What Men Say, What Women Hear: Finding Gender-Specific Meaning Shades

Abstract

The authors examine the problem of gender discrimination and attempt to move beyond the typical surface-level text classification approach by identifying differences between genders in the ways they use the same words. They present several experiments using data from a large collection of blogs authored by men and women, and they report results for a new task of "gender-based word disambiguation" for a set of over 350 words.