gender.hankstoever.com

Data

name gender classification api

SHOW HN2014

18points
45comments
#1,320of 2,272 in 2014
Top 59%of 2014 by points

How HN took it

MixedNo clear lean

4 positive, 16 neutral or asking, 0 mixed, 18 critical, out of 38 comments about the project. Thread score -0.33.

Performance: 0 for, 14 againstIdea: 2 for, 3 againstPrivacy: 0 for, 1 againstDocs: 1 for, 0 againstDesign: 1 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Fun to play with and test names

    From 3 comments
    • I started searching for the most gender ambiguous names I could think of like "Jesse", "Alex", "Erin", etc. The best one I've found so far is "Angel" at 51.1% male.
      joshfraser on HN
    • This is pretty fun lol. I searched for Santa and it said 99% female haha.
      cclogg on HN
    • This is great fun, could you embed share options? I could trigger a share-war amongst my friends!
      mastersk3 on HN
  • Useful for choosing gender-neutral names and deduplication

    From 2 comments
    • One use I've come across for inferring genders was tackling record depupliction across multiple data sources. In one data set we might have the gender information of an…
      joaomsa on HN
    • I spend a lot of time choosing gender neutral names for story based scenarios in proposals (the joys of corporate work). http://en.wikipedia.org/wiki/Unisex_name has been…
      nl on HN

Objections

  • Results are inaccurate for many names

    From 5 comments
    • "Permelia"[1] is definitely a girl's name[2]. [1]: http://blog.xkcd.com/2014/01/31/the-baby-name-wizard/ [2]: http://gender.hankstoever.com/classify/Permelia
      sdegutis on HN
    • My name has a 50.444139% chance of being female. In the present case, the API is, unfortunately, incorrect.
      robinjfisher on HN
    • Definitely some odd results: Michael = 52%, Thomas = 62% (although Tom = 98%)
      ddeck on HN
    • I get ~70% for a name I've never even heard of being used for a female.
      blueskin_ on HN
    • Apparently Karan is female :(
      karanbhangui on HN
  • Gender is not binary and should not be inferred from names

    From 2 comments
    • The only reliable way to find out someone's gender is to ask them what gender they currently think they are. There are more than two genders and an individual's gender can change…
      sambeau on HN
    • While it's a quite interesting coding task to write a classifier, for the overwhelming majority of applications you simply don't need to know a user's gender. Making it a public…
      onion2k on HN
  • Works only for English names and is not culturally neutral

    From 4 comments
    • Without a location parameter this is pretty useless. Andrea for example is a male name in Spain and Italy as far as I know. Also this:…
      splitbrain on HN
    • I'm Italian, my name is Gabriele and it classifies it as female. That's wrong. In Italy, Gabriele is a male name. I agree that this is useless without location information.
      terabytest on HN
    • My name has 99.99...% chance of being male. But when I change it to the English/Anglophone version, the chance is only 60.641%.
      Dewie on HN
    • Neat. Should probably call out that it's an API for "gender classification of english names". Did you build this mostly for learning/personal purposes?
      levlandau on HN
  • Probabilities are not reliable without location data

    From 2 comments
    • Without a location parameter this is pretty useless. Andrea for example is a male name in Spain and Italy as far as I know. Also this:…
      splitbrain on HN
    • Fun, although you might want to state it applies to the US only
      ozh on HN

Requests

  • Add location parameter or country scope

    From 2 comments
    • Without a location parameter this is pretty useless. Andrea for example is a male name in Spain and Italy as far as I know. Also this:…
      splitbrain on HN
    • Fun, although you might want to state it applies to the US only
      ozh on HN
  • State that it applies to the US only or English names

    From 2 comments
    • Fun, although you might want to state it applies to the US only
      ozh on HN
    • Neat. Should probably call out that it's an API for "gender classification of english names". Did you build this mostly for learning/personal purposes?
      levlandau on HN
  • Add share options

    From 1 comment
    • This is great fun, could you embed share options? I could trigger a share-war amongst my friends!
      mastersk3 on HN

Questions

  • What is the training set?

    From 1 comment
  • Was it built for learning or personal purposes?

    From 1 comment
    • Neat. Should probably call out that it's an API for "gender classification of english names". Did you build this mostly for learning/personal purposes?
      levlandau on HN

Alternatives named

  • Microsoft Windows gndr app using US Census data

    From 2 comments
    • Bah I much rather use this app as it's much faster: http://apps.microsoft.com/windows/app/gndr/a062944e-744e-4955-b685-f3197faa2560
      abe238 on HN
    • I'm not even sure of that. I have seen much better results from US Census data with very different %'s of prob e.g.…
      abe238 on HN
  • Unisex names list on Wikipedia

    From 2 comments
    • There is an entire Wikipedia page on Unisex names [1]. Most Punjabi Sikh first names are applicable to both genders. [1]: http://en.wikipedia.org/wiki/Unisex_name
      arocks on HN
    • I spend a lot of time choosing gender neutral names for story based scenarios in proposals (the joys of corporate work). http://en.wikipedia.org/wiki/Unisex_name has been…
      nl on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/7175869)