Computers Learning How to Write Movies

(Noted News) — The next way that computers are preparing to replace humans is by learning how to write movie scripts. 

Researchers from the University of Granada and the University of Cádiz analyzed tens of thousands of different movie “tropes” and concepts found in thousands of different movies. They found that almost every popular movie in existence contains some common tropes in regards to plots, characters, music, scenes, and other storytelling gadgets. 

The tropes they noted included ones like Dramatic Unmask, Face Framed in Shadow, Bank Robbery, Bad Liar, No Honor Among Thieves, Evil Wears Black, Blunt Yes, and Hero’s Journey.

By analyzing classic tropes for every aspect of filmmaking, the researchers hope to feed the data into a machine learning camera that can watch films, recognize the tropes, and then create a repertoire of them for when they create their own movies. 

“There’s a whole ‘narrative artificial intelligence’ field that is burgeoning, and that has produced for the time being nothing more than quirky Twitter bots, but might very well progress to whole feature-length films in the future,” said co-author of the study, Juan Merelo. 

“Creating a story is a challenging task due to the complex relations between the parts that make it up…Which is why many new stories are built on those cohesive elements or patterns, called tropes that have been shown to work in the past.”

This is nascent, but not entirely new technology. Researchers at the Georgia Institute of Technology have already created, though rudimentary, video games using artificial intelligence. Motherboard reported in 2018 that the institution was working on the “Automated Game Design via Conceptual Expansion,” a study to create video games using the same methods that researchers today hope to make films with. 

“It’s the mimicry approach to creativity, which isn’t a bad place to start because humans also learn to be creative by mimicking at first,” Mark Riedl, one of the developers said.

“The other day it made this really cool game where every time you jumped on a platform you also destroyed that platform. You had to continually move right, you couldn’t pause ever. It was really cool.”

According to the Automated Game Design via Conceptual Expansion paper, machine learning technology of this kind can democratize the creation of digital art because of its ability to allow creators to bypass much of the intensive work of development.  

“The promise of automated game design could not only democratize game design, but allow for educational, scientific, and entertainment applications of games currently infeasible given the resource requirements of modern game development. However, up to this point, automated game design has relied upon encoding human design knowledge in terms of authoring parameterized game design spaces or entire games for a system to remix. This authoring work requires expert knowledge, and is time intensive to debug, which limits the applications of these automated game design approaches.” 

As of yet, there is no word on when we will get to see the next fully artificial intelligence-created film on the big screen, but hopes are high, especially for streaming services like Netflix who spend big bucks paying for film and television productions that unfortunately require humans.

Show More

Related Articles

Back to top button