As I mentioned here, I’ve often wanted a way to know whether an email from a Chinese stranger (like 张安平) is from a man or woman. There’s a cool new (to me) tool at Chinese-Tools that can help.

Presenting the Chinese Name Gender Guesser!

It immediately guessed that 张安平 was a boy and 李娟 was a girl. So I gave it (one name at a time) an entire class roster of 20 of my English students here at the college.

Result: 19/20 gender guessed correctly!

To protect the innocent, I’m not going to give you the name of the girl it thought was a boy. But still, I thought that was pretty good.

Just remember that whatever the first character is will be treated as the family name. So if you only know the given name of the person you’re trying to identify, just make up a family name for him/her (like 张).

I just HAD to know how it worked so I emailed Chinese-Tools. They told me it’s based on this database by Wudi.

Here’s an excerpt from the email I got back from Chinese-Tools:

There’s a database with a lot of Chinese characters, and for each of them a gender level indicator. For example 丽 is 100% female, 军 100% male, but some like 丹 can be both, maybe 65% female. Then an average of both characters of the name is calculated.

Very cool. Yet another example of how creative, open-source, free databases are making everyone’s lives better. Thanks Wudi!