After Consecutive Years Of Progress, The Percentage Of Top-Grossing Films With Female Protagonists “Dropped Dramatically”
An article by David Robb featured in Dateline.
The percentage of top-grossing films that featured female protagonists “dropped dramatically” in 2020, down from 40% in 2019 to just 29% in 2020 – a decline of more than 10%, according to the latest study from Dr. Martha Lauzen, executive director of the Center for the Study of Women in Television and Film at San Diego State University. The report found that after two years of gains, 2020’s percentage of female protagonists was the same as in 2016 – the year before the start of the #MeToo movement.
Films led by women grossed 15.8% more on average than films led by men. Found in a study by Geena Davis Institute on Gender in Media and University of Southern California.
And the numbers don’t get any better with age: 2020, males 40 and over accounted for 52% of all male characters in the 100 top domestic-grossing films, while females 40 and over comprised 32% of all female characters. The report also found that major female characters experience “a precipitous drop” from their 30s to their 40s – falling from 31% of the roles to just 13%.
“We see a handful of mature female actresses and assume that ageism has declined in Hollywood,” Lauzen said. “But unless your last name happens to be Streep or McDormand, chances are you’re not working much in film.”
The report, titled “It’s a Man’s (Celluloid) World,” found that only 17% of the top-grossing films had more female than male characters; that 78% featured more male than female characters, and that 5% had an equal number.
“As protagonists in films, females took a step back in 2020, after two consecutive years of growth,” Lauzen said. “This decline is reflected in the low number of female-driven films nominated for a Best Picture Oscar. Only two films on this year’s slate of nominees, Nomadland and Promising Young Woman, feature female protagonists.”
The percentage of Black female roles also dropped: down from 20% of all characters in 2019, to 17% 2020 year – a 15% decline. Only 13% of those roles in 2020 were “major characters,” which the report defines as those who appear in more than one scene and are instrumental to the narrative of the story. Protagonists are those from whose perspective the story is told.
Even so, the percentages of females as major characters and in speaking roles increased slightly in 2020. The percentage of major female characters rose from 37% in 2019 to 38% in 2020. The percentage of female characters in speaking roles climbed from 34% in 2019 to 36% in 2020.
The percentage of Latina characters was up from 5% in 2019 to 6% in 2020 – a 20% increase, while the percentage of female Asian characters was down: from 7% in 2019 to 6% in 2020 – a 14% drop. Of the major female roles in 2020, 6% were Latina and 6% were Asian; 74% were white, and 1% were from “some other race or ethnicity.”
The report found that films with at least one woman director and/or writer are much more likely to employ female actors. In those films, females comprised 60% of protagonists, while in films with exclusively male directors and/or writers, females accounted for just 17% of protagonists.
The report also made clear that the number of roles for men and women is not the only gender disparity in the movies: that stereotypically portrayed lifestyles still persist, especially as depicted in the workplace. According to the report:
A larger proportion of male than female characters had an identifiable job or occupation: 73% vs. 57%.
A higher percentage of male characters were seen in their work setting, actually working: 59% vs. 42%.
Male characters were seen more often in primarily work-related roles: 59% vs. 41%.
Female characters were more often seen in primarily personal life-related roles: 54% vs. 36%.
Male characters were more likely to have primarily work-related goals: 41% vs. 32%.
Female characters were nearly to have primarily personal life-related goals: 19% vs. 10%.
Female characters also much more likely than their male counterparts to have a known marital status: 47% vs. 35%.
Methodologies
Algorithms are a set of rules of calculations that are used in problem-solving.
For this report, we employed two automated algorithms that measure screen and speaking time of characters by their gender.
Here is an overview of the procedures we used for each algorithm.
Screen Time Analysis
We compute the screen time of female characters by calculating the ratio of female faces to the total number of faces in the film’s visuals. The screen time is calculated using online face detection and tracking with tools provided by Google’s machine learning technology. In the interest of precision and time, we estimate screen time by computing statistics over face-tracks (boxes tracking the general outline of each face) instead of individual faces. The face-tracks returned by technology include different attributes of the face with the corresponding time of occurrence in the video. Among the attributes returned for each of the detected faces, we use two parameters – the confidence of the detected face and the system’s posterior probability for gender prediction. A threshold of 0.25 was empirically chosen for determining confident face detection. An overview of the on-screen time estimation process is shown in Figure 1.
Due to multiple characters appearing on screen simultaneously, the face-tracks can be overlapping, as illustrated in Figure 1. A gender label is then assigned to each track using the average gender posterior associated with the confident faces in the track. If the average gender posterior probability of the Identify confident faces per track Average gender posterior per track >0.5 ? Track 1 Track 2 ... Track N Male Track No Yes Female Track track is greater than 0.5, the track is classified as a “female track,” otherwise, it is a “male track.” The number of frames with confident face detections in each track is summed up across all tracks to get the total number of faces. The number of female tracks is aggregated to get the total number of faces predicted as female. Finally, the screen time is computed as the ratio between the number of female face detections to the total number of face detections across the length of the movie. Supplementary analysis shows that screen time estimated at frame-level (individual faces) instead of using face-tracks was not significantly different and was comparable. Furthermore, computing the average of gender posterior over tracks has an added benefit of “smoothing out” some of the local gender prediction errors. Face tracking incorporates temporal contiguity information to reduce transient errors in gender prediction that may occur with analyzing individual faces independently.
Speaking Time Analysis
Using movie audio, we compute the speaking time of male and female characters to obtain an objective indicator of gender representation. The algorithm for performing this analysis involves automatic voice activity detection, audio segmentation, and gender classification.
Voice Activity Detection:
Movie audio typically contains many non-speech regions, including sound effects, background music, and silence. The first step is to eliminate non-speech regions from the audio using voice activity detection (VAD) and retain only speech segments. We used a recurrent neural network based VAD algorithm implemented in the open-source toolkit OpenSMILE to isolate speech segments.
Segmentation: We then break speech segments into smaller sections in order to ensure each segment includes speech from only one speaker. This is performed using an algorithm based on Bayes Information Criterion (BIC), available in the KALDI toolkit. Thirteen dimensional Mel Frequency Cepstral Coefficient (MFCC) features are used for the automatic speaker segmentation. This step essentially decomposes continuous speech segments obtained in the VAD step into smaller segments to make sure no segment contains speech from two different speakers.
Gender Classification: The speech segment is then classified into two categories based on whether it was likely spoken by a male or a female character. This is accomplished with acoustic feature extraction and feature normalization.
Acoustic Feature Extraction: We use 13-dimensional MFCC features for gender classification because they can be reliably extracted from movie audio, unlike pitch or other high-level features where extraction is made unreliable by the diverse and noisy nature of movie audio.
Feature Normalization: Feature normalization is deemed necessary to address the issue of variability of speech across different movies and speakers, and to reduce the effect of noise present in the audio channel. Cepstral Mean Normalization (CMN) is a standard technique popular in Automatic Speech Recognition (ASR) and other speech technology applications. Using this method, the cepstral coefficients are linearly transformed to have the same segmental statistics (zero mean). Classification of the speaker as either male or female is based on gender-specific Gaussian mixture models (GMMs) of the acoustic features. These models are trained on a gender-annotated subset of general speech databases used for developing speech technologies using frame-level features for each gender. The GMM we use in this system has 100 mixture components and is optimized by tuning the parameters in a held-out evaluation set. For a new input segment whose gender label is to be predicted, the likelihoods of the segment belonging to a male or female class are computed based on this pre-trained model. The class with higher likelihood is assigned to the segment as the estimated gender prediction. The total speaking time by gender is then computed by adding together the durations for each utterance classified as Male/Female. This gives us the male and female speaking time in a movie.
