Gender Equality Monitor (GEM)

Date: 01/2020 - 06/2023
Funding: ANR
Call: AAPG2019
Partners: INA, LIMSI, Carism, Deezer, LERASS, ENS Lyon
URL: https://lium.univ-lemans.fr/en/gem/


Media and society have an intricate relationship. Descriptive, the media are also prescriptive and shape our perception of the world. The GEM project aims to describe the differences in representation and treatment between women and men in the media, based on the automatic analysis of large volumes of data in French contained in the INA and Deezer collections: TV, radio, print media and music collections.

The ambition of this project is to conduct the largest study ever carried out on the place of men and women in the media, based on the analysis of several million documents sampled over a period of more than 80 years. This study is made possible by the extensive collections of audiovisual documents held by INA and Deezer, as well as by recent advances in ICST: speech processing, artificial vision, automatic language processing. The completion of this study requires the definition of a set of indicators representing differences in treatment and representation, the implementation of a technological basis for automatically estimating these indicators and, finally, the questioning of the reception and contextualization of the analyses carried out using qualitative approaches.

This large-scale quantitative approach aims to create new knowledge in the human sciences, to assess the evolution of differences in the representation of women and men over time and between different types of materials, in order to objectify some of the citizen debates on gender equality in the media. This automatic description of men and women representation responds to societal as well as industrial challenges: estimating the impact of actions aimed at a more equitable representation of the sexes in the programmes broadcast, exploring and enhancing large digital collections, improving the performance of automatic systems and studying borderline cases. The extraction of indicators of gender difference in treatment requires the removal of technological and methodological obstacles, contributing to advances in the state of the art in ICST and SHS.