Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Linguists Out Men Impersonating Women On Twitter

timothy posted about 3 years ago | from the anything-that-can-be-described-can-be-faked dept.

Twitter 350

Hugh Pickens writes "Remember when the Gay Girl in Damascus revealed himself as a middle-aged man from Georgia? On a platform like Twitter, which doesn't ask for much biographical information, it's easy (and fun!) to take on a fake persona but now linguistic researchers have developed an algorithm that can predict the gender of a tweeter based solely on the 140 characters they choose to tweet. The research is based on the idea that women use language differently than men. 'The mere fact of a tweet containing an exclamation mark or a smiley face meant that odds were a woman was tweeting, for instance,' reports David Zax. Other research corroborates these findings, finding that women tend to use emoticons, abbreviations, repeated letters and expressions of affection more than men and linguists have also developed a list of gender-skewed words used more often by women including love, ha-ha, cute, omg, yay, hahaha, happy, girl, hair, lol, hubby, and chocolate. Remarkably, even when only provided with one tweet, the program could correctly identify gender 65.9% of the time. (PDF). Depending on how successful the program is proven to be, it could be used for ad-targeting, or for socio-linguistic research."

cancel ×

350 comments

Let's hope that 15%... (4, Insightful)

Lead Butthead (321013) | about 3 years ago | (#36914946)

I hope that extra 15% certainty didn't cost millions in research grants; as a blind guess has 50% chance of being right.

Re:Let's hope that 15%... (1)

MyFirstNameIsPaul (1552283) | about 3 years ago | (#36914970)

I dunno'. What's 1 SD worth?

Re:Let's hope that 15%... (1)

Anonymous Coward | about 3 years ago | (#36915032)

That's 65% with just one tweet, though; presumably quality is better given more tweets as sample data.

Going by the description of the research in the article, it doesn't sound even remotely impressive though- yes, just because certain words happen to be used more by women and certain words used more by men doesn't mean that this is specifically helpful in working out people who are deliberately trying to be perceived as the opposite sex. This 65% will have been an average over a huge corpus of tweets, a lot of which would likely include terms like the ones listed in the summary- in short, ones that make the sex of the tweeter either obvious or close to obvious. I'd say a human could probably get better than 65% from a single tweet _on average_, making the ability of this to determine the sex of a tweeter who is deliberately trying to fool people (and succeeding at it) dubious.

Re:Let's hope that 15%... (1)

101010_or_0x2A (1001372) | about 3 years ago | (#36915400)

One of their graphs is labeled "Performance increases with more tweets from target user", showing that at 32 tweets, their accuracy is > 90%. However this is including things like screen name, profile descriptions and full name. Using only tweets they are at 76% even with many tweets, so yeah quality *is* bettwe but not by much. They also say that only 5% of humans performed better than the machine with many tweets.

Re:Let's hope that 15%... (1)

spazdor (902907) | about 3 years ago | (#36915462)

That's 65% with just one tweet, though; presumably quality is better given more tweets as sample data.

I wouldn't be so sure. I think the uncertainty might have less to do with a given user's linguistic variation from one tweet to the next, and more to do with the fact that gender isn't actually the sole determinant of how people talk. If 30% of women consistently produce "male-sounding" language and 30% of men produce "female-sounding" language, according to whatever metric these researchers have come up with, that's quite different from if all women produce "male-sounding" language 30% of the time and vice versa. I find the first scenario far more likely than the second, and if this were true, it would imply that gathering more tweets from the same user is unlikely to make their guess much better.

Reading between the lines, I suspect that if reading subsequent tweets *did* refine their estimates significantly, they would have opted to use a more impressive stat such as "80% certainty after reading ten tweets".

Re:Let's hope that 15%... (1)

spazdor (902907) | about 3 years ago | (#36915496)

(this is all from merely RTFS, though. I'm not really interested enough to look at their data, but which stat they chose to put in the summary speaks volumes.)

Re:Let's hope that 15%... (1)

dreampod (1093343) | about 3 years ago | (#36915712)

They also had a handful of Amazon Mechanical Turk users identify gender for the same tweets and they were 67.3% accurate for single tweets compared to the automated system's 67.8%.

Well depends on how it increases (3, Insightful)

Sycraft-fu (314770) | about 3 years ago | (#36915044)

A statistically significant amount of accurate based on a single, at most 140 character, statement is not a small thing, so long as it scales with more. If that means that with a few statements or a longer statement you get in to the high 90s then that would be quite interesting. If it is 65% right all the time, then yes it was rather a waste.

Re:Well depends on how it increases (1)

Jah-Wren Ryel (80510) | about 3 years ago | (#36915146)

If it is 65% right all the time, then yes it was rather a waste.

Disagree - that's 2:1 odds, which is still pretty huge all on its own.

Re:Well depends on how it increases (2)

wealthychef (584778) | about 3 years ago | (#36915180)

How is this "huge?" What the hell are you going to do with it? Someone tweets and uses an exclamation point, so you... what now?

Re:Well depends on how it increases (5, Funny)

raehl (609729) | about 3 years ago | (#36915298)

I go to my congressional office, take my shirt off, arrange my family photos in the background, and take a picture to send to them.

Re:Well depends on how it increases (1)

mdf356 (774923) | about 3 years ago | (#36915812)

hahaha, dammit, my mod points expired yesterday. You, sir, made me LOL. I assume you're a guy since there's no exclamation points or smileys! :-)

Re:Well depends on how it increases (2)

Strange Ranger (454494) | about 3 years ago | (#36915506)

"How is this "huge?" What the hell are you going to do with it? Someone tweets and uses an exclamation point, so you... what now?"
 
You look at more of their tweets until you're 98% sure. Then target your advertising.
 
GONG! Thanks for playing.

Re:Well depends on how it increases (1)

Jah-Wren Ryel (80510) | about 3 years ago | (#36915574)

How is this "huge?" What the hell are you going to do with it? Someone tweets and uses an exclamation point, so you... what now?

What's your point? 2:1 doesn't qualify as huge to you? If it were 10:1 odds what now?

Re:Well depends on how it increases (3, Funny)

IceNinjaNine (2026774) | about 3 years ago | (#36915300)

If that means that with a few statements or a longer statement you get in to the high 90s then that would be quite interesting.

Interesting stuff. I wrote the first revision of my best friend's profile for match.com (I'm a man, she's a woman) simply because she was just awful at putting her best foot forward. She tweaked it, but I wonder how that would have come out under such analysis.

Noooo! She's not a lithe fifty year old target shooting yoga instructor, she's a MAN! ;)

Re:Well depends on how it increases (3, Insightful)

LordLucless (582312) | about 3 years ago | (#36915484)

I wonder what the proportions are on tweets that are deliberately intending to be misleading. Getting a 65% hit rate on people who are attempting to deceive is much more impressive than 65% who aren't making any attempt to obfuscate their gender.

Re:Well depends on how it increases (1)

dreampod (1093343) | about 3 years ago | (#36915700)

They claim 75% accuracy when they analyze every tweet the account produced.

Re:Well depends on how it increases (0)

Anonymous Coward | about 3 years ago | (#36915792)

the accuracy does scale with extra info, but tops out in the low 90s.

from TFA:

info: gender prediction success rate
one tweet: 65.9%
profile description: 71.2%
all tweets: 75.8%
screen name: 77.1%
full name: 89.1%

all tweets + screen name: 81.4%
screen name + description + all tweets: 84.3%
all four fields: 92.0%

i didn't catch how (if) the algorithm weights the fields differently when predicting gender.

Re:Let's hope that 15%... (0)

Anonymous Coward | about 3 years ago | (#36915088)

Source for twitter accounts being split evenly between genders ?

Re:Let's hope that 15%... (2)

MightyMartian (840721) | about 3 years ago | (#36915102)

We'll just pay the researchers in bitcoins.

Re:Let's hope that 15%... (0)

Anonymous Coward | about 3 years ago | (#36915104)

I hope that extra 15% certainty didn't cost millions in research grants; as a blind guess has 50% chance of being right.

Nope. A blind guess is equal to the proportion of women on twitter. If there are 65% of twitter users that are actually women, then their predictor is just doing as good as random...

Re:Let's hope that 15%... (0)

Anonymous Coward | about 3 years ago | (#36915498)

Nope. A blind guess is equal to the proportion of women on twitter. If there are 65% of twitter users that are actually women, then their predictor is just doing as good as random...

Not really. Even if all the users were women you'd still have a 50% chance of guessing right using an unbiased coin toss: whatever the sex of each person, you either get it right or get it wrong.

A biased guess would of course yield different results depending on the population, but that's not usually what people mean by "guessing".

Re:Let's hope that 15%... (1)

Gideon Wells (1412675) | about 3 years ago | (#36915170)

Apparently "blind guessing" didn't work with "Gay Girl in Damascus".

With only 140 characters to work with I am finding 65.9% impressive. When I get a chance I hope to read the full article to see if it mentions that 15% increases dramatically when given more to work with. As I implied/snarked in the first line, a blind guess would requiring assuming every person is a lying SOB and randomly assuming they could be a different gender. I'd like to see how this program compared to neutral online entities (not trying to be one or the other), genuine entities (truthfully who they say they are) and liars (false genders).

This research does have uses and benefits if it can be expanded upon. Boosting the efficiency of targeted advertising, as said in the summary. The stated socio-linguistic research could assist in robotics/AIs bridge the uncanny valley when we reach that river. There is also the psychology aspect of it. How much of this is universal and just American-English? Can this be applied to other languages to pick up like patterns?

It reminds me of a TED talk, will link in a sub-comment if I can find it, from a man who that was given the task to mediate between Western and Indian medical professionals. Eventually he found out that language and the psychology of each culture was leading to problems. He found his Western colleagues were more bound by absolute truths and hierarchy while the Indian colleagues were more generalists. He attributed this to the regional cultural faiths (one life, obey the god, one truth, one chance vs reincarnation, multiple attempts, will work out eventually).

I hope millions were spent on this, but I don't see it is a complete waste for just being only 15%.

Agree (0)

Anonymous Coward | about 3 years ago | (#36915206)

I'd be more impressed if it was wrong 70% of the time.

Re:Agree (1)

Anonymous Coward | about 3 years ago | (#36915730)

Then all the women would know that the algorithm is a man ;-)

Re:Let's hope that 15%... (0)

Anonymous Coward | about 3 years ago | (#36915224)

Wouldn't a man impersonating a woman try to use language and 'smiley' faces to seem like a woman. I think this is more they can identify males, writing as males, on twitter.

Re:Let's hope that 15%... (2, Insightful)

Anonymous Coward | about 3 years ago | (#36915232)

It seems to me that there are more men than women posting on twitter, so guessing man on every tweet might yield a higher accuracy than this algorithm.

Re:Let's hope that 15%... (1)

dreampod (1093343) | about 3 years ago | (#36915680)

According to the study's (dubious) technique of identifying the gender of tweeters, the breakdown is 42% female, 35% male, 23% unidentified.

Re:Let's hope that 15%... (4, Insightful)

bwayne314 (1854406) | about 3 years ago | (#36915244)

HAHA! omg, thats soooo cute! ....

oh, yea, :)

MOD PARENT UP (1)

PRMan (959735) | about 3 years ago | (#36915328)

This is exactly what I was going to say... Where's my mod points?

Re:Let's hope that 15%... (2)

he-sk (103163) | about 3 years ago | (#36915330)

That's a 65% prediction rate based on a single tweet. The authors report a 92% success rate for the best classifier on the entire set. If they restrict the data set just to tweet texts (but more than one), they achieved a 76% success rate. That still might not satisfy you, but the authors also report that only 5 in 130 people correctly classified 100 tweets with a higher accuracy.

Re:Let's hope that 15%... (1)

shermo (1284310) | about 3 years ago | (#36915724)

What's the male/female split of posters on Twitter?

If 65.7% of users are male I can guess what gender a poster is and I'll get it right 65.7% of the time.

Re:Let's hope that 15%... (0)

Anonymous Coward | about 3 years ago | (#36915788)

It's not like the money spent on the research was burned in an incinerator in the middle of no where. The money went towards the pay researchers, managers, support staff, cleaning staff, etc. at the research facility. These people then went out and bought houses, cars, McDonald's shakes, LCD TVs, etc. Other portions of the money go toward lab equipment and facilities and the like. These funds also enter the economy.

Money spent on research isn't wasted. It goes right into the economy.

I'm tired of these teabag-esque people always stating the money spent on research is pissed-away. It is not. It goes into the economy.

The type of thinking this person has is indicative of someone that has their mental development stunted at 14 years of age.

This doesn't work on me. (0)

Anonymous Coward | about 3 years ago | (#36914948)

I'm a lesbian trapped in a man's body.

Re:This doesn't work on me. (1)

_merlin (160982) | about 3 years ago | (#36915256)

Quite seriously though, I'm a straight guy, and I make heavy use of exclamation marks, emoticons, "omg", "haha" and "love" in IM conversations, although not so much when blogging. I don't use Twitter, so one can't say whether I'd show these girly traits there.

Re:This doesn't work on me. (0)

Anonymous Coward | about 3 years ago | (#36915268)

I think you mean:

Hi lovers, I'm a lesbian trapped in a man's body! ;) Kisses!

Re:This doesn't work on me. (1)

jc42 (318812) | about 3 years ago | (#36915274)

I'm a lesbian trapped in a man's body.

Heh. In our house, my wife occasionally comments on how several well-known online companies (including netflix and google) seem to have decided that she's a gay male. If so, she's very good at impersonating a straight female when I'm around. ;-)

So far, we haven't actually found any downside to this, but it's not hard to imagine situations where it could cause serious problems. For example, the guys who killed Matt Shepard [wikipedia.org] might not believe that her "disguise" isn't a disguise. Such things happen in our world.

So I'm not really all that comfortable with the idea that a piece of software somewhere will be inferring things about me related to sex, and giving its conclusions to people who I don't know, to do with as they like. Our society has a long, sorry history telling us what this can lead to.

One thought, I suppose, might be "How can a lot of us work to sabotage things like this and poison their inferences?" Another might be "Is there a way we can learn about who is getting such inferred info about us, and what they're planning to do with it?" Or "It there a way we can find out who has bought this information, and sue the perpetrators if the information is incorrect?"

Re:This doesn't work on me. (1)

snowgirl (978879) | about 3 years ago | (#36915504)

One thought, I suppose, might be "How can a lot of us work to sabotage things like this and poison their inferences?" Another might be "Is there a way we can learn about who is getting such inferred info about us, and what they're planning to do with it?" Or "It there a way we can find out who has bought this information, and sue the perpetrators if the information is incorrect?"

There really isn't a way to be able to sue them, unless you consider being called the wrong sex defamation, but even if you do, I doubt that courts would really recognize it as an actionable claim.

Who Knew! (2)

DoomHamster (1918204) | about 3 years ago | (#36914952)

Huh...the word "hubby" is used more by women. Who knew!

Re:Who Knew! (1)

DoomHamster (1918204) | about 3 years ago | (#36914968)

Yikes! Does the fact that I used an exclamation mark make me more feminine? OMG!! Err....AAUUUUGHHH!!!!! :(

Re:Who Knew! (5, Funny)

MightyMartian (840721) | about 3 years ago | (#36915116)

The mere fact that you show emotion outs you. Real men only use periods and commas, AND TYPE IN ALL CAPS BECAUSE REAL MEN ARE ALWAYS SHOUTING.

Re:Who Knew! (1)

raehl (609729) | about 3 years ago | (#36915354)

It's ok. The program filters for exclamation points used after the opening word or after all-caps.

Women do use lol more though, to use up some of the 120 characters left over after anything intelligent they had to say.

Re:Who Knew! (1)

nschubach (922175) | about 3 years ago | (#36915236)

I'm totally going to hell for this but in order to re-enforce my manhood, I must say:

My zipper was down and my wife found my gf. My nigga wanted my beer and my shorts! I took my jeep and my woman to my vegas timeshare.

(Here! [fastcompany.com] )

Re:Who Knew! (2)

el3mentary (1349033) | about 3 years ago | (#36915442)

I'm totally going to hell for this but in order to re-enforce my manhood, I must say:

My zipper was down and my wife found my gf. My nigga wanted my beer and my shorts! I took my jeep and my woman to my vegas timeshare.

(Here! [fastcompany.com] )

You used an exclamation mark you are clearly a woman.

Re:Who Knew! (1)

Lemmy Caution (8378) | about 3 years ago | (#36915322)

I hate the word "hubby". It's the linguistic equivalent of shopping for groceries in slippers and a mumu.

just better than guessing (0)

Anonymous Coward | about 3 years ago | (#36914956)

but only just?

Oh! (0)

Anonymous Coward | about 3 years ago | (#36914960)

Those cunning linguists!

Or... (1)

Shillo (64681) | about 3 years ago | (#36914962)

Or it can be used as a training tool for would-be impersonators.

Re:Or... (1)

Nationless (2123580) | about 3 years ago | (#36915058)

omg, yayyy!

Wait until my hubby hears about this! hahaha

-Happy girl with chocolate hair, lol.

Re:Or... (1)

Shillo (64681) | about 3 years ago | (#36915100)

I see your point. It won't fool the people who use common sense but it -will- fool the people who use the same software. :)

Re:Or... (2)

John Hasler (414242) | about 3 years ago | (#36915108)

> Or it can be used as a training tool for would-be impersonators.

Or to test gender-altering scripts. OMG! :)

Linguists Need to Visit a Starbucks Occasionally (5, Funny)

RobotRunAmok (595286) | about 3 years ago | (#36914964)

The mere fact of a tweet containing an exclamation mark or a smiley face meant that odds were a woman was tweeting

or a Mac user.

Re:Linguists Need to Visit a Starbucks Occasionall (0)

Anonymous Coward | about 3 years ago | (#36915024)

Hahahahahaha

Re:Linguists Need to Visit a Starbucks Occasionall (0)

Anonymous Coward | about 3 years ago | (#36915036)

OK, so you're suggesting they should replace "man" with "likes girls" and "woman" with "likes boys"? I'd buy that...

Re:Linguists Need to Visit a Starbucks Occasionall (0)

Anonymous Coward | about 3 years ago | (#36915806)

omg lol! hair? Does that make me gay :'(

Trotting out this old joke. (1)

Anonymous Coward | about 3 years ago | (#36914966)

The internet: where men are men, women are men, and children are federal agents (also men.)

65.9% aint so hot (0)

Anonymous Coward | about 3 years ago | (#36914974)

Given that a drunken monkey with a dart gun could manage roughly 50% accuracy given only two choices, 65.9% doesn't exactly seem like a major advance...

65 percent (0)

Anonymous Coward | about 3 years ago | (#36914982)

65%?? that's very close to myself flipping a coin...

Re:65 percent (1)

Squiffy (242681) | about 3 years ago | (#36915226)

The test set represented 18000 users. The probability of flipping 18000 coins and getting 65.9% heads or more is 8.1e-405.

Who cares? (1)

Anonymous Coward | about 3 years ago | (#36914998)

Really. Who cares?

The Phrase to Type (1)

Murdoch5 (1563847) | about 3 years ago | (#36915000)

How do you fold a fitted sheet and why do you need more then 2 pairs of shoes.

Wow! (0)

Anonymous Coward | about 3 years ago | (#36915004)

But will it help me score?!?

Well that buggered the job up (0)

Anonymous Coward | about 3 years ago | (#36915020)

Now the fakers will all be using exclamation marks and smileys.

Wow, 65.9%. (0)

Anonymous Coward | about 3 years ago | (#36915028)

Uh, that's not very impressive.

Uh Oh (1)

BJ_Covert_Action (1499847) | about 3 years ago | (#36915040)

Apparently I have very feminine text messages/tweets, as I use excessive emoticons, exclamation points, and affectionate pet names (though those are directed towards females). And here I thought I had solidified my masculinity when I burnt all my pink shirts.

Then again, the nickname probably isn't helping either...

Re:Uh Oh (0)

Anonymous Coward | about 3 years ago | (#36915142)

funny ... there was no emoticons or exclamation marks in your post! :)

Re:Uh Oh (1)

BJ_Covert_Action (1499847) | about 3 years ago | (#36915352)

I try to keep it professional on slashdot. I have no idea why that is.

Re:Uh Oh (0)

Anonymous Coward | about 3 years ago | (#36915296)

Nah your just a faggot

The male keywords (0)

Anonymous Coward | about 3 years ago | (#36915042)

"http, google"

That's it. Those are the words guys use more? They link to stuff and Google? Really?

The Internet... (1)

slick7 (1703596) | about 3 years ago | (#36915064)

where men are women, women are women and kids are cops.

So what about people like me? (1)

killmenow (184444) | about 3 years ago | (#36915068)

I'm a guy. And I used to keep up a personal blog. Once upon a time there was a website that would analyze your blog for you and guess if you were male or female much like this twitter nonsense.

It guessed I was female. Dude! I'm not even gay! STOP SAYING THAT!!!

I mean...seriously! Jesus Christ!

Re:So what about people like me? (1)

ElectricTurtle (1171201) | about 3 years ago | (#36915156)

Too many exclamation points is your problem... uh... dude...

Re:So what about people like me? (1)

reason (39714) | about 3 years ago | (#36915764)

Yeah, it guessed I was male, so it got that wrong too. Looking at the details of the twitter algorithm, this, too, would probably mistake me for a man.

I find the girly squee stuff off-putting. Most of the women I follow on twitter are engineers and scientists, so I don't see that much of it. But when I was looking for a forum to get some support regarding pregnancy, I couldn't find anything remotely comfortable. I was looking for a bit of quiet reflection and rational advice, but all the forums were dominated by "OMG yay!" and enourmous sigs with animated gifs of butterflies and babies. It positively gave me the heebie-jeebies.

OMG! (1)

Anonymous Coward | about 3 years ago | (#36915120)

Ponies!!!

wow (0)

Anonymous Coward | about 3 years ago | (#36915144)

So dont get this guys! Gonna pretend you do it right..right ;)

Disclaimer: It took about over 15 minutes for me to write one line which didn't seem unequivocally to have been written by a guy, and when I finally thought I managed such a feat I found it so jarring that I was moved to append a disaclaimer explaining it. Must be girl thing.

V.S. Naipaul was right? (1)

l00sr (266426) | about 3 years ago | (#36915192)

Nobel laureate V. S. Naipaul recently caused an uproar when he claimed, among other things, that he could identify the gender of an author from their work [care2.com] :

In what must have been an attempt to be as offensive as possible, he continued, saying that men’s and women’s writing is “quite different I read a piece of writing and within a paragraph or two I know whether it is by a woman or not. I think [it is] unequal to me.”

I guess this means he was right? Although, for the record, he still seems like an arrogant, sexist SOB--just not for this particular reason.

Well... (1)

raehl (609729) | about 3 years ago | (#36915336)

I've spent a long time online. And I can pretty easily and reliably deduce gender from what someone "says". Women write differently. I wouldn't say they write worse, just differently.

IDENTITY CRISIS!! (0)

Anonymous Coward | about 3 years ago | (#36915246)

OMG, does this mean I'm really gay?!!! NLOL, WMS!!!

[NLOL, WMS = not laughing out loud, wetting my self]

It's a 140 character sex-change operation!

This is easy (1)

ue85 (1961968) | about 3 years ago | (#36915252)

WhEn YoU SeE pOsTs LiKe ThIs It iS aLwAyS a GiRl!!!!

man vs. machine (1)

king neckbeard (1801738) | about 3 years ago | (#36915262)

Do we have a benchmark for how well a human can detect genders? I understand being automagic has some special applications, but it seems like a useful point of comparison for its accuracy.

Re:man vs. machine (1)

snowgirl (978879) | about 3 years ago | (#36915404)

I would off-the-cuff suggest that it's unlikely that humans are good at it. We have a high-tendency to let previous biases or preconceptions of people get in the way.

So, for example, you see the picture of a tweeter as a female, and you impose that belief into his/her text.

Differently from / differently than (1)

gawaino (1191849) | about 3 years ago | (#36915270)

"The research is based on the idea that women use language differently than men." I have another idea - that old people use language differently *from* you.

What about Rule #30? (1)

Froeschle (943753) | about 3 years ago | (#36915302)

linguists have also developed a list of gender-skewed words used more often by women including love, ha-ha, cute, omg, yay, hahaha, happy, girl, hair, lol, hubby, and chocolate. Remarkably, even when only provided with one tweet,

Yay omg, you are cute! I want to be a happy girl! I have no hubby and want u to rub chocolate in my hair. Hahaha!

Oh this ought to be good (1)

BlueParrot (965239) | about 3 years ago | (#36915368)

I wonder what would happen if you fed my stuff to this algorithm. I'm transsexual and hang out in very different environments depending on which of my friends I psend time with. It can range from LANs to baking parties. On the overall I'd say I'm a poor fit for both male and female stereotypes. It would also be fun to see what it would do with my lesbian friends, many of which are immense tomboys.

Re:Oh this ought to be good (3, Funny)

93 Escort Wagon (326346) | about 3 years ago | (#36915556)

It would also be fun to see what it would do with my lesbian friends, many of which are immense tomboys.

I guess I don't quite see what their weight has to do with anything...

Recognizing gender 65.9% based on one tweet (3, Insightful)

wurp (51446) | about 3 years ago | (#36915388)

What was the gender distribution of the tweets this was tested against? If 65.9% of the tweets were from a male, the algorithm "return Gender.male;" will get the gender right 65.9% of the time...

Re:Recognizing gender 65.9% based on one tweet (1)

raynet (51803) | about 3 years ago | (#36915570)

Also how did they know that the users claiming to be women were actually women. How were the 18000 users selected? Perhaps the article does clarify these things but I'd rather sleep now than read it.

They've done studies... (1)

PunkFloyd (817784) | about 3 years ago | (#36915396)

They've done studies, you know. They say 65.9% of the time, it works every time.

Linguists don't "out" anyone. (1)

blair1q (305137) | about 3 years ago | (#36915408)

Linguists know that "out" is not a verb.

Re:Linguists don't "out" anyone. (1)

DoomHamster (1918204) | about 3 years ago | (#36915606)

Pedants know that "out" is not a verb.

FTFY. As for Linguists, it would depend on what school of thought they subscribe to.

Research? (1)

mrclevesque (1413593) | about 3 years ago | (#36915412)

The paper is done by MITRE Corporation, I gave up reading it, scanned most of it and the results and method seem convoluted and unclear. By the way, the company's motto is: "Applying systems engineering and advanced technology to critical national problems"

What's the unicode ... (1)

PPH (736903) | about 3 years ago | (#36915450)

... for the glyph of an 'I' dotted by a little heart?

Well duh. (0)

Anonymous Coward | about 3 years ago | (#36915476)

Bitches love smilies.

This will only lead... (1)

DollyTheSheep (576243) | about 3 years ago | (#36915600)

This will only lead to better impersonations skills

Gender Inequality (3, Insightful)

FrootLoops (1817694) | about 3 years ago | (#36915638)

From the paper, in their data set 47.7% of tweets were from females, 32.8% were from males, and the rest was unspecified. Tossing out the unspecified ones, guessing "female" all the time would then give ~59% accuracy. On the surface that makes the 65.9% figure in the summary very lackluster, though better figures are reported with more information elsewhere in the article.

The only reason for the deduction is... (0)

Anonymous Coward | about 3 years ago | (#36915750)

The only reason for the stipulated deduction that men and women speak differently is due to the enforcement of gender stereotypes. Given no outside influence, they wouldn't speak like this. A small percentage yes. Given the gender normatives, one could easily impersonate the other gender as the scripters have erroneously created it. The study is utter bollocks.

I used UK vernacular...I must be from the UK! ...I'm from Texas...I don't say Y'all and I don't have an accent. I also use the phrase No Worries. Why? Because it is the nicest way to say what you intend. The list can go on ex infinitum.

Cultural enforcement studies are abhorrent.

False Headline on Slashdot - News at 11 (1)

dreampod (1093343) | about 3 years ago | (#36915796)

This study in no way outs men impersonating women. In fact it specifically identifies gender for analysis by comparing it to the linked blog/website profile information and assuming that "the effort involved in maintaining this deception in two different places suggests that the blog labels on Twitter data are largely reliable". Basically it assumes that anyone attempting to impersonate the opposing gender is a tech ignorant moron that has made no effort to create a persona - something that is contrary to pretty much every piece of information we have on people who do this.

Overall, a poorly constructed study that oversells what it discovers and is then exagerated and stretched by the media who claim things that even the study isn't pretending that it does - in other words a typical day in research and scientific reporting.

Not impressed (0)

Anonymous Coward | about 3 years ago | (#36915862)

Call me when they are able to identify people who actually try to impersonate the other gender. Otherwise, this isn't very useful, as asking people is probably going to yield more accurate results.

Ad (Mis-)Targeting (1)

dougr650 (1115217) | about 3 years ago | (#36915868)

So now if I tweet that I "love" something, or god forbid, use a smiley face or an exclamation point, I'm going to get tampon and other feminine product ads? Super.
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...