Skip to main content

Film dialogue often reinforces stereotypes about race and gender, a machine learning study confirms

Film dialogue often reinforces stereotypes about race and gender, a machine learning study confirms


There’s a way to help fix the problem: put more women in writer’s rooms

Share this story


In news that should be no surprise to anyone who follows the film industry, a new study has found that men speak more than twice as much as women in film, and often, the dialogue that is given to women helps reinforce gender and racial stereotypes.

The new study comes from the Signal Analysis and Interpretation Lab at the University of Southern California’s Viterbi School of Engineering. Researchers examined more than 53,000 dialogue segments from 7,000 characters in 1,000 scripts, and used machine learning to study how characters spoke and interacted along racial, gender, and age lines. They also examined the makeup of the crews that produced the films, including the writers, directors, and casting agents.

The study had a couple of takeaways. First, male characters spoke far more than their female counterparts, with 37,000 dialogues vs. just 15,000, while women portrayed 2,000 characters, as opposed to 4,900 played by men. The team also found that of the thousand scripts they examined, male writers were seven times more likely to be involved in a project, male directors were 12 times more likely to direct a film, and men were three times more likely to produce a film than female producers. While the gender of casting directors is the exception to the pattern — women outnumbered their male counterparts in casting-director positions two to one — the report found that this had no impact on the gender of the characters they were casting.

Hollywood is currently contending with criticism of the discrepancies between men and women in the film industry, and recent studies have shown that this bias extends to the characters onscreen. Researchers found that between 2014 and 2016, women spoke 47 percent of the time in the top 100 grossing films. But this study didn’t look at the content of those lines. This new study does, and finds that women and minorities tended to use language that reinforced stereotypes.

According to The New York Times, the researchers found that dialogue from female characters “tended to be more positive, emotional and related to family values,” while the dialogue from their male counterparts was “closely linked to achievement,” and to death. At the same time, the study found that black characters swore more, Latino characters spoke more about sexuality, and older characters spoke more about religion.

Researchers also wanted to use machine learning to figure out how important characters are to the film, based on the relationships they have with their counterparts. Removing female characters from most films, they found, often didn’t alter the film’s plot significantly, except in horror films, which the researchers noted was because women tend to be “portrayed as victims.”

“Writers consciously or subconsciously agree to established norms about gender that are built into their word choices,” says the study’s author, Anil Ramakrishna, who also suggests there could be a relatively easy way to fix the inequality: The authors found that when women were part of a writer’s room, “female representation on screen was on average 50 percent higher.”

Today’s Storystream

Feed refreshed 36 minutes ago Striking out

Andrew Webster36 minutes ago
Look at this Thing.

At its Tudum event today, Netflix showed off a new clip from the Tim Burton series Wednesday, which focused on a very important character: the sentient hand known as Thing. The full series starts streaming on November 23rd.

The Verge
Andrew WebsterTwo hours ago
Get ready for some Netflix news.

At 1PM ET today Netflix is streaming its second annual Tudum event, where you can expect to hear news about and see trailers from its biggest franchises, including The Witcher and Bridgerton. I’ll be covering the event live alongside my colleague Charles Pulliam-Moore, and you can also watch along at the link below. There will be lots of expected names during the stream, but I have my fingers crossed for a new season of Hemlock Grove.

Andrew Webster1:05 PM UTC
Looking for something to do this weekend?

Why not hang out on the couch playing video games and watching TV. It’s a good time for it, with intriguing recent releases like Return to Monkey Island, Session: Skate Sim, and the Star Wars spinoff Andor. Or you could check out some of the new anime on Netflix, including Thermae Romae Novae (pictured below), which is my personal favorite time-traveling story about bathing.

A screenshot from the Netflix anime Thermae Romae Novae.
Thermae Romae Novae.
Image: Netflix

Welcome to the new Verge

Revolutionizing the media with blog posts

Nilay PatelSep 13
Tom WarrenSep 23
Has the Windows 11 2022 Update made your gaming PC stutter?

Nvidia GPU owners have been complaining of stuttering and poor frame rates with the latest Windows 11 update, but thankfully there’s a fix. Nvidia has identified an issue with its GeForce Experience overlay and the Windows 11 2022 Update (22H2). A fix is available in beta from Nvidia’s website.

External Link
If you’re using crash detection on the iPhone 14, invest in a really good phone mount.

Motorcycle owner Douglas Sonders has a cautionary tale in Jalopnik today about the iPhone 14’s new crash detection feature. He was riding his LiveWire One motorcycle down the West Side Highway at about 60 mph when he hit a bump, causing his iPhone 14 Pro Max to fly off its handlebar mount. Soon after, his girlfriend and parents received text messages that he had been in a horrible accident, causing several hours of panic. The phone even called the police, all because it fell off the handlebars. All thanks to crash detection.

Riding a motorcycle is very dangerous, and the last thing anyone needs is to think their loved one was in a horrible crash when they weren’t. This is obviously an edge case, but it makes me wonder what other sort of false positives we see as more phones adopt this technology.

External Link
Ford is running out of its own Blue Oval badges.

Running out of semiconductors is one thing, but running out of your own iconic nameplates is just downright brutal. The Wall Street Journal reports badge and nameplate shortages are impacting the automaker's popular F-series pickup lineup, delaying deliveries and causing general chaos.

Some executives are even proposing a 3D printing workaround, but they didn’t feel like the substitutes would clear the bar. All in all, it's been a dreadful summer of supply chain setbacks for Ford, leading the company to reorganize its org chart to bring some sort of relief.

Spain’s Transports Urbans de Sabadell has La Bussí.

Once again, the US has fallen behind in transportation — call it the Bussí gap. A hole in our infrastructure, if you will.

External Link
Jay PetersSep 23
Doing more with less (extravagant holiday parties).

Sundar Pichai addressed employees’ questions about Google’s spending changes at an all-hands this week, according to CNBC.

“Maybe you were planning on hiring six more people but maybe you are going to have to do with four and how are you going to make that happen?” Pichai sent a memo to workers in July about a hiring slowdown.

In the all-hands, Google’s head of finance also asked staff to try not to go “over the top” for holiday parties.

External Link
Insiders made the most money off of Helium’s “People’s Network.”

Remember Helium, which was touted by The New York Times in an article entitled “Maybe There’s a Use for Crypto After All?” Not only was the company misleading people about who used it — Salesforce and Lime weren’t using it, despite what Helium said on its site — Helium disproportionately enriched insiders, Forbes reports.

James VincentSep 23
Nvidia’s latest AI model generates endless 3D models.

Need to fill your video game, VR world, or project render with 3D chaff? Nvidia’s latest AI model could help. Trained on 2D images, it can churn out customizable 3D objects ready to import and tweak.

The model seems rudimentary (the renders aren’t amazing quality and seem limited in their variety), but generative AI models like this are only going to improve, speeding up work for all sorts of creative types.