Detecting Gender Stereotypes In Film

A team of researchers from South Korea has developed a system that uses computer vision technology to automatically analyze images in films to identify gender bias.

AsianScientist (Dec. 23, 2019) – Production houses continue to portray womanhood in a stereotypical manner, say researchers at the Korea Advanced Institute of Science and Technology (KAIST), South Korea. Their findings are published in the journal Proceedings of the 22nd Association for Computing Machinery Conference on Computer-Supported Cooperative Work and Social Computing.

The ‘Bechdel Test’ has been the most representative and general method of evaluating gender bias in films. This test indicates the degree of gender bias in a film by measuring how active the presence of women is in a film. A film passes the Bechdel Test if it has at least two female characters who talk to each other and their conversation is not related to the male characters.

However, the Bechdel Test has fundamental limitations regarding the accuracy and practicality of the evaluation. Firstly, the Bechdel Test requires considerable human resources, as it is performed subjectively by a person. More importantly, the Bechdel Test analyzes only a single aspect of the film—the dialogues between characters in the script—and provides only a dichotomous result of passing the test.

To overcome these limitations, a KAIST research team led by Professor Lee Byungjoo proposed a system that uses computer vision technology to automatically analyze the visual information of each frame of films. This allows the system to more accurately and practically evaluate how female and male characters are depicted in films.

The researchers analyzed 40 films from Hollywood and South Korea released between 2017 and 2018. They downsampled the films from 24 to 3 frames per second before applying facial recognition and object detection technology to verify the details of the characters and their surrounding objects in the scenes.

The team computed eight quantitative indices that describe the representation of a particular gender in the films studied: emotional diversity, spatial staticity, spatial occupancy, temporal occupancy, mean age, intellectual image, emphasis on appearance, and type and frequency of surrounding objects.

According to the emotional diversity index, the films tended to depict women as more prone to expressing passive emotions such as sadness, fear and surprise. In contrast, male characters in the same films were more likely to demonstrate active emotions, such as anger and hatred.

The type and frequency of surrounding objects index revealed that female characters and automobiles were tracked together only 55.7 percent as much as that of male characters, while they were more likely to appear with furniture and in a household.

In terms of temporal occupancy and mean age, female characters appeared less frequently in films than males and were on average younger in 79.1 percent of the cases. These two indices were especially conspicuous in Korean films.

“Our research confirmed that many commercial films depict women from a stereotypical perspective. I hope this result promotes public awareness of the importance of taking prudence when filmmakers create characters in films,” said Lee.

The article can be found at: Jang et al. (2019) Quantification of Gender Representation Bias in Commercial Films based on Image Analysis.


Source: Korea Advanced Institute of Science and Technology. Photo: Pixabay.
Disclaimer: This article does not necessarily reflect the views of AsianScientist or its staff.

Asian Scientist Magazine is an award-winning science and technology magazine that highlights R&D news stories from Asia to a global audience. The magazine is published by Singapore-headquartered Wildtype Media Group.

Related Stories from Asian Scientist