As part of my Machine Learning class at Penn, I got a chance to work on a gender identification project based on Twitter data. The goal of the project was to try to identify the gender of 5000 people on Twitter based on their profile pictures and a summary of all the tweets they had written. In order to stimulate creativity, the professor made the project a sort of competition between all the teams in our class with prizes (and more importantly, grade bumps) going to the best teams. While my team had no intentions of trying to win the competition from the outset, we actually ended up doing just that! Read on to find out how.
Viewing entries tagged