Comment by languagehacker | Hacker News Reader

Comment by languagehacker | Hacker News Reader

Yeah, not only are they probably using two-year-old data, but if the confidence given is 97% for it being the wrong gender for me, I doubt that it's actually an effective tool.

There are all kinds of fuzzy behavioral ways to analyze gender. I remember when the Gender Genie (http://bookblog.net/gender/genie.php) made a similar splash. The issue is that it ignores the finer-grained sociological contexts in how certain people behave.

I can't find their name, but there is an African tribe where, as a courtship ritual, men dress up and wear makeup to attract women. To other people, this would sound like gender roles are reversed, but in reality, it's just their cultural definition of gender roles at play.

Mainstream culture subsumes a variety of subcultures and idioms, meaning that using statistical methods to determine the characteristics of specific behaviors within a coarse-grained social group may overgeneralize. For a more nuanced approach, it would be a good idea to use ensembles, or add subculture membership as a feature to a linear regression classifier.

if the confidence given is 97% for it being the wrong gender for me, I doubt that it's actually an effective tool.

Not necessarily. Of all those it predicts with a 97% confidence interval, you'd expect it to be wrong 3% of the time. Without any information other than that it was wrong about you, there's not much evidence about how accurate it is.

I can't find their name, but there is an African tribe where, as a courtship ritual, men dress up and wear makeup to attract women. To other people, this would sound like gender roles are reversed, but in reality, it's just their cultural definition of gender roles at play.

Men dress up to attract women in just about every culture. The fact that they also wear makeup shouldn't be surprising.

I can't find their name, but there is an African tribe where, as a courtship ritual, men dress up and wear makeup to attract women. To other people, this would sound like gender roles are reversed, but in reality, it's just their cultural definition of gender roles at play.

My, what a lot of big words. Of course, what we're looking at is somewhat culturally dependent; it just so happens that in our culture there's a heavily male-biased interest in, frinstance, looking at car websites (these seem to be the most male-dominated sites on the list it gives me). What's really interesting, though, is to what extent these patterns persist across different cultures... are men always more interested in transport than women are?

Men (in American culture and similar ones) aren't interested in cars because they are transport. They are interested in cars because they make noise and go fast.

Apparently scientific writing is astoundingly gender-neutral, Gender Genie reports the following for my last paper:

    Female Score: 3450
    Male Score: 3259

Reply on news.ycombinator.com