Hacker News new | comments | show | ask | jobs | submit login
[flagged] Gender Roles with Text Mining and N-grams (juliasilge.com)
50 points by denzil_correa 186 days ago | hide | past | web | 4 comments | favorite

I kind of expected this to say something about "married" being flipped between Jane Austen and George Elliot rather than just glossing over it and saying the results for both authors are substantially similar.

Also I wonder about the approach here. Austen's protagonists are generally female, right? So of course we're privy to more of their internal thoughts than the men.

I agree with your comment about Austen's female protagonists. The article's author appears to have assumed that because Austen writes in the third person, equal weight can be given to she/he bi-grams. But, a writer can still internalize when using the third person and that could explain the differences much more than the gender of the subject.

Always impressed with the expressiveness and flexibility of the tidytext framework for analysing text. Well done Julia!

Julia and David Robinson's book Tidy Text Mining with R[1] has plenty more great text mining examples like this one.

[1] http://tidytextmining.com/

It would be fun to compare results with male writers, just to investigate the discrepancies in how genders may perceive the other.

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | DMCA | Apply to YC | Contact