Computational appraisal of gender representativeness in popular movies

Abstract Gender representation in mass media has long been mainly studied by qualitatively analyzing content. This article illustrates how automated computational methods may be used this context to scale up such empirical observations and increase their resolution significance. We specifically apply a face gender detection algorithm on broad set of popular movies spanning more than three decades carry out large-scale appraisal the on-screen presence women men. Beyond confirmation strong under-representation women, we exhibit clear temporal trend towards fairer representativeness. further contrast our findings with respect movie genre, budget, various audience-related features as gross user ratings. lastly propose fine description significant asymmetries mise-en-scène mise-en-cadre characters relation spatial composition given frame.