SP-23: Advertising Gender - Using Computer Vision to Trace Gender Displays in Historical Advertisements, 1920-1990


This study applies computer vision techniques to examine the representation of gender in historical advertisements. Using information on the relative size, position, and gaze of men and women in images, we chart gender displays in Dutch newspaper adverts between 1920 and 1990. In this short paper, we operationalize aspects of Erving Goffman’s theories on gender displays in two ways. First, Goffman argues that ‘differences in size will correlate with differences in social weight.’ Using facial recognition software, we select adverts that include people and then run gender detection software to estimate whether men or woman were represented in the images This allows us to visually represent the changing faces of men and women in adverts. Part of the process also entails a reflection on the possible bias in these algorithms.

DH2019, Tivoli Vredenburg, Utrecht, the Netherlands
Melvin Wevers

Mevin Wevers has a background in psychology, American Studies, and Cultural Analysis. My research interests include the study of cultural-historical phenomena using computational means with a specific interest in the formation and evolution of ideas and concepts in public discourse.