Sunday, November 16, 2008

Should have guessed...

While riding on the internets, and surfing the tubes, I came across this nifty site called Gender Analyzer. Using free text classifier algorithms from a site called Uclassify, this site aims to judge whether a blog/website is written by a woman or a man. A very active research topic.

Gender Analyzer

I tried out using some known standard cases, and here’s the goldmine.
Evil Sense
Gosh, I didn't know that Machine Learning had become so accurate these days. Be paranoid, very.

Incidentally, Chappar, when you were on wordpress, your manliness rating was 83%. Did anything special happen during the transition phase?

A thousand apologies, plus one extra, just in case.
And to those who might think of an oh-so-brilliant, "Look who's talking !!!",line. I'm at 71%. Muha ha ha.

So go ahead, check your (wo)manliness rating...

P.S: Incidentally again, this is the 2nd in the chappar series of posts, the first one having been written nearly 2 years ago.[hyper-link to click in case you're bored]


  1. We think is written by a man (85%).

  2. Must be all that "mindf**k" episodes you wrote about. Had all sorta gangsta words.

  3. 100% female !!? Duh

  4. Dude, its text based. With stuff like " Bollywood hungama", "glitzy glamour", "fashion tips", and "britney spears gossip" dominating the yahoo homepage, what else did you expect?
    Now a days even chicks write about sports and politics, so no points there as well.
    Even a 'lazy' algorithm would make the same decision.
    And this is only meant for blogs where content, news is put up. Not for generic websites, eg. google is supposedly male. This is because the training set in the first place, were some 2000 blogs. So random sites, would end up being outliers.

  5. 1. had only 3 posts when you did that.
    2. Thanks for reminding, I went on and installed wordpress.

    51% with such less data is quite interesting.

  6. @Dr.evil -
    1.More data needn't necessary improve your mojo.Or maybe your writing was so weird that it couldn't decipher it. Humans can't anyway, so I am not betting much on a program to do it.
    In fact, this is the new version of the turing test. Anything that says that it can understand you, can't possibly be a human.
    2. You're most welcome.

  7. @Logik: I think it was mainly because it took in data from my Master TB Ascii art.

  8. Dude, that ascii thing was a master piece man.. why did you remove that?.
    And btw, did you check out the ascii train tool. It is a script/program, runs on bash/terminal. and produces a moving train of ascii-ness.

  9. WTF??? I am 56% female??? I hate my blog now!

  10. Humph! Check out

    I made a list of gender blunders here.. that site is not accurate!

  11. @hashish - Dude, I know u get a devious pleasure when u say that out loud, but care to elaborate?

    @varun - A new training set was added on 26th november, and my manlyhood rating has changed sides.
    But, the whole thing was meant for timepass. And if u want ur alpha-male affirmation from that, so be it. Best of luck.

  12. @Abhi: D-uh! Its a joke in our class, the alpha male term is a lil different.. Leave!

  13. @varun- as i said before, whatever floats your boat is fine. I don't believe the alpha-male concept anyway. For all i care, it's just a politically correct term for an arrogant bully. And as for your class, i suppose the alpha male spot is a bit too competitive. ;-)

  14. Good one: "politically correct term for an arrogant bully"...