As featured in the July 18th Nature:
A new computer program can tell whether a book was written by a man or a woman. The simple scan of key words and syntax is around 80% accurate on both fiction and non-fiction1,2.
The program's success seems to confirm the stereotypical perception of differences in male and female language use. Crudely put, men talk more about objects, and women more about relationships.
Female writers use more pronouns (I, you, she, their, myself), say the program's developers, Moshe Koppel of Bar-Ilan University in Ramat Gan, Israel, and colleagues. Males prefer words that identify or determine nouns (a, the, that) and words that quantify them (one, two, more).
Crude, but effective. And interesting , especially amongst writers. Of course, I was confident that this blog ... would be a masculine blog ... and the computer agrees.
This kind of technology may well lead to offspring -- are there rules to distinguish female painters from males? How about filmmakers ? Can you look at a CEO's record of decisions and draw conclusions about about gender?
The point is the same, as always: trends and tendencies are kind of interesting, but not terribly instructive or predictive. There will always be exceptions -- women who write in bold, declarative statements and men who paint in the style of Cassat. Also, the jury is out on categorizing homosexual prose, as well as female writers who claimed to be men (George Elliot), or those sometimes misunderstood as such (Mr. Hassle).
Aside from its utility in lit crit term papers, and possibly espionage, the usefulness of the Gender Genie seems limited. It seems obvious, but writers should be judged by the content of their prose, not the idiosyncrasies of their syntax.