br />
[should]<br />
[she]<br />
[and]<br />
[me]<br />
[myself]<br />
[hers]<br />
[was]<br />
[to]</p>
<p>MALE:<br />
[around]<br />
[what]<br />
[more]<br />
[are]<br />
[as]<br />
[who]<br />
[below]<br />
[is]<br />
[these]<br />
[the]<br />
[a]	3<br />
[at]<br />
[it]<br />
[many]<br />
[said]<br />
[above]	</p>
<p>(Teresa, &#8216;scuse the verticals, BB ain&#8217;t fixed-width)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Trent Hawkins</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321876</link>
		<dc:creator>Trent Hawkins</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321876</guid>
		<description>to Zan: Yes, it&#039;s basically a 50/50 coin toss. However it is an advanced virtual reality coin toss that warrants thousands of dollars of research funding.</description>
		<content:encoded><![CDATA[<p>to Zan: Yes, it&#8217;s basically a 50/50 coin toss. However it is an advanced virtual reality coin toss that warrants thousands of dollars of research funding.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: jccalhoun</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321890</link>
		<dc:creator>jccalhoun</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321890</guid>
		<description>I tried a few gaming websites written by women and it said 3/4 of them were written by men.  </description>
		<content:encoded><![CDATA[<p>I tried a few gaming websites written by women and it said 3/4 of them were written by men.  </p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Secret_Life_of_Plants</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321910</link>
		<dc:creator>Secret_Life_of_Plants</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321910</guid>
		<description>The computer classified my two blogs, and the blog of my roommate as having been created by men. (I am a woman and so is my roommate).

I will say that even on message boards, people responding to something I wrote inevitably address me as &quot;dude&quot; or &quot;that guy&quot;. 

Oh well.</description>
		<content:encoded><![CDATA[<p>The computer classified my two blogs, and the blog of my roommate as having been created by men. (I am a woman and so is my roommate).</p>
<p>I will say that even on message boards, people responding to something I wrote inevitably address me as &#8220;dude&#8221; or &#8220;that guy&#8221;. </p>
<p>Oh well.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: LYNDON</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-322169</link>
		<dc:creator>LYNDON</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-322169</guid>
		<description>Interesting. I just put two of my blog posts and a satire column through the gender genie, and I turned into a female for the last one.

...which was a parody election manifesto, so to was the &quot;we&quot;s that did it.</description>
		<content:encoded><![CDATA[<p>Interesting. I just put two of my blog posts and a satire column through the gender genie, and I turned into a female for the last one.</p>
<p>&#8230;which was a parody election manifesto, so to was the &#8220;we&#8221;s that did it.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: retchdog</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321919</link>
		<dc:creator>retchdog</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321919</guid>
		<description>Yet another boastful claim based on performance on the &lt;i&gt;training&lt;/i&gt; data, blown to bits when exposed to the world&#039;s diversity.

The map is not the territory; especially if the map is drawn by some dot-com-2.0 yahoos with too much python and not enough statistics.

Unexpected bonus: With seven tabs open, my firefox truncates this one as &quot;GenderAnal...&quot;</description>
		<content:encoded><![CDATA[<p>Yet another boastful claim based on performance on the <i>training</i> data, blown to bits when exposed to the world&#8217;s diversity.</p>
<p>The map is not the territory; especially if the map is drawn by some dot-com-2.0 yahoos with too much python and not enough statistics.</p>
<p>Unexpected bonus: With seven tabs open, my firefox truncates this one as &#8220;GenderAnal&#8230;&#8221;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jerril</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321929</link>
		<dc:creator>Jerril</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321929</guid>
		<description>Currently, the correct rate is 56%, which is uncomfortably close to &quot;we flipped a coin&quot;. They don&#039;t give any information on sample size on the poll/result feedback, and of course there are no controls on responses so who knows what people are saying...

But yeah. Currently, totally pointless.</description>
		<content:encoded><![CDATA[<p>Currently, the correct rate is 56%, which is uncomfortably close to &#8220;we flipped a coin&#8221;. They don&#8217;t give any information on sample size on the poll/result feedback, and of course there are no controls on responses so who knows what people are saying&#8230;</p>
<p>But yeah. Currently, totally pointless.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Pam Rosengren</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-322188</link>
		<dc:creator>Pam Rosengren</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-322188</guid>
		<description>I guess I shouldn&#039;t feel bad about it deciding I am a guy. 

But having grown up in the days when we were taught in science class that women&#039;s brains stopped growing before men&#039;s, that an intelligent woman was an anomaly and that intelligent women tended to have smaller breasts and be less attractive, this analyzer makes me boak. 

If they are researching whether there are any statistically significant differences in the way each gender writes, and what we write about, their results at this stage are &quot;not really&quot;. If the researchers have assumed there is a difference, then the results so far suggest that they need to revisit their assumptions.</description>
		<content:encoded><![CDATA[<p>I guess I shouldn&#8217;t feel bad about it deciding I am a guy. </p>
<p>But having grown up in the days when we were taught in science class that women&#8217;s brains stopped growing before men&#8217;s, that an intelligent woman was an anomaly and that intelligent women tended to have smaller breasts and be less attractive, this analyzer makes me boak. </p>
<p>If they are researching whether there are any statistically significant differences in the way each gender writes, and what we write about, their results at this stage are &#8220;not really&#8221;. If the researchers have assumed there is a difference, then the results so far suggest that they need to revisit their assumptions.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Anonymous</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-322972</link>
		<dc:creator>Anonymous</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-322972</guid>
		<description>I&#039;m willing to bet it&#039;s just a standard Bayesian filtering mechanism. So, for example, tech writing on the web is dominated by men (and easily identifiable) and it&#039;s just trained to classify accordingly. Don&#039;t read too much into it!

- Udo</description>
		<content:encoded><![CDATA[<p>I&#8217;m willing to bet it&#8217;s just a standard Bayesian filtering mechanism. So, for example, tech writing on the web is dominated by men (and easily identifiable) and it&#8217;s just trained to classify accordingly. Don&#8217;t read too much into it!</p>
<p>- Udo</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: macguffin</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-322211</link>
		<dc:creator>macguffin</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-322211</guid>
		<description>Well put, Pam. It&#039;s neat when it gets it right, but that seems to happen only half of the time. The generalisations just don&#039;t work.</description>
		<content:encoded><![CDATA[<p>Well put, Pam. It&#8217;s neat when it gets it right, but that seems to happen only half of the time. The generalisations just don&#8217;t work.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: gabrielm</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321703</link>
		<dc:creator>gabrielm</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321703</guid>
		<description>&quot;Could not find female probability in response...&quot;
I hate when that happens.</description>
		<content:encoded><![CDATA[<p>&#8220;Could not find female probability in response&#8230;&#8221;<br />
I hate when that happens.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: erissian</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321959</link>
		<dc:creator>erissian</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321959</guid>
		<description>To be fair, anything above 50.02% is an improvement over just guessing; even if it isn&#039;t by much it&#039;s a start.

@#18: This /is/ training data for it. It will become accustom to the world&#039;s diversity, and on June 9th, 2012 it will become self-aware.</description>
		<content:encoded><![CDATA[<p>To be fair, anything above 50.02% is an improvement over just guessing; even if it isn&#8217;t by much it&#8217;s a start.</p>
<p>@#18: This /is/ training data for it. It will become accustom to the world&#8217;s diversity, and on June 9th, 2012 it will become self-aware.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: IamInnocent</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321706</link>
		<dc:creator>IamInnocent</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321706</guid>
		<description>Apparently it is a little confused now... maybe someone asked it the question about itself and their server is kept in a closet ?</description>
		<content:encoded><![CDATA[<p>Apparently it is a little confused now&#8230; maybe someone asked it the question about itself and their server is kept in a closet ?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Sekino</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321970</link>
		<dc:creator>Sekino</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321970</guid>
		<description>&lt;i&gt;Every web paged I&#039;ve checked gets a &quot;male&quot; output. I&#039;d like to know the algorithms behind this.&lt;/i&gt;

Keywords &lt;i&gt;relationship&lt;/i&gt;, &lt;i&gt;shoes&lt;/i&gt;; animated GIFs of sparkling fairies, kissing emoticons = female

Keywords &lt;i&gt;gaming&lt;/i&gt;, &lt;i&gt;beer&lt;/i&gt;, technical lingo; animated GIFs of large breasts, mooning emoticons = male

That&#039;s my guess. Clearly, we&#039;re dealing with geniuses. :P



</description>
		<content:encoded><![CDATA[<p><i>Every web paged I&#8217;ve checked gets a &#8220;male&#8221; output. I&#8217;d like to know the algorithms behind this.</i></p>
<p>Keywords <i>relationship</i>, <i>shoes</i>; animated GIFs of sparkling fairies, kissing emoticons = female</p>
<p>Keywords <i>gaming</i>, <i>beer</i>, technical lingo; animated GIFs of large breasts, mooning emoticons = male</p>
<p>That&#8217;s my guess. Clearly, we&#8217;re dealing with geniuses. :P</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Lauren O</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321974</link>
		<dc:creator>Lauren O</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321974</guid>
		<description>&lt;i&gt;Clearly, we&#039;re dealing with geniuses.&lt;/i&gt;

Hey, these people know their gender stereotypes &lt;i&gt;very well&lt;/i&gt;.</description>
		<content:encoded><![CDATA[<p><i>Clearly, we&#8217;re dealing with geniuses.</i></p>
<p>Hey, these people know their gender stereotypes <i>very well</i>.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: justanotherusername</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-322230</link>
		<dc:creator>justanotherusername</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-322230</guid>
		<description>Who cares anyway?</description>
		<content:encoded><![CDATA[<p>Who cares anyway?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: rolandog</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321719</link>
		<dc:creator>rolandog</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321719</guid>
		<description>Drats. It says I&#039;m neither a man or a woman... I seem to have a gender error.</description>
		<content:encoded><![CDATA[<p>Drats. It says I&#8217;m neither a man or a woman&#8230; I seem to have a gender error.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: tubgull</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321724</link>
		<dc:creator>tubgull</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321724</guid>
		<description>&lt;a href=&quot;#comment-321703&quot; rel=&quot;nofollow&quot;&gt;@1&lt;/a&gt;

Could be worse. Last time I directly inquired as to someone&#039;s gender, I did not get so gracious a response.

Maybe someone could make a similar website that lets me ask women if they&#039;re pregnant.</description>
		<content:encoded><![CDATA[<p><a href="#comment-321703" rel="nofollow">@1</a></p>
<p>Could be worse. Last time I directly inquired as to someone&#8217;s gender, I did not get so gracious a response.</p>
<p>Maybe someone could make a similar website that lets me ask women if they&#8217;re pregnant.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Muscato</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321725</link>
		<dc:creator>Muscato</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321725</guid>
		<description>Three errors - and then being taken for a woman.  Takes me back to the 80s, when at least I had feathered hair and too much eye makeup...</description>
		<content:encoded><![CDATA[<p>Three errors &#8211; and then being taken for a woman.  Takes me back to the 80s, when at least I had feathered hair and too much eye makeup&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: LYNDON</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321985</link>
		<dc:creator>LYNDON</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321985</guid>
		<description>My guess the kind of thing it&#039;s looking for would be standard language features - as opposed to content - that are statistically more used by one gender.

In spoken conversation these usually include things like, kind of, more hedges and, um, conversational noise, y&#039;know?

(To my mind the gender trait here is signalling social non-dominance, which the females do more)

Or using &quot;I think&quot; rather than just asserting your opinion as fact. Or empathising and being agreeable.

I know someone did a thesis looking for these kinds of thing in IRC-style chat - specifically at whether people moderated their language style to the supposed gender of the person they were talking to.

This is statistically real diffrence but you&#039;ll find a lot of overlap between boys and girls.

But I don&#039;t know about more deliberate written work - people will use different voices for different purposes, For eg, as noted above, technical documentation will come out male.

Of course it&#039;s (I imagine) training and been fed a lot of examples - like a clever spam filter. So if it gets to working, it would indeed be interesting to see how.</description>
		<content:encoded><![CDATA[<p>My guess the kind of thing it&#8217;s looking for would be standard language features &#8211; as opposed to content &#8211; that are statistically more used by one gender.</p>
<p>In spoken conversation these usually include things like, kind of, more hedges and, um, conversational noise, y&#8217;know?</p>
<p>(To my mind the gender trait here is signalling social non-dominance, which the females do more)</p>
<p>Or using &#8220;I think&#8221; rather than just asserting your opinion as fact. Or empathising and being agreeable.</p>
<p>I know someone did a thesis looking for these kinds of thing in IRC-style chat &#8211; specifically at whether people moderated their language style to the supposed gender of the person they were talking to.</p>
<p>This is statistically real diffrence but you&#8217;ll find a lot of overlap between boys and girls.</p>
<p>But I don&#8217;t know about more deliberate written work &#8211; people will use different voices for different purposes, For eg, as noted above, technical documentation will come out male.</p>
<p>Of course it&#8217;s (I imagine) training and been fed a lot of examples &#8211; like a clever spam filter. So if it gets to working, it would indeed be interesting to see how.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Nancy Jane Moore</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-322498</link>
		<dc:creator>Nancy Jane Moore</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-322498</guid>
		<description>Well, it thinks my self defense blog -- &lt;a href=&quot;http://takingcareofourselves.blogspot.com/&quot;&gt;Taking Care of Ourselves&lt;/a&gt; is written by a man. I can&#039;t help but think that the concepts and language of self defense are automatically typed as male in our society. 

Or maybe the program just latched onto the words &quot;fourth-degree black belt&quot; and assumed I must be a guy. (In case you didn&#039;t look at my name or assumed &quot;Nancy Jane&quot; was just my online presence, I&#039;m female.)</description>
		<content:encoded><![CDATA[<p>Well, it thinks my self defense blog &#8212; <a href="http://takingcareofourselves.blogspot.com/">Taking Care of Ourselves</a> is written by a man. I can&#8217;t help but think that the concepts and language of self defense are automatically typed as male in our society. </p>
<p>Or maybe the program just latched onto the words &#8220;fourth-degree black belt&#8221; and assumed I must be a guy. (In case you didn&#8217;t look at my name or assumed &#8220;Nancy Jane&#8221; was just my online presence, I&#8217;m female.)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Abby</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321733</link>
		<dc:creator>Abby</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321733</guid>
		<description>Cuteoverload isn&#039;t written in English, apparently. 
&quot;Sorry, we can only classify web pages written in english&quot;</description>
		<content:encoded><![CDATA[<p>Cuteoverload isn&#8217;t written in English, apparently.<br />
&#8220;Sorry, we can only classify web pages written in english&#8221;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Sister Y</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321736</link>
		<dc:creator>Sister Y</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321736</guid>
		<description>My theory is that it thinks you&#039;re a woman if you talk about your feelings and stuff, and a man if you don&#039;t.</description>
		<content:encoded><![CDATA[<p>My theory is that it thinks you&#8217;re a woman if you talk about your feelings and stuff, and a man if you don&#8217;t.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Anonymous</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321743</link>
		<dc:creator>Anonymous</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321743</guid>
		<description>All technical articles written by me (female) are classified &quot;written by a male&quot;.
Only my English homepage where I state clearly &quot;gender: female&quot; is classified correctly.
Either not working for female geeks or its confused by my non-native English. Or should a female care about other themes? Then this tool is a case for real gender studies ...</description>
		<content:encoded><![CDATA[<p>All technical articles written by me (female) are classified &#8220;written by a male&#8221;.<br />
Only my English homepage where I state clearly &#8220;gender: female&#8221; is classified correctly.<br />
Either not working for female geeks or its confused by my non-native English. Or should a female care about other themes? Then this tool is a case for real gender studies &#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Clumpy</title>
		<link>http://boingboing.net/2008/11/03/gender-analyzer-did.html#comment-321757</link>
		<dc:creator>Clumpy</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">#comment-321757</guid>
		<description>Every web paged I&#039;ve checked gets a &quot;male&quot; output. I&#039;d like to know the algorithms behind this.</description>
		<content:encoded><![CDATA[<p>Every web paged I&#8217;ve checked gets a &#8220;male&#8221; output. I&#8217;d like to know the algorithms behind this.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
