Hard Light Productions Forums
Off-Topic Discussion => General Discussion => Topic started by: Dark Hunter on July 20, 2011, 11:55:24 pm
-
This is a silly little thing I recently came across. (http://www.hackerfactor.com/GenderGuesser.php) Basically, it's a word analysis program that takes large amounts of text someone writes and tries to determine their gender based on their use of language.
I hardly think it's very accurate, but still fun. It is supposed to work better the longer the text you enter.
My results, based on a short paper I recently wrote for college:
Total words: 1420
Genre: Informal
Female = 1698
Male = 3633
Difference = 1935; 68.14%
Verdict: MALE
Genre: Formal
Female = 1549
Male = 2640
Difference = 1091; 63.02%
Verdict: MALE
(For the record, I am male.)
-
Amusing, it says I'm 70% MALE in informal writing, but 43% WEAK FEMALE in formal writing...
Apparently this also could be an indication that I'm secretly European.
:shaking:
-
I could probably make this thing explode with one of my lab reports or senior design paper.
-
Make Batutta use this.
-
Make Batutta use this.
hahahahaha
-
Inputting some of my fiction gave the complete range of results depending on what I gave it.
The only thing I can tell that actually changed, though, was the the Female bit failed the Bechdel Test. Which doesn't say good things about whoever wrote this.
-
Make Batutta use this.
Inputting his Cyclops bug report:
Genre: Informal
Female = 1043
Male = 1620
Difference = 577; 60.83%
Verdict: MALE
Genre: Formal
Female = 658
Male = 857
Difference = 199; 56.56%
Verdict: Weak MALE
Weak emphasis could indicate European.
-
Weak emphasis could indicate European.
Because Europeans are effeminate.
-
For the record that's part of the program's output, not my commentary.
-
well at least I'm not a female :P, but weak male??
I need to start going to the gym again.
-
I was assuming there was going to be a bunch of Thai hookers and you had to guess which one was naturally a woman.
-
And if you lost you had to drink liposuction fluid?
-
I input a short story I wrote from a first-person perspective, as a female character. The results are:
Genre: Informal
Female = 2817
Male = 7696
Difference = 4879; 73.2%
Verdict: MALE
Genre: Formal
Female = 3823
Male = 4104
Difference = 281; 51.77%
Verdict: Weak MALE
Weak emphasis could indicate European.
I'm not sure what specifically that indicates
-
well at least I'm not a female :P, but weak male??
I need to start going to the gym again.
For the record, at some level everyone can be AT LEAST be classified as "weak female." :p
-
I put in an article by Ursula K. Le Guin (maybe one of the most feminine writers ever) and it gave me 70% male. Some guesser.
-
well at least I'm not a female :P, but weak male??
I need to start going to the gym again.
For the record, at some level everyone can be AT LEAST be classified as "weak female." :p
or "european".... I'm slightly pissed off at the innuendo there if no one else noticed...
-
These are the results I got. I don't have anything longer on hand that might give a more accurate result... oh well. :blah:
Total words: 1055
Genre: Informal
Female = 1881
Male = 2207
Difference = 326; 53.98%
Verdict: Weak MALE
Weak emphasis could indicate European.
Genre: Formal
Female = 1030
Male = 1610
Difference = 580; 60.98%
Verdict: MALE
-
this is one of Battuta's short stories he posted on here a while ago, think it was about space tube babies and spaceships and cyborgs or something. Just for kicks. :p
Total words: 9028
Genre: Informal
Female = 9173
Male = 15914
Difference = 6741; 63.43%
Verdict: MALE
Genre: Formal
Female = 10705
Male = 10883
Difference = 178; 50.41%
Verdict: Weak MALE
Weak emphasis could indicate European.
and myself, from a term paper I wrote on Armor back in high school
Total words: 6799
Genre: Informal
Female = 7449
Male = 16237
Difference = 8788; 68.55%
Verdict: MALE
Genre: Formal
Female = 6695
Male = 10802
Difference = 4107; 61.73%
Verdict: MALE
Though all of my short stories that I've ran through it seem to come up weak male in formal. Not too surprising, as my narrative writing is understandably different than expository.
-
I wonder penis what would happen penis if you wrote "penis" every five words penis.
-
I wonder penis what would happen penis if you wrote "penis" every five words penis.
Verdict: You're apparently a 13 year old weak male
-
Total words: 15
Too few words. Try 300 words or more.
Genre: Informal
Female = 0
Male = 25
Difference = 25; 100%
Verdict: MALE
Genre: Formal
Female = 47
Male = 35
Difference = -12; 42.68%
Verdict: Weak FEMALE
Weak emphasis could indicate European.
:lol:
-
OH SNAP, ANOTHER WEAK FEMALE! GET OVER HERE, WE GOTTA COMPARE OUR EUROPEAN SHOULDERBAGS!
It's like its got this hint of sexism but you can't quite pinpoint exactly where!
-
Oh nice, a program that manages to combine racial and sexual stereotypes in one easy bundle....
-
I think I get a formal average of 75% male and informal percentage of 50% :p based on lab reports and silly little stories and lists that I have written...
-
so i took a sample out of one of my old colledge reports and tested it. mind you this is circa 2002. and here are the results:
Total words: 1093
Genre: Informal
Female = 1121
Male = 2375
Difference = 1254; 67.93%
Verdict: MALE
Genre: Formal
Female = 1158
Male = 1748
Difference = 590; 60.15%
Verdict: MALE
not satisfied i looked at my most recent forum posts, found the biggest one on the first page and got this:
Total words: 472
Genre: Informal
Female = 788
Male = 1078
Difference = 290; 57.77%
Verdict: Weak MALE
Weak emphasis could indicate European.
Genre: Formal
Female = 496
Male = 470
Difference = -26; 48.65%
Verdict: Weak FEMALE
Weak emphasis could indicate European.
the first sample was obviously formal, since it got me an a in my psychology 101 class. the second sample just being a long forum post on gd from one of the recent space threads (so slightly technical), sans spelling errors. so id call it informal. using the right genre preference, id say their algorithms are adequate though far from perfect.
-
Weak emphasis could indicate European.
Total words: 481
Genre: Informal
Female = 558
Male = 877
Difference = 319; 61.11%
Verdict: MALE
Genre: Formal
Female = 183
Male = 591
Difference = 408; 76.35%
Verdict: MALE
Not bad for a European, eh?
Conclusive proof that EU >>> US. Both in masculinity and otherwise.
-
for the record i am not european.
-
Proud English.
-
When I wrote something simple and normal about daily things, I get this:
Genre: Informal
Female = 725
Male = 285
Difference = -440; 28.21%
Verdict: FEMALE
Genre: Formal
Female = 676
Male = 350
Difference = -326; 34.11%
Verdict: FEMALE
But if I use more serious text about games or aliens like the shivans I said in the BP forum, it says something else again. So I'm not sure about these silly things, I guess it gives words a score or whatever which then says how likely it is a guy or girl wrote it. If I write formal, I write the way my old teachers at school told me to write. And ofcourse because Dutch standards were not so high back then for learning English, I used what I read on forums and have seen on television and what I saw in games. Having to write scriptions for college and artschool also makes you look at native english texts to get your sentences just right. A good example is my old teacher I had the last few years who was a britton himself. He saw I had a keen interesting in improving my english and asked if I wanted to go a step further by learning to use british english. I say colour and not color and Americans and Europeans raise eyebrows when I pronounce the word 'either', while the British crack a smile and give a thumb up. It sure shows that when you are not english, you instead go with what you learned. Monkey see, monkey do?
Taking a text from my post history that I wrote, trying to be a lot more formal, gives:
Genre: Informal
Female = 2628
Male = 7291
Difference = 4663; 73.5%
Verdict: MALE
Genre: Formal
Female = 3926
Male = 4735
Difference = 809; 54.67%
Verdict: Weak MALE
Weak emphasis could indicate European.
So I say, shenanigans! :P I might be an alternate rock baitch, but I'm sure not butch, lol.
So here comes the interesting part.. I tried playing around with that tool a bit! And the results? Amazing(ly wrong), but really funny too! Some really funny facts I collected by playing around with the tool :lol::
- When I used the words hon, honey, love, sweetie and dove a lot, I got a predominantly female score!
- Upon pasting texts written by a 12 years old Yahoo!Answers user who lacks punctuation marks, it almost always says female!
- I pasted a text from a feminist blog, then another text and yet again another text. They were all rated very Male (over 75% of the score)!
- Also I pasted some rants, complaints and generic writings by Conservative Republicans which I googled up and despite the poster's gender, almost all were rated as weakly female!
- If I paste texts written by people with a learning disability, it says they are female!
So I guess that debunks it. :P It embraces sexism to the point that everything written by someone with not such a high IQ is considered female, while formal and elaborate texts are rated as male! And that by an Israeli university? We must release Herr Battuta on this topic at once! :D
-
Total words: 933
Genre: Informal
Female = 180
Male = 2607
Difference = 2427; 93.54%
Verdict: MALE
Genre: Formal
Female = 888
Male = 1406
Difference = 518; 61.29%
Verdict: MALE
-
.....and to call europeans "WEAK FEMALES". I mean just gimme a gun and an address, will you?
-
Am I the only one who actually opened the cited paper that spawned this thing? If one looks at the abstract...
This paper explores differences between male and female writing in a large subset of the
British National Corpus covering a range of genres. Several classes of simple lexical and
syntactic features that differ substantially according to author gender are identified, both in
fiction and in non-fiction documents. In particular, we find significant differences between
male- and female-authored documents in the use of pronouns and certain types of noun
modifiers: although the total number of nominals used by male and female authors is virtually
identical, females use many more pronouns and males use many more noun specifiers. More
generally, it is found that even in formal writing, female writing exhibits greater usage of
features identified by previous researchers as "involved" while male writing exhibits greater
usage of features which have been identified as "informational". Finally, a strong correlation
between the characteristics of male (female) writing and those of nonfiction (fiction) is
demonstrated.
...one will find the experimentally-derived rationale for the formula. Don't criticize the tool for sexism; it's merely reporting on writing tendency correlations. It has nothing whatsoever to do with IQ, stereotypes, or sexism.
(As an aside, it is unsurprising that much formal/technical writing returns a male result as it tends to be used in fields that, until very recently, were/are dominated by men. Successful women tend to emulate male writing styles in those scenarios, and in doing so conform to the expectations of the reader. Nowhere is this more evident than in journalism - a point the paper touches on). As for weak emphasis indicating European, non-native English speakers should show fewer markers in general because they tend to think in their own native language - most of which actually incorporate gender directly into several aspects of language (while English generally does not). French is an excellent example.
But don't let me get in the way of silly outrage, please do continue. *eyeroll*
-
this implementation may be bogus but it makes you think that this is a thing computers can do given the proper algorithms. no doubt the basis of these algorithms is stereotypical data. you would have to to a lot more research into how males and females use language, identify other cues than simply whether words used were weighted male or female. take it a step further and you could probably identify country of origin as well. id bet the cia has something that can do this.
-
no doubt the basis of these algorithms is stereotypical data.
Looks observationally-derived from a scientific methodology to me. See my post above.
-
no doubt the basis of these algorithms is stereotypical data.
Looks observationally-derived from a scientific methodology to me. See my post above.
sorry we posted at exactly the same time there. and i wasnt gonna edit :D
-
sorry we posted at exactly the same time there. and i wasnt gonna edit :D
Fair enough. =)
-
It mostly seems statistical rubbish to me, conveyed to demonstrate the stereotypes that the researcher already had in his mysoginistic mind.
-
It mostly seems statistical rubbish to me, conveyed to demonstrate the stereotypes that the researcher already had in his mysoginistic mind.
Maybe you should have read the paper before leaping to conclusions. If you had, you'd see that the principle is based on 30 years of research and that the methodology used here is based on rigorous AUTOMATED (i.e. no human input) statistical analysis of published documents (including journal articles), half from writers of each gender, from a reputable source collection (British National Corpus). Page 5 of the PDF, if you'd like to stop making silly assertions without a shred of evidence.
Or carry on, whichever.
-
Every statistical analysis is "automated" in the sense of being a computation, so I really don't get where you are going there with that word. The paper is fine and dandy, in that sense. It would only get interesting if it really predicted anything outside of its own database.
-
Your little deviations produces this result, you guys:
Genre: Informal
Female = 107
Male = 317
Difference = 210; 74.76%
Verdict: MALE
Genre: Formal
Female = 230
Male = 160
Difference = -70; 41.02%
Verdict: Weak FEMALE
-
Every statistical analysis is "automated" in the sense of being a computation, so I really don't get where you are going there with that word. The paper is fine and dandy, in that sense. It would only get interesting if it really predicted anything outside of its own database.
The statistical analysis was automated in the sense that a human being did not pick what things identified "male" or "female" writing. The tool is BASED on the methodology and algorithm used in the paper - so it IS predicting outside of the database used to create it.
Read. The. Paper.
-
MP-Ryan is completely correct. If you even skim over page 5 - 6 of the paper you'll see that the data was gathered quite objectively. An examination of the source code of the tool reveals its operation to be really quite simple: It splits the input into a list of words, and then searches that list for occurences of particular words which have been determined to be useful (ie statistically viable) in distinguishing texts written by one gender from tests written by the other gender. Based on the word, it adds a certain weight to a score for either informal or formal words. Words suggesting a male author have a positive weight and words suggesting a female author have a negative weight, and the absolute value obviously denotes how much it suggests its respective gender. The algorithm the tool uses really has little to do with the algorithm used to determine the weights of each word, merely being an application of the findings of the study that used the algorithm. In fact, the tool on the website could have been written by a first year programming student.
-
TBH, I never expected this thing to work. If anybody could guess the writer's gender based on one example of his/her writing, it'd be a human psychologist who worked on that for these 30 years, and even then, he/she won't be 100% sucessfull. I tend to be skeptical about both statistics and psychology, and this is "statistical psychology", conducted by a machine to boot. In order for computer to handle this, it'd need to have a real artificial intelligence (and even then, it'd still make mistakes from time to time).
-
Well if you're still skeptical of the study, you've got a tool here that can confirm its results. Even disregarding any support shown here, I'd bet money that it's right a fair amount more often than it's wrong.
-
I have to admit, I'm likewise fairly convinced that if you present it truthful data it will likely return a truthful answer.
Except about being European. That it's got a problem with.
-
I could never stomach reading papers like this, so if somebody (Ryan) who did could sum up: what is with the European thing?
Did they find that European writers tend to use more of the same words regardless of whether they were male or female?
-
What I suspect is that the software was written to analyze American English. Europeans use the language a bit differently, so they're acknowledging that that might mess with its results.
-
Total words: 1439
Genre: Informal
Female = 346
Male = 4845
Difference = 4499; 93.33%
Verdict: MALE
Genre: Formal
Female = 1048
Male = 2498
Difference = 1450; 70.44%
Verdict: MALE
Have it the first few paragraphs of a research essay I wrote for a uni class on eroge/anime.
Yeah, I did a lot of what it said males generally do. :/
Guess paper on the wonders of 2D women is manly.
-
(http://img36.imageshack.us/img36/5169/guesser.png)
Very interesting this gender guesser. I'm obviously not that inspired or caring to type more into it. Just wanted to see what it would do with such blatancy. I've had my fun.
-
So i typed the word "sex" in 300 times (hey it said 300 words minimum!!) and it couldn't decide the gender... mmmh ;)
-
It'll basically read that as 1 word...
-
You could try the lyrics to "I Just Had Sex" instead.
-
What you gon' do with all that junk?
All that junk inside your trunk?
I'ma get, get, get, get, you drunk,
Get you love drunk off my hump.
My hump, my hump, my hump, my hump, my hump,
My hump, my hump, my hump, my lovely little lumps (Check it out)
I drive these brothers crazy,
I do it on the daily,
They treat me really nicely,
They buy me all these ices.
Dolce & Gabbana,
Fendi and that Donna
Karan, they be sharin'
All their money got me wearin' fly
Brother I ain't askin,
They say they love my ass ‘n,
Seven Jeans, True Religion's,
I say no, but they keep givin'
So I keep on takin'
And no I ain't taken
We can keep on datin'
I keep on demonstrating.
My love (love), my love, my love, my love (love)
You love my lady lumps (love),
My hump, my hump, my hump (love),
My humps they got you,
She's got me spending.
(Oh) Spendin' all your money on me and spending time on me.
She's got me spendin'.
(Oh) Spendin' all your money on me, up on me, on me
What you gon' do with all that junk?
All that junk inside that trunk?
I'ma get, get, get, get, you drunk,
Get you love drunk off my hump.
What you gon' do with all that ass?
All that ass inside them jeans?
I'm a make, make, make, make you scream
Make you scream, make you scream.
Cos of my hump (ha), my hump, my hump, my hump (what).
My hump, my hump, my hump (ha), my lovely lady lumps (Check it out)
I met a girl down at the disco.
She said hey, hey, hey yea let's go.
I could be your baby, you can be my honey
Let's spend time not money.
I mix your milk wit my cocoa puff,
Milky, milky cocoa,
Mix your milk with my cocoa puff, milky, milky riiiiiiight.
They say I'm really sexy,
The boys they wanna sex me.
They always standing next to me,
Always dancing next to me,
Tryin' a feel my hump, hump.
Lookin' at my lump, lump.
You can look but you can't touch it,
If you touch it I'ma start some drama,
You don't want no drama,
No, no drama, no, no, no, no drama
So don't pull on my hand boy,
You ain't my man, boy,
I'm just tryn'a dance boy,
And move my hump.
My hump, my hump, my hump, my hump,
My hump, my hump, my hump, my hump, my hump, my hump.
My lovely lady lumps (lumps)
My lovely lady lumps (lumps)
My lovely lady lumps (lumps)
In the back and in the front (lumps)
My lovin' got you,
She's got me spendin'.
(Oh) Spendin' all your money on me and spending time on me.
She's got me spendin'.
(Oh) Spendin' all your money on me, up on me, on me.
What you gon' do with all that junk?
All that junk inside that trunk?
I'ma get, get, get, get you drunk,
Get you love drunk off my hump.
What you gon' do with all that ass?
All that ass inside them jeans?
I'ma make, make, make, make you scream
Make you scream, make you scream.
What you gon' do with all that junk?
All that junk inside that trunk?
I'ma get, get, get, get you drunk,
Get you love drunk off this hump.
What you gon' do wit all that breast?
All that breast inside that shirt?
I'ma make, make, make, make you work
Make you work, work, make you work.
(A-ha, a-ha, a-ha, a-ha) [x4]
She's got me spendin'.
(Oh) Spendin' all your money on me and spendin' time on me
She's got me spendin'.
(Oh) Spendin' all your money on me, up on me, on me.
Genre: Informal
Female = 292
Male = 232
Difference = -60; 44.27%
Verdict: Weak FEMALE
Weak emphasis could indicate European.
Genre: Formal
Female = 845
Male = 430
Difference = -415; 33.72%
Verdict: FEMALE
Maybe they're on to something.
-
baaahahahahahaha