News for hackers. Stuff that matters.
Re:Show HN: List of movie and book characters I use during a... by spdustin on Friday January 22, 2016 @09:16AM (#10952784)
Would you humor a fellow HNer and tell me if you're in your early forties?

I happen to be working on a toy machine learning project that, based on the fictional characters known by someone, predicts their approximate age. Your list is the first organic validation set that happened onto my machine!

Re:Show HN: List of movie and book characters I use during a... by pgwhalen on Friday January 22, 2016 @09:26AM (#10952837)
This is the most HN thing ever, I love it. Can't wait to see this public.
Re:Show HN: List of movie and book characters I use during a... by NameNickHN on Friday January 22, 2016 @09:22AM (#10952810)
LOL yes.
Re:Show HN: List of movie and book characters I use during a... by spdustin on Friday January 22, 2016 @09:44AM (#10952943)
Excellent. The theory is that, for most people in the US (perhaps elsewhere?), one's reading / movie watching / tv watching tend to be clustered into specific time periods.

When Friends or Firefly were on, for example, I was watching a lot of TV (like you) because at that stage of my life I was settling into a long-term relationship (early twenties) and we found those to be mutually enjoyable things to watch. Movie watching tends to fall off around the time people start having kids. So far, on my friends-and-family (kids and grandparents alike) polls, it's pretty accurate.

Thanks again for answering :) I may just post my quick and dirty hack when I'm through playing with it.

Re:Show HN: List of movie and book characters I use during a... by MuEta on Friday January 22, 2016 @10:05AM (#10953058)
I'm fresh out of college, and I'm curious if this would stand up with people that are my age and close-ish to my demographic. From my experience, I think our cultural experience is the file-sharing or "Netflix" generation. My friends and I all have deep connections to characters from 80s, 90s, 00s and 10s entertainment, because we have been able to access it all. I am definitely going to reference Flash Gordon, Mal Reynolds and Patrick Star in a poll of fictitious characters.

I don't know, it's just something that I'm curious about. I would love to take your test (although I am already primed by seeing the OP's list).

Re:Show HN: List of movie and book characters I use during a... by mccolin on Friday January 22, 2016 @10:22AM (#10953176)
I think there's a chance your cohort will have more people like this (that have great fondness for "older" characters and media) due to Netflix/streaming, but on the overall I think you're a subset. For every person who appreciates classics, there are ten that binge watch current/trendy/popular stuff only.

It will be interesting to see how this plays out with all of the great access to media history we have today!

Re:Show HN: List of movie and book characters I use during a... by pjmorris on Friday January 22, 2016 @10:22AM (#10953178)
Fantastic. Want to try a smaller dataset? My stock names start with Alfred E. Neuman, George Tirebiter, and Ted Nugent.
Re:Show HN: List of movie and book characters I use during a... by spdustin on Friday January 22, 2016 @11:14AM (#10953540)
I had Alfred E. Neuman and Ted Nugent in the data, but I really need more music references.

It guessed early 70's.

It's written to guess early/mid/late subsets of ten-year ranges, and actually does have some data for kids/teens. Mostly it had fictional characters in movies, books and television but some singers snuck in there when I had my family fill out excel worksheets, heh!

Any advice on how I could collect this kind of data? A survey on ask HN? Mechanical Turk?

EDIT: the only features it uses are fictional names that one can rattle off in one sitting and the specific age to use for the label. No gender or other demographic information. So that's what I would collect, just a list of fictional names a submitter can think of in one sitting, and their age. It's basically a form of supervised topic classification training seen in other ML tutorials, but using the age as the training set topic label. I'm experimenting on enriching the data afterwards with media (book/movie/tv flags) see if that feature improves its performance, but I'm teaching a class this week and don't have any spare time to work on it.

Re:Show HN: List of movie and book characters I use during a... by spdustin on Friday January 22, 2016 @01:16PM (#10954504)
I see after going over your comment history that you're 52. Now I feel bad!

Looking at my data, only one person had Ted Nugent. My uncle, who is now 77. I have new respect for him. A handful of Alfred E. Neuman references are in there, wildly varying ages. It really underscores the value of a comprehensive training set to see how wildly off some predictions are when there aren't enough samples. Plus, just two vectors (as in your case) do not a classification make.

It does make me wonder about the validation though... I should try validating the model with varying numbers of input names to see if there's a baseline where it's able to reliably predict age. I think that's where media would come in handy...

Re:Show HN: List of movie and book characters I use during a... by pjmorris on Friday January 22, 2016 @04:26PM (#10955702)
My informal theory is that everyone's favorite music is what they were listening to when they were in high school. I'd guess that's a less well-specified version of your idea, but I think including musicians/bands would improve your results. The point someone else made about having access to all of prior history is valid though; my George Tirebiter reference came from listening to 'Don't Crush That Dwarf, Hand Me The Pliers' by The Firesign Theater, which is a decade or so older than I'd be expected to know if you just knew my age.
Re:Show HN: List of movie and book characters I use during a... by ayberk on Friday January 22, 2016 @06:01PM (#10956138)
I didn't know there was a fictional character named after him! That's neat!
Re:Show HN: List of movie and book characters I use during a... by marincounty on Friday January 22, 2016 @12:47PM (#10954318)
I was going to say 45-55, but George Tirebiter threw me. I now have no clue.
Re:Show HN: List of movie and book characters I use during a... by spdustin on Saturday January 23, 2016 @06:46PM (#10960691)
I've submitted a Show HN post asking for assistance in getting more data for this little exercise. I'll post a Jupyter Notebook describing the model and results, along with a live "guess my age" form, in a week or so.
Re:Show HN: List of movie and book characters I use during a... by marincounty on Friday January 22, 2016 @01:02PM (#10954423)
Speaking of datasets, and age, I have a question for younger people. I don't know if you like, or it's politically correct to refer to you as Millenials. I didn't like generation X, or baby boomer.

Here goes, and I'm not trying to make fun of anyone, and I don't belive it's true. Personally, I believe the millenial generation might be the most knowledgable in history.

That said, I've heard some of you don't know what a 45 record is, or how a rotary telephone works?

Some people claim to not to know certain dated things because it's fashionable. I once heard a young Rebublican claim to know nothing about the GOP past. The guy sitting next to her said, "I didn't live through the French Revolution, but I know what happened?" That ended the conversation.

So what the truth?

Re:Show HN: List of movie and book characters I use during a... by spdustin on Friday January 22, 2016 @01:09PM (#10954468)
Rotary phones reminds me of a "hack" I was most proud of as a teenager.

I was barred from calling my girlfriend at night in my room, and my phone was replaced with one that was broken. My parents wanted me to be able to answer the phone, but the keypad didn't work, so I couldn't dial out.

What I could do, however, was rapidly toggle the receiver hook. Turns out the pulse frequency tolerance had a pretty wide range, and I became quite skilled at quickly tapping out her number. That, and the Nintendo gamer hotline. Priorities!