As I thought

Submitted by Ray on Thu, 07/31/2008 - 12:46

Followed a link today from my twitter feed to a new fun app that examines your browser history. It takes the sites that you view and correlates them against listings of male and female oriented sites and then tries to guess your sex.

The processing as you can imagine is quite complicated, rather than try to explain it myself, I will paraphrase the author;

So what I did is I modified the SocialHistory JS so that it polled the browser to find out which of the Quantcast top 10k sites were visited. I then apply the ratio of male to female users for each site and with some basic math determine a guestimate of your gender. The math is really quite simple, I just take:
1 / (1 + r_1 * r_2 * … * r_n)

where p_i is the ratio of men-to-women for the specific site. For example, if you had been to two sites that had a 2-1 ratio of men to women, the probability of you being female would be:
1 / (1 + 2 * 2) = 1/5 = 20%

The results for me I am glad to say were favourable..

Likelihood of you being FEMALE is 1%
Likelihood of you being MALE is 99%
Site Male-Female Ratio
google.com
0.98
youtube.com
1
craigslist.org
1.13
facebook.com
0.83
flickr.com
1.15
apple.com
0.89
dell.com
1.04
digg.com
1.56
hp.com
1.11
linkedin.com
0.94
perezhilton.com
0.75
ning.com
1.15
lifehacker.com
1.63
hotmail.com
0.83
sourceforge.net
1.74
thepiratebay.org
2.13
boingboing.net
1.5
slashdot.org
1.74
alleyinsider.com
1.94
valleywag.com
1.7
pcpitstop.com
1.11
google.co.uk
1.35
tatuagemdaboa.com.br
1.27
hypem.com
1.27

This is a testament to the power of JavaScript, certainly a language that is thought more of now than it was 5 years ago when people were scared to allow any scripts to run on their page.