top of page

Geena Davis gender recognition software

Gender Representation between France and the US in Transnational TV Series Adaptations

The present research analyzes the inequality of gender representation in transnational TV series. For this purpose, a content analysis was carried out on 18 episodes of the US crime show Law & Order: Criminal Intent and its French adaptation Paris Enquêtes Criminelles. To conduct this research, we used the artificial intelligence toolkit the Möbius Trip, which is equipped with a gender and emotion recognition feature and relies on big data. The main findings indicate that male characters overwhelmingly dominate the onscreen time equally in both the US and the French versions. The data also show that male characters are more emotionally expressive and that women tend to display a wider range of emotions. The French characters are slightly more emotionally expressive than their American counterparts. The data also suggest that male characters tend to display violent behavior and that female characters tend to be portrayed as a victim in both versions of the show. The emotions-related results show a trend, but the difference of emotions between male and female characters and between the French and American cultures remain fairly narrow.

According to the above results, both Law & Order: Criminal Intent and Paris Enquêtes Criminelles tend to show a negative characterization of females based on underrepresentation. Male characters overwhelmingly dominate the show. We also proved that the lack of representation of female characters is fairly similar in both versions of the show. We demonstrated that emotion is contingent on gender and that female characters show a wider range of emotions, but that male characters are more emotionally expressive. We also demonstrated that the French characters are more emotionally expressive and show a wider range of emotions than their American counterparts. Lastly, we have shown that male characters tend to display violent behavior and that female characters tend to be portrayed as victims. The emotions-related results showed a trend, but the difference of emotions between male and female characters and between the French and American cultures were fairly narrow. We will continue investigating other French and American TV series in order to confirm the trend we have revealed in this study.

To conclude, the Möbius Trip can be a potent tool to raise awareness of women’s discrimination in transnational TV series adaptation. In the future, we hope the Möbius Trip will help TV series directors check and balance their subjective opinions to make a more accurate decision based on real and objective data. We encourage TV series directors and broadcasters to define quantified progress objectives to improve the presence of women on their channels for more gender representation equity. In this way, our study could contribute to more awareness, social justice, and better cinematographic decisions.

The Geena Davis Institute

Research on gender and race representation in media has been traditionally made by hand, or at least without a potent tool that could assist researchers in their endeavors. For the most part, the research is content- analysis based. They are very long and tedious and are prone to human error as well as lack of precision. Such a method has not proved to be productive because the limited amount of data extracted was insufficient to bring trends to light. The new advent of technology offers a new perspective in the ways we collect and analyze data and develop new methodologies.

To study gender representation and screen time in popular films, the Geena Davis Institute has turned towards artificial intelligence solutions. The institute has partnered with Dr. Shrikanth (Shri) Narayanan and his team of researchers at the University of Southern California, the University of Southern California's audio-visual processing technologies, to develop the CG-IQ (Geena Davis Inclusion Quotient). CG-IQ is an innovative software tool that incorporates Google's machine learning technology to collect and analyze audio-visual information automatically from media. Geena Davis states, "The GD-IQ is an extraordinary tool that gives us the power to uncover unconscious gender bias with a depth that had never been possible to date" (Geena Davis).

CG-IQ is an Automated Analysis Tool. Today, GD-IQ is the only known tool that can automatically measure the on-screen time and speaking time of characters in a movie. It has been able to reveal the representation imbalance that has been pervasive in the film industry. In doing so, the Geena Davis Institute aims to influence the film industry and to increase the number as well as the diversity of female characters. The ultimate goal is to create role models and inspire young girls and women in the world (Geena Davis)

The Geena Davis Institute focuses on the gender and racial representation of US society on screen. Their goal is to uncover unconscious biases on gender. As of today, Geena Davis Institute scholars have collected the largest body of research on gender prevalence in movies (family entertainment) over a span of 28 years. Based on quantitative data, the software offers unprecedented information regarding gender representation in Hollywood. The software is able to measure the time women appear on the screen, as well as the time they can be heard.

In order to make their case, researchers at the Geena Davis Institute conducted a study on recent movies. They analyzed 200 movies selected from the top-grossing Variety movies during the 2014 and 2015 period. Such a sample size is unprecedented in movie analysis. While this study conducted by hand would have been possible, it would have been quite demanding in terms of time and concentration of the researcher. With the GD-IQ and its unequaled potential, the software was able to extract data in a brief period of time. That is truly revolutionary. It can analyze movies efficiently in little time with extreme accuracy. The software runs on both face detection and tracking. That is, it is able to detect faces and identify gender (figure 21). It is also able to track each face individually. This is a crucial aspect when measuring the on-screen time of characters because when there is more than one character on screen, the tool kit assigns a gender to each character. After adding the total on-time screen duration for each character, the GD-IQ calculates the ratio between screen time of men and women on the total duration of the movie. The on-screen time of a character is arguably as important as the speaking time. Often in movies, characters are heard and not necessarily seen. It is important to take this element into account when measuring the overall presence of a character. Regarding the speaking time, the GD-IQ uses an automatic speech detection program that can identify the gender of the characters. The voice recognition software runs on automatic voice activity detection, audio segmentation, and gender classification.

The prowess here is twofold. First, the results achieved by the Geena Davis Institute are groundbreaking. The Geena Davis Institute was able to highlight the staggering unbalance of women's representation on screen. Such a compelling result was only possible because the Geena Davis Institute was able to establish trends based on data mining. The second important point in the research is the method itself, and Big Data is certainly a key concept that fuels the research. Because it seeks trends and patterns, big data accurately reveals the trends that have led the film industry throughout the years. After analyzing the 200 films released in 2015, the researchers are able to uncover clear trends that rely on objective data. They were able to point out the unconscious gender bias and demonstrate the staggering underrepresentation of women. Among the most relevant findings, Geena Davis reveals that men had twice the screen time as women in 2015 (28.5% compared to 16.0%). Geena Davis looks at the male lead as well as female lead movies. In male lead movies, the representation gap increases. Male characters appear 33.5% of the time, while female characters only 12.9%). In contrast, female lead movies portray almost as many men as women. There is 24.0% female compared to 22.6% male. Interestingly, in co-lead movies, male characters are significantly more represented than females as they get about 24.8% against only 16.0% for women.

These figures objectively reveal the underrepresentation of women in movies and clearly shed light on male domination in the film industry. This trend is corroborated by the calculated speaking time. The Geena Davis Institute found that 28.4% of men occupied speaking time compared to 15.4% for women. In male lead movies, men talk 33.1% of the time, while only 9.8% is dedicated to women. In women lead movies, men still talked for a considerable amount, almost equaling the women speaking time (23.9% compared to 26%). Lastly, in male/female co-lead, male characters spoke 25.5% compared with only 16.7 % for female characters (figure 22).

Just like the on-screen time, the male hegemony is being asserted at the speaking level. On-screen and speaking time both concur that men dominate the screen. Such results have several implications. Women represent half of the population of humanity. Yet, they are being underrepresented on screen. Geena Davis proves that the film industry perpetuates discrimination against women by suppressing their presence on screen and by literally not being heard.

The CG-IQ has unquestionably developed unprecedented ways to measure gender representation accurately in films. Because of this state-of-the-art software, the Geena Davis Institute was able to amass the largest body of research on gender prevalence on screen over the course of 28 years. The multiple studies highlight the stark imbalance of women's representation on screen. Despite the effectiveness of the automated software, the methodology, and the big data, there are still limitations to the Geena Davis Institute method and toolkit. As of today, the Geena Davis Institute has only relied on quantitative data; that is, they measured the screen time and the number of words. The Geena Davis Institute has not explored qualitative aspects of movies. For instance, though they measure who speaks and who is on screen, they don't measure the importance of each character's appearance or the importance of their words or action. Nor can the Geena Davis Institute provide information on the social status of each character. Though Geena Davis has been concerned with worldwide mass media, no research has been conducted on transnational TV series adaptation. As of today, no research on the cultural representation of gender in tv series adaptation between France and the US has been conducted.

bottom of page