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.
6 Bumps On The Sidewalk, A Story of Accessibility
In a recent Webinar from EMI Research Solutions, I got to thinking about things in my world that aren’t readily known by most people. Brian Lamar’s blister curb example made me think, there’s WAY more to unpack and so the research began!
I scoured the web for information and found the bulk of that from Paving Experts, a company located across the pond. I hope this helps you think a bit differently as you navigate the world!
Firstly, tactile refers to the sense of touch, and therefore tactile paving is paving that conveys information to users via that sense of touch. This is most commonly achieved by having a distinctive raised profile that can be detected by users, such as ‘ribs’ running across the paving, or ‘spots’ that create a bumpy surface.
Interestingly, one person asked whether the ‘Rumble Strips’, used at the edge of major highways to alert vehicles they are straying onto the hard shoulder, could be considered to be Tactile Paving. These “bumpy white lines” certainly meet the above definition of tactiles, but, probably because they are not modular, and not laid as traditional paving, they are generally considered to lie outside the remit for tactile paving.
Types
As the implementation of tactile paving has progressed, new forms have been made available. When they were first introduced, back in the 1980s, the only readily available form was the 450x450mm pre-cast concrete flag, but they are now available as clays pavers and natural stone, as well as in bespoke formats, such as the units with steel or brass 'blisters'. Further, many of the concrete flag forms, are now manufactured as 400x400mm units (F50s and F65s) rather than 450mm (E50 and E65) units. The units are generally laid in the same manner as standard pre-cast concrete flags or block pavers, although many are now being laid on a full concrete bed to ensure accidental trafficking by cars, vans and lorries doesn't result in expensive breakages.
The key element with tactile paving is that different surface profiles are intended to denote different hazards, and these are outlined below.
Tactile Types
Blister paving: the most common type features 6mm high 'blisters' in a square pattern and these are used to indicate pedestrian crossings with dropped curbs. Normally, the red-colored units are used with light-controlled crossings, and buff for those crossings with no traffic lights. However, when natural stone units are used, this color-coding is disregarded.
The Offset Blister units are used to indicate the edge of the platform at train stations, also referred to as off-street applications. Note that the orientation of the offset blister units is critical - the rows of blisters MUST be parallel to the platform edge, and they are generally placed approximately 500mm back from the edge.
Hazard Warning units use continuous half-rods, raised 6mm higher than the surface of the paving, to denote a hazard, such as the top/bottom of a flight of steps. Again, the rods should be parallel to the edge of the hazard.
Cycleway paving uses continuous flat bars to indicate a cycle lane. The bars run parallel to the direction of travel so as not to impede cycles. Where a cycleway and a footpath are adjacent, these pavings may also be used for the pedestrian section, with the bars running transversely, and a demarcation strip between the two.
Directional or Guidance paving is used to indicate the safest direction of travel for the visually impaired. The raised flat bars have rounded ends.
Lozenge paving is used as a platform edge warning for on-street applications. As towns and cities rediscover the advantages of trams and Light Rail Transport (LRT), this type of paving will become more common.
Blister Paving
Tactile paving can be found in more and more places on the streets around the world, in a seemingly bewildering array of layouts. We're not sure all the applications we've seen are strictly in accordance with the official guidance, but what follows is a general guide to possible uses, and is factually correct, to the best of our knowledge. For controlled crossings, the blister paving should span the full width of the crossing, from the dropper curb on the right-hand side, to the dropper on the left-hand side (or as near as dammit without needing to cut the units). This strip of blister paving is normally 800-1000mm wide.
Where the footpath is wider than the 800-1000mm wide blister strip parallel to the roadway, two or three courses of the paving are extended to the back edge of the footpath so that the location of the crossing can be detected by all users.
For the concrete flag versions of the blister paving, the red, buff and 'Natural' grey are the three usual colors.
At the discretion of the local highways department, the guidance that recommends red units for light-controlled crossings and buff or grey for other crossing can sometimes be over-ruled when there would be an aesthetic clash of materials or colors.
With stone tactile paving, the blisters are normally milled to a circular shape to match those found with the concrete and clay equivalents, but such work can be expensive and so a number of suppliers offer a slightly cheaper 'square milled' profile, which meets the requirement of having the blisters at a specified separation, but the shape is different.
It is usually at the discretion of the local highways authority as to whether this profile is acceptable. Not all of them will be in favor.
The relatively high cost of having bespoke blister paving manufactured in a stone to match or complement other stone paving in the vicinity has resulted in some local authorities using metal 'studs' that are affixed to standard paving units. Some studs rely on drilling and gluing into position, while others use a high strength adhesive or epoxy resin to fix them into position.
The most commonly encountered metal studs tend to be stainless steel in the usual chromed steel color or a bronzed effect. They are typically retro-fitted, once the paving is installed, and therefore almost any stone paving can now be used for crossing points as the stones ability to be milled to a blister profile is irrelevant.
A growing use for metal studs is as a deterrent against skateboards, micro-scoooters, heelies and other forms of wheel-based youthful exuberance.
Occasionally, studs will be set into low benches and planter walls, but by placing the studs into the pavement immediately adjacent to these tempting obstacles, the various bits of street hardscaping can be effectively protected with minimal impact on un-wheeled citizens.
The clay blister pavers offer great versatility. The most popular size measures 200x133x65mm with 6 blisters, although at least one manufacturer produces an 8-blister 200x100mm unit. There is a good range of complimentary units, such as half-blocks and they can all be laid in a range of patterns. Where there are abrupt or significant changes in surface levels, they offer all the flexibility of block pavers in being able to roll and fold, whereas the large concrete and stone units often need to be mitre cut , which isn't the prettiest of treatments.These 'stick-on' tiles have been used in some of our towns and cities where retro-fitting of concrete, clay or stone tactile units to a crossing point is deemed impractical for whatever reason. Originally, they were often used as 'temporary' tactiles, on crossings where the local Highways Department hoped to effect a more permanent tactile pavement at some point in the future, but their performance has surpassed expectations and they are now commonly fitted as permanent fixtures.
The correct name for these units is "Surface Mounted Tactile Paving", reflecting the fact that they are fixed (or "mounted") over an existing surface.
They are epoxy glued into place over the top of the existing paving, making installation simple, quick and cost effective, as it eliminates excavation and the footpath can be re-opened in as little as two hours.
Most of us wouldn't think to combine two different formats of a tactile, but it may have benefits
Offset Blister
Although there are clay paver units available for this type of tactile paving, they are rarely used, as the regular, standardized layout of rail station platforms makes the use of the 400x400mm or 450x450mm pre-cast concrete units much simpler.
The flags are normally laid 500mm or so back from the platform edge, and, as mentioned above, the rows of blisters should be parallel to the rail track.
Hazard Warning
This type of tactile paving is also known as Corduroy paving, and features a rounded or rod-like surface protrusion which distinguishes it from the flat, bar-like protrusions of the directional guidance paving. It is intended to be used as a hazard warning, most notably for flights of steps.
They are readily available in pre-cast concrete, in a range of colors as clay pavers, and in natural stone by special order.
Cycleway Paving
Flat bars run longitudinally with the direction of travel. These units tend to be used in those projects where there is no curb or other strong demarcation between a footpath and the cycleway. In many towns and cities where cycle lanes are delineated by means of a curb or similar, the bicycle-only lanes are now being identified by using a red or green surface dressing to give a strong visual indicator.
Note that the tactile paving is aligned longitudinally.
Directional or Guidance Paving
This tactile paving is intended to act as a guide across large paved spaces, with the bars lying parallel to the direction of travel. Where a turn is encountered, the alignment of the paving should reflect the change of direction.
Lozenge Paving
Used for trains and, increasingly, bus stops in non-station applications, ie, on the open street.
With the expansion of train networks along with on-going redevelopment of bus stops to make them more disabled-friendly, this type of paving is becoming more common.
4,948 Americans Who Identify As Female’s Thoughts On Roe v. Wade
Link to the full study: Roe v. Wade
How Far Is Too Far? Disability Language. Our Thoughts.
by Jason Hahr
"Language....has as much to do with the philosophical and political conditioning of society as geography or climate...people do not realize the extent to which their attitudes have been conditioned since early childhood by the power of words to enable or condemn, augment, or detract, glorify or demean. Negative Language inflicts most people's subconscious from the time they first learn to speak. Prejudice is not merely imparted or superimposed. It is metabolized in the bloodstream of society. What is needed is not so much a change in Language as an awareness of the power of words to condition attitudes." (Saturday Review 1967)
When one thinks about the above quote, it takes a minute to sink in, but when it finally does, we are reminded that we, as humans, are complex creatures. The one thing that sets us apart from all other life on earth is Language. From early infancy, we are conditioned by our physical surroundings and the Language we take in. For example, a child in India will learn several dialects of the Indian subcontinent. Still, US English will be foreign to them, whereas someone who grew up in America will quickly pick up on the idiom of "chilling." It is amazing the power we give Language. It can be positive or neutral; however, it's most dangerous when it is given the ability to affect someone or a group of people negatively. Notice how I said that it is only harmful when we allow it to be; this essay will argue that it is not Language that has the power of negativity; instead, all of the power remains with the person. I mean that something I may find offensive may or may not be offensive to another person. At the end of this blog, I hope you will understand why I believe that just because we sanitize Language does not mean that we can sanitize ignorance.
The idea for this blog post came about as a result of a conversation with one of my new caregivers. She recently asked me what the acceptable term is for someone with a disability? It got me thinking, what exactly does the term "disability" even mean? Words only have context if we give them context. I use the word "gimp" to refer to myself quite often. It has no negative context because I am using it humorously. However, other individuals who are in my situation distinctly hate the word. Why is this? The answer is simple. I was not conditioned to have any negative connotation of "gimp." The first time I encountered the word was in a movie entitled King Gimp. The film is about an art student named Dan, who was extraordinarily disabled but used his disability to increase his quality of life significantly. I recommend that everyone, whether disabled or not, check out this excellent documentary at some point in their lives. It will give you a different perspective on disability and life in general.
However, back to my point. Since I had a positive experience the first time I heard the word gimp, there's no negative connotation behind it. Language is a unique tool that humans possess. We can establish our meaning and context for a variety of words. Something insulting in one Language may be a term of endearment in another. The same can be said for terms relating to disability. One of the most common terms to describe disability is "true disability. This term is used in disability circles to refer to a person who has been disabled from birth. I argue that, if we use this term, aren't we in all actuality segregating ourselves even more?
I have never been one to be politically correct. Like I said above, I make fun of myself all the time, but I understand the need in an appropriate professional setting to be non-condescending. Therefore, I make this argument. The term "disability" should no longer be used. One might ask, what do I suggest? What should be used to replace it? When I was going to get my Master's in education, a term that was often used was exceptionality. I think this is a neutral term—neither positive nor negative, which allows the person with the exceptionality to determine the word's context. The person sitting next to me, helping me write this, is exceptional in some areas of her life, just as I am exceptional in certain areas. While not changing one's condition, Neutral Language may be better than society immediately labeling a person. Because as much as I would like to hope that society's labels don't impact people, I would not be honest if I said this was the case. On the deepest level, the Language we hear daily affects us.
How Far Is Too Far? Disability Language
To further illustrate my point, let us look at the phenomenon known as the "Special Olympics." Earlier, I said that words are only as powerful as we allow them to be; however, do the same rules apply when it comes to these games? The overall concept of the games is a good one. I am not here to dispute the benefits of these Special Olympics; that is for another post later. I bring them up here for one reason. As I have argued throughout this piece, words are just words until people put a negative spin on them. It is the opinion of this writer and not anyone else that by calling the athletic efforts by people with developmental disabilities "special," an entire segment of the population is being infantilized. If you don’t believe me, look at the Paralympic games held in the same city as the summer or winter Olympic Games. These games focus on athletes who are disabled but not developmentally disabled. At no point in time are these athletes seen as "special" just because of who they are. However, as a former special Olympian, I can say that the whole focus of the special Olympics is different. The language they use to describe the entire event makes organizers feel like they have done something great. Don't get me wrong; I am not saying that the concept is flawed; instead, the organizers need to be reminded that even though these athletes are different from you, they are just as human as you. They are not special bundles of joy just because they got out of bed that day.
As a final thought, it is essential to remember that just because we sanitize language, it doesn't change one's ability, or in this case, one's disability. Sanitizing language does not get rid of prejudice. Indeed, it gives those who are prejudiced more firepower. My opinion is just that, an opinion. If you disagree with something I said in this essay, I welcome an open and honest discussion. I believe that it is through dialogue and exposure that we will change hearts and minds.