Gender is playing an important role in the 2016 U.S. presidential election,especially with Hillary Clinton becoming the first female presidential nomineeand Donald Trump being frequently accused of sexism. In this paper, weintroduce computer vision to the study of gender politics and present animage-driven method that can measure the effects of gender in an accurate andtimely manner. We first collect all the profile images of the candidates'Twitter followers. Then we train a convolutional neural network using imagesthat contain gender labels. Lastly, we classify all the follower and unfollowerimages. Through two case studies, one on the `woman card' controversy and oneon Sanders followers, we demonstrate how gender is informing the 2016presidential election. Our framework of analysis can be readily generalized toother case studies and elections.
展开▼
