So, this is just me brainstorming, but I am pretty sure I have a solid idea for what I want to do for my final project:

This semester, I am in a linguistics course (other than this one), Langauge and Gender, and this idea for research came from this class. I have been rather intrigued by the idea that men and women use language differently and have specific features of language, and this is something I would like to examine on my own in this particular research, and in other research I plan on doing in the future.   I want to investigate the use of language (via twitter) to determine if language in use is sexist or not.  Specifically, I want to look at people that I know on twitter, so that I can have background information on these people–social class, age, gender, etc. These aspects of a person go hand and hand with their language and gender.  I will employ the use of a classifier to look at the sexism of language. If the classifier can accurately put the tweets in the correct gender category (male or female), then I can see if features of women’s language and men’s language do exist.  So far, for this research, I have found a few scholarly articles (some older, some newer) that suggest features of men’s and women’s language.  From these articles, I will extract the information provided on said features and teach the classifier the features.  Professor Zacharski and I are currently working on a program (using Python) that gathers tweets from a selected group of twitter accounts at a specific time during the day.  Zacharski has provided the code, and I am working on getting the cron job up and running, but have been having internet issues until today.  But hopefully our program will be up and running by the end of today.

WOO!