Seminare from David Doukhan, researcher et Ina

 

Date: 12/12/2024
Time : 14h00
Place: IC2, Boardroom
Speaker: David Doukhan
 
 

Analysing and quantifying gendered representations in the audiovisual media: five years of interaction between research, political players and the general public

 

Summary:

The media have been described by the philosopher Michel Foucault as technologies of power that help to establish norms while claiming to reflect society. The under-representation of women and their stereotypical representation in the media contribute to their marginalisation. Media analysis is therefore seen as a tool for objectifying these representational biases and promoting social equality.

Numerical data is often perceived as an authority argument, essential for convincing people and triggering political action. Carrying out studies involves addressing a number of practical challenges in order to find the most acceptable trade-off between the number of samples and the finesse of the analyses to produce the most relevant knowledge with necessarily limited resources. Recent advances in automatic analysis mean that larger volumes of data can be examined, reducing the sampling bias associated with manual methods. This exhaustiveness, combined with a fascination for machine learning, contributes to the credibility and social impact of the descriptors obtained. A number of these automatic indicators are now included in reports designed to guide public policy: the report by MP Calvez on the place of women in the media in times of crisis, the annual report by ARCOM (formerly CSA) on the representation of women on television and radio.

This presentation will review the analysis methods developed as part of the ANR-funded Gender Equality Monitor project: automatic estimation of men’s and women’s speaking time [Dou18], visual exposure time [Dou24], analysis of text inserts [Dou20], counting of gendered first names [Dou24], analysis of themes raised by men and women [Peil24] and interruptions [Uro24]. In addition to the numerical findings, the presentation will focus on the relationships between the various automatic indicators and with the manual indicators of the GMMP [Bis24] and the ARCOM annual report [Dou24]. We will address the question of the technological and theoretical maturity of the various analysis methods proposed, a decisive factor in guiding the transfer of technology to public reports with a media and social impact. Finally, the presentation will look at the challenges involved in designing systems that can go beyond the binary definitions of the gender
[Dou23].

 
References:

• [Bis24] Biscarrat, L., Coulomb-Gully, M., Doukhan, D., & Méadel, C. (2024). Quantifier le genre dans les médias. Défis méthodologiques d’une enquête politique. Communication. Information médias théories pratiques, 41(1).
• [Dou18] Doukhan, D., Poels, G., Rezgui, Z., & Carrive, J. (2018). Describing gender equality in french audiovisual streams with a deep learning approach. VIEW Journal of European Television History and Culture, 7(14), 103-122.
• [Dou20] Doukhan, D., Coulomb-Gully, M., & Méadel, C. (2020). En période de coronavirus, la parole d’autorité dans l’info télé reste largement masculine. La revue des médias, (1)
• [Dou23] Doukhan, D., Devauchelle, S., Girard-Monneron, L., Chávez Ruz, M., Chaddouk, V., Wagner, I., Rilliard, A. (2023) Voice Passing : a Non-Binary Voice Gender Prediction System for evaluating Transgender voice transition. Proc. INTERSPEECH 2023, 5207-5211, doi: 10.21437/Interspeech.2023-1835
• [Dou24] Doukhan, D., Dodson, L., Conan, M., Pelloin, V., Clamouse, A., Lepape, M., Van Hille, G., Méadel, C., Coulomb-Gully, M. (2024) Gender Representation in TV and Radio: Automatic Information Extraction methods versus Manual Analyses. Proc. Interspeech 2024, 3060-3064
• [Pel24] Pelloin, V., Dodson, L., Chapuis, É., Hervé, N., Doukhan, D. (2024) Automatic Classification of News Subjects in Broadcast News: Application to a Gender Bias Representation Analysis. Proc. Interspeech 2024, 3055-3059
• [Uro24] Uro, R., Tahon, M., Doukhan, D., Laurent, A., Rilliard, A. (2024) Detecting the terminality of speech-turn boundary for spoken interactions in French TV and Radio content. Proc. Interspeech 2024