Some things are just not right.. This happens to be one of them!!

So I admit I am something of a blog troll. I have the blogs I read daily, the ones I wait till the end of the week to entertain me when I'm at work late at night and then those that are observed more casually. Well its one of my casual observation's that had something that amused me.. some what.

What if you read a blog regularly but couldn't tell the gender of the blogger? What if for the curious nature all humans have had gotten to you when it came to this blogger? Have no fear! The GenderAnalyzer is here to save your day! Almost. See the way the program works is over a set amount of time data was imputed from bloggers here on Blogger.Com where their gender was already known for a set amount of blogs. I smell creative failure in the making, but hey I'm an open minded girl! Lets give it a try. I tested it with my blog - anyone care to take a guess at the gender it asumed for me?

-- Jeperdy theme --

If you guess Male, you'd get a cookie. If I had any. I'm not surprised really as my blog is about things guys often talk about after all. Moving on, the other blogger that wrote this artical on this page on did a randomized test in which they either knew the gender of the blogger before hand or (in the case of the New York Times ) it wouldn't take much to figure out. Some information on the blog - its HeartlessDoll.Com, a pop Culture blog of sorts writen by a few women. Its entertaining often and has some good articals. I don't always aggree but the girls make good points that I can see so it keeps me coming back.

Heartless Doll: written by a woman.
NYTimes.com: written by a man.
Jezebel: written by a woman.
Salon's Broadsheet: written by a man.
Heroine Sheik (my own blog): written by a man.

As you can see, there are some problems right off the bat. 1) NYTimes.com is not written exclusively by men. 2) Broadsheet is written by women. 3) I am not a man.

The break down of the way the program processes data shows that obviously the developers of this "Gender finder" really need to expand their testing ground and take blogs where their may be multiple posters in to consideration for the data used. My understanding of the way it works is much like a search bot on any webpage, crawling a site to hit on keywords basicly. Right?

Says Kagstrom, the developer, "I think the reason for the somewhat low accuracy is because we have biased training data (only collected from blogspot)." Yeah, Blogspot isn't necessarily the height of cultural nuance, but it is interesting to see what stereotypes get dredged up by using blogs like that to determine how men and women write. Check out some example of how Gender Analyzer thinks the following words break down, and you'll see what I mean:

Technology: 99.3% male
Love: 89.9% female
Sex: 56.6% male, 43.4% female.

So, if I follow this blog up with one where I typed Love a good twenty or thrity times - it MIGHT get my gender right. And the point of this silly program again is?

About GenderAnalyzer (BETA)

We created Genderanalyzer out of curiosity and fun. It uses Artificial Intelligence to determine if a homepage is written by a man or woman. Behind the scene, a text classifier hosted over at uClassify.com has been trained on 2000 blogs written by men and women. In our lab it seems to works pretty well, we want to see how it performs on the web! We hope you like it!

Uhm. Yeah.