Rape Fantasies and Hygiene By State

June 25th, 2009 by Chris Coyne

For OkCupid‘s inaugural blog post, I’ve picked a few match questions and will be showing you some cool graphs. Graphs you’ll never find elsewhere.

But first, a reminder: OkCupid match questions are written by OkCupid users, not by staff. The community writes the questions, and our software simply asks them. Good questions climb to the top, and new users are asked to answer these first. By “good” I mean people (1) disagree over them and (2) feel strongly about them. God and sex are hot topics, as you’d expect. So are dating expectations, personal politics, and habits.

And a word about statistical validity: the best questions on OkCupid have been answered over a million times. Therefore we have unique insights into the American mindset. A quick comparison:

OkCupid Question Popularity

Old media could only get 3,050 people to answer a poll about Obama. And it was enough to call the election with confidence.

OkCupid, on the other hand, can ask the world’s most personal questions and get hundreds of thousands of answers. For example, here’s a provocative match question posed by a user:

OkCupid Sample Question

300,000 people have answered that question in 3 parts, and there are thousands more questions with as large or larger data sets.

Yesterday, I wrote a Python jam that consolidates the data by state and plots the trends using Google’s chart API. I plotted a handful of questions, and what follows are a few of the more exciting results.

OkCupid Rules

Would you consider role-playing out a RAPE FANTASY with partner who asked you to?


OkCupid Rape Fantasy

Scale

data set: 340,000 people answered


The few states skewing green said “Yes” more than the national average, and the reddish states said “No” more. Perfectly yellow states (like Virginia and Tennessee) answered “Yes” and “No” in the same proportion as the nation as a whole. It’s worth pointing out that because there are only a handful of greenish states and yet roughly a dozen reddish ones on the other side of the mean, those few green ones came down very strongly in favor of rape role-playing compared to the rest of the country. It’s also worth pointing out that cattle outnumber women 26:1 in Wyoming.

Here’s the same question, plotted on Europe:

OkCupid Rape Fantasy Europe

Scale

As you can see, the original England skewed the same as the brand New England. And there’s a strong interest in consent play in Lithuania. Sadly, countries in white have too little data for conclusions; maybe in a year we’ll be able to look deeper in those places.

Would you date someone just for the sex?


Just For the Sex

Scale

data set: 448,000 people answered


I guess I didn’t know what I was expecting from this question; maybe that the more “metropolitan” places would be greener and the more “rural” ones redder, and while that turned out somewhat true (for New York at least), the overall geographic continuity of this plot was a big surprise. I guess things are literally more wide-open in the West, and it looks like the depression is hitting more than just pocketbooks in the near Midwest. Is the Rust Belt now the Chastity Belt?

How often do you bathe or shower?


Bathe or Shower

Scale

data set: 261,000 people answered


This is a good example of results that seems surprising at first, but make sense after some thought: it stands to reason people in hot and/or humid states must shower more regularly. I’d be very interested to hear from any New Mexicans why their state bucks this logic; I suppose there are a lot of mountains there, so maybe it should have more in common with Colorado than with its other neighbors. Those of us up North skip once in a while, probably in the Winter. Vermont and Oregon are earthy as hell.

Should burning your nation’s flag be illegal?


Flag burning

Attempts to chart this question state-by-state yielded indifferent results, which makes sense since a person’s answer is fairly closely tied to his general political views and only a few states show extreme (far-off-the-norm) tendencies one way or the other on that. Digging deeper, I plotted this question by latitude and longitude. And now the results really show what’s going on: only people in cities believe flag burning should be legal. And even then, many conservative cities are opposed. Look at Texas: Austin, a liberal college town, is surrounded by Dallas, Houston, and San Antonio. It’s interesting that Florida, even though it went blue in the last election, is almost entirely red here.

OkCupid Rules

These are just a few of the thousands of questions we have in our database. Are there any other you’d like us to analyze? I’d be happy to; just drop me a line. Either way, I hope you enjoy these graphs and the discussion. I had a lot of fun programming them. We’re going to be posting similar back-end and data discussions on this blog every week, so see you next time. Also, just so you know: though we plan to discuss and manipulate user data on this blog, it will always be anonymized.

OkCupid Rules

OkCupid is totally free, so if you’ve stumbled on this blog entry, check out www.okcupid.com. If you’re an existing OkCupid user, invite your friends! Become a pixel in our graphs!

211 Responses to “Rape Fantasies and Hygiene By State”

  1. Nick says:

    This is all very interesting stuff (I like stats!), but…

    Therefore we have unique insights into the American mindset.

    Okcupid keeps forgetting that their own site isn’t just for Americans! This is frustrating.

  2. Tom says:

    Awesome article. Like sociology, but weird, pointless, and fun. Would it be possible to make the program part of the site, so anyone could pull whatever data they like?

  3. chris says:

    Hey Nick – expect some more, uh, worldly analysis soon. On average, 1 in 7 of our users logged in isn’t American. And we care about everyone. Sadly, I was getting much more interesting results with American data.

  4. chris says:

    Tom – generating graphs out of this data is time intensive. Each map took many seconds to render. Let’s say a million answers need to be looked up and joined with latitudes and longitudes from another table. It’s not something we can provide, currently, on demand.

    That said, we’re working on some cool graphs that let you see the world color-coded by how well you match people.

  5. ablondecouple says:

    I’d like to see some results cross referencing things like what people are looking for vs. their number of conversations, age breakdowns compared to message length, number of conversations vs. number of questions answered.

    Most delicately–and I’m no statistician so I’m not at all sure how to tease this out–but I’m very curious to see success results vs. demographics: something like age and sex vs. showing up first as looking for dating, then changing to seeing someone or married, then deleting their profiles.

    Freaky things like what age, religion, economic status and location are most likely to get blocked is also intriguing.

  6. joe says:

    this is all interesting data – i am curious to know, also, how this data breaks down by gender and race.

  7. Mike Rouse says:

    This sort of stuff fascinates me. Keep it rolling. Good work.

  8. chris says:

    Thanks, Mike. Hey – I just saw your blog post about our blog post. That’s cool, thanks.

  9. ry says:

    …this is awesome. I think further research is necessary to get a better outline on these things. The implications are HUGE. Not only could it make this dating site more effective, but it could also do many other things that are geographic/demographic related/dependent.

    That’s just my two cents.. When I see things like this I get excited. I want to do this kind of stuff for a living… ;-p

  10. Justin says:

    I love my state, Nevada. We will play out rape fantasies and date for the sex, but dammit, we bathe enough (maybe because of all the casual sex involving rape fantasies).

  11. no says:

    Looks cool

  12. misti says:

    I love this! it’s great that you’re finally using all this data for something interesting. I’d love to see state and country breakdowns of faith-based questions. Having lived on both coasts, I’m interested to know what other differences there might be. Any chance of getting a break down on punctuality questions?

  13. Kate says:

    This is simply fascinating. Thanks for making this information available, OKCupid!

  14. Scott says:

    Hey, great graphs, but I thought I’d share a little info with you about New Mexico, seeing as I spent four years in college there. It may occasionally get hot in New Mexico, but it’s a very dry heat. In fact, it’s a dry cold. New Mexico is pretty much always dry (at least Santa Fe and Albuquerque, probably the only places you have a lot of responses from, any way). Even the flash flooding in the summer months quickly dries up.

    Another factor that might be affecting those results which you seem to be too polite to mention is dirty, smelly hippies. Santa Fe is full of them. Albuquerque is pretty normal for a midsized city, which is probably why New Mexico isn’t entirely red.

  15. Joe says:

    That’s pretty fascinating, Chris, but what is the scale of the variations for each graph? Do 5% more people bathe every day in Florida than Minnesota or 50% ?

  16. me says:

    this is great! i’d love to see more posts about answers to random questions in the future.

  17. pauli133 says:

    neat stuff!

    one request, though: in future, could you use more colorblind friendly colors? red-orange-yellow-green is very hard to interpret, where red-orange-yellow wouldn’t be, for instance.

  18. Tom says:

    Yeah, OKC has been telling me I need to move to Seattle or Portland, based on the much better matches I seem to have in those places. I like the idea of match maps – think about it, you might start influencing – indirectly – where people live… not just who has children together – eeep!

  19. r-ant says:

    Awesome, I always assumed you had some really awesome information that could be used to make proper generalizations. What I want to know is when we (the okc public) will have access to this info. I’d love to be able to try out my own questions based on okc’s massive banks of info.

  20. Skippy says:

    I’m downright frustrated about the results of the flag-burning question. Also curious. Are the people who answer that they feel it should be illegal merely having a knee-jerk reaction to the question, thinking it’s one of respect? Or do they realize it’s a question about freedom of speech? Are they really so quick to marginalize their right to communicate?

  21. Lojikbom says:

    This is all very interesting stuff, but I hope you ran this past legal before you published it.

    I admittedly have not read your TOS, but publishing data without the consent of the person submitting the data to publish it is highly unethical.

  22. eric-the-read says:

    holy shit this is good.

  23. eric-the-read says:

    distro on responses to: u.s.a. was asking for it on 9/11 plz.
    It’s for science. political science.

  24. StellaStarrySky says:

    This is excellent. I live for this kind of quirky data. Keep it coming!

  25. Pingback: Do you like rape fantasies? | Mike Rouse

  26. RoguishPaladin says:

    I think it might be valuable to have a map showing the skew of people on this site versus real world averages for things like age, gender, and political affiliation. For example, the ratio of people over 65 using this site, as opposed to 18-65, should (hopefully!) be significantly lower – but just because they’re not looking for dates doesn’t mean that they don’t also have opinions. There may also be regional skews on the sorts of people who have found OKC, and this skew may in turn affect the responses you’ll get.

  27. radiosilence_ says:

    Could you possibly include the european stats for the other things, not just the US ones? Thanks!

  28. Grapey4U says:

    Fascinating data – would love to see age/gender/education breakdown on some of the questions. You have a unique opportunity here to breakdown data based on any number of factors. Looking forward to the next blog!

  29. sleeplongtime says:

    That was a great article. This site probably has a better grasp on the psyche of the dating public than anyone or anything anywhere else. I just hope that more people answer more questions to help get more data on any (possible) future maps. Thanks for the site and keep up the hard work. P.S. Any stats on marriages from people who have met on here?

  30. robin says:

    so interesting!

  31. james says:

    fascinating. i’d like to see the results plotted of one of the more mathy questions (e.g. “if the price of something is raised 25%, then dropped 50%…”).

  32. marimachita says:

    this is great. Thank you for taking the time to make these graphs, and explaining them a little. :)

  33. Jason D'Orazio says:

    1) Gallup uses a sample size of about 3000 because if you make it larger the chances of finding a significant finding plateaus.

    2) Gallup tries to randomize who they poll (although this has been less effective recently as they do not call mobile phones). For your data, you are using a convenience sample, which is more open to bias. From my extensive interaction with the site, OKC attracts younger, poorer, non-committal, more artsy sexual deviants. I think that would bias the results greatly.

    3) You make this big pomp and circumstance about how serious you are about statistics, and then you make asinine interpretations of the data. For instance, you imply that Lithuania like rape-play because of its history of being screwed over by Russia (figuratively and literally). Well, Poland got invaded a lot by neighbors, so why is it the opposite color? And insulting the Midwest and Vermont just because people do not like to have sex with anything that moves.

  34. Harvey_HiPoint says:

    YES! I freakin’ suggested this a couple weeks ago when you guys were asking for features we’d pay for. I’m SO stoked over here! Thanks. :)

    Of course, it would be nice to see the variances throughout the state. I guess it would all end up lookin’ kinda tie-dyed though. Or like vomit.

    I’d like to see a particular question answered! I would LOVE LOVE LOVE to know more about people’s orientation. How many people admit to having a lover of the same-sex? Would it really be more hetero in the south? That’s a freakin’ fascinating, controversial question right there, I suppose, huh. I have my theories though.

    Anyway, thanks, Chris! Dreaming big, it would be awesome to be able to run reports like this on our own, but I know that would be a MASSIVE undertaking. Maybe people could pay per question! LOL

  35. Harvey_HiPoint says:

    Correction: How many people would admit to having *had* a lover of the same sex at any point in time, regardless of their operational, public orientation?

  36. hoosierpap says:

    Very cool and the kinds of things I’m looking for. But old media still has one up on you. Your sample is highly selective and not representative of the countries or states but ofcourse of their cupid members who chose to answer.

  37. SplitBrain says:

    I would love to know how many people in each state are willing to consider an open relationship or relationships with multiple committed partners (and whether those two questions have different answers!). There aren’t many poly people out there, but OkCupid is frequently recommended as poly-friendly. I’d love to know where poly people log in … would it be another city/country breakdown?

  38. bbulkow says:

    Chris, I’d appreciate if you clarified how statistical significance works.

    The reason Gallup polls work with only 3,300 samples is their obsession with random sampling. Good pollsters crosscheck their randomization methods by asking questions they know the answer to (how old are you), to confirm their sampling methodology.

    Now, I know you very carefully *didn’t say* you have a good sample, you do say you know something about America. That’s misleading – you know about OK Cupid users, which are a self-selecting slice of America.

    But don’t let perfect be the enemy of the good – these are cool graphs, and thanks for making them! I just ask that you’re a little clearer about how statistics works.

  39. Gus says:

    Isn’t this data leaving out the bulk of the happily married population? I would think that single people have a slightly skewed perspective of the world vs. married people, furthermore I think that most of the world’s major decisions are made by married people. I know that OkCupid has married people on it… but let’s be honest, for most people, if you are happily married the last thing you are going to be doing is going to a dating site and answering questions. So what we are really seeing here are the opinions of of a large group of single people, who are liberal enough to use a website for dating, and a handful of very liberal married people. Just makes me wonder how useful this data really is.

  40. A patriot says:

    If our country is ever attacked it will be to large metropolitan areas. It’s good to know all the flag burners will be wiped out and the true patriots will take back our country. Flag burners: please use your freedom of expression by leaving our country. Why did I post anonymously? So I’m not persecuted for using my “freedom of speech”

  41. bob says:

    of course the gallup poll is from a random, representative sample of the US population (and adjusted for non-response, etc.). OKCupid most certainly is not. Your standard errors may be small but your bias may be quite large.

    Now in terms of showing what “typical” OKC members think, by state, well, have at it.

  42. Evan says:

    anonymize the data and publish it, I’m sure psychology departments round the country would go cuckoo for this stuff

  43. aspiciously13 says:

    i am a bit troubled by the validity of a number of aspects in this answering of match questions;; it was only after 1000 questions that i was finally happy with at least my approach

    one of my problems is this assumption that I deem certain questions in any quantifiable measure of importance

    but that is not what the tird questions asks: it asks how important their answer is to me, and that very often has very little to do with how important i find a question

    there are many stupid of other questions i deem irrelevant in itself; but would say THEIR answer would be extremely relevant

    next problem is answering the second question: how would my ‘ideal’ s.o. answer; well… you have no idea how that varies, depending on the topic at hand… i would love disagreeing over a great many things [on the one hand] – and answering so specifically rules out a lot interesting people…

    which forces you back to question no. three [yes you have certain biases BUT] none of the above rules out anyone: THEIR answer becomes ‘irrelevant’ at least in terms of being of ‘discriminite’ power, and that latter thingy…
    that is precisely the entire point of all this statistical magic

    or isn’t it?

  44. Echo3Delta says:

    While this is all very interesting (and fun) I’d like to point out a critique. Just because you have hundreds of thousands of respondents and Gallup only has 3000, this does not make your data any more accurate or reliable. This is due to the statistical principle of randomness, as well as the problem with open surveys in general (respondent bias – only people who are motivated to do so will respond to your questions). Gallup is a very well known for their statistical reliability, honesty, and methodology – to write them off as ‘old hat’ is disappionting to someone who hates the misuse of statistics in modern society.

    Statistics don’t lie, but the people who present them almost certainly do – and sometimes unintentionally!

  45. otakucode says:

    I’d really like it if you would make your data available rather than doing the analysis yourself… I’d love to be able to do some analysis on some of this data!

  46. Cavalary says:

    This is really nice (though of course I’d like to see more non-US data).

    A question I’d want to see the data for you say… Hmm… Well, tons of them, but the first one that came to mind was a non-controversial one actually: “Which best describes your main motivation for checking out this site?” :)

  47. r-ant says:

    @A patriot:

    Yes, the “true” patriots. The ones that know that a piece of cloth is worth more than a person’s freedom because we put some dye in it and say so… It’s just weird to hear a “true” patriot say that a piece of cloth is worth more than someone’s freedom. Not just of expression, but in general, or did you think making things illegal would have no repercussions? I wonder what kind of punishment you’d think was fair for burning a flag?

    Your kind of patriotism is ugly.

    Oh yeah, and I left an email address in the website slot so that you or anyone else can have an open dialog about this with me.

  48. r-ant says:

    But of course, after saying all that, it didn’t put the email address in the bar… anon.posthaste@gmail.com if anyone cares…

  49. 5Year-OKC-User says:

    Very interesting stats and very interesting comments! Especially compared to the net as a whole (can you say YouTube), the… let’s say, “average integrity” of comments in this blog are incredible :D

    And I love that you OKC guys (e.g. Chris) are responding to the posts, it really livens it up.

    I do agree with comments about the analyses of the data – please be careful in your application of statistics theory. Echo3Delta put it well, don’t unintentionally lie :)

  50. Nom De Plume says:

    This is super cool. The statistics and data analysis has been a big reason why i have stayed on okcupid. I dont suppose you guys are hiriing? I would love to get my hands on this data.