Computer Vision and machine learning methods were previously used to reveal screen presence of genders in TV and movies. In this work, using head pose, gender detection, and skin color estimation techniques, we demonstrate that the gender disparity in TV in a South Asian country such as Bangladesh exhibits unique characteristics and is sometimes counter-intuitive to popular perception. We demonstrate a noticeable discrepancy in female screen presence in Bangladeshi TV advertisements and political talk shows. Further, contrary to popular hypotheses, we demonstrate that lighter-toned skin colors are less prevalent than darker complexions, and additionally, quantifiable body language markers do not provide conclusive insights about gender dynamics. Overall, these gender portrayal parameters reveal the different layers of onscreen gender politics and can help direct incentives to address existing disparities in a nuanced and targeted manner.
@article{arxiv.1711.09728,
title = {Evaluating gender portrayal in Bangladeshi TV},
author = {Md. Naimul Hoque and Rawshan E Fatima and Manash Kumar Mandal and Nazmus Saquib},
journal= {arXiv preprint arXiv:1711.09728},
year = {2017}
}
Comments
Presented at NIPS 2017 Workshop on Machine Learning for the Developing World. Corresponding author: Nazmus Saquib