AI tool could predict future ratings of films

Researchers have developed an AI tool that can rate a film’s content in a matter of seconds, based on the film script and before a single scene has been shot.

 Ratings can determine a film’s appeal to consumers and the size of its potential audience. Thus, they have an impact on a film’s bottom line. Typically, humans do the tedious task of manually rating a movie based on viewing the movie and making decisions on the presence of violence, drug abuse, and sexual content.

To overcome this, a team at the USC Viterbi School of Engineering in Los Angeles created an approach that could give film executives the ability to design a film rating in advance and as desired, by making the appropriate edits on a script and before the shooting of a single scene.

Beyond the potential financial impact, such instantaneous feedback would allow storytellers and decision-makers to reflect on the content they are creating for the public and the impact such content might have on viewers.

By using AI applied to scripts, a team from the Signal Analysis and Interpretation Lab (SAIL) at USC Viterbi have demonstrated that linguistic cues can effectively signal behaviours on violent acts, drug abuse, and sexual content about to be taken by a character in the script.

“Our model looks at the movie script, rather than the actual scenes, including, for example, sounds like a gunshot or explosion that occur later in the production pipeline,” said Victor Martinez of USC Viterbi. “This has the benefit of providing a rating long before production to help filmmakers decide the degree of violence, for example, and whether it needs to be toned down.”

Using 992 film scripts that included violent, substance abuse, and sexual content, as determined by Common Sense Media (a non-profit organisation that rates films and makes recommendations for families and schools) the SAIL research team trained a neural network to recognise corresponding risk behaviors, patterns, and language.

The tool receives as input the script, processes it through a neural network, and scans it for semantics and sentiment expressed. In the process, it classifies sentences and phrases as positive, negative, aggressive, and other descriptors. The AI tool automatically classifies words and phrases into three categories: violence, drug abuse, and sexual content, the team said.

Narayanan, a professor of computer science and linguistics whose SAIL lab has pioneered the field of media informatics and applied natural language processing in order to bring awareness in the creative community about the nuances of storytelling, calls media “a rich avenue for studying human communication, interaction and behaviour, since it provides a window into society.”

Narayanan added: “At SAIL, we are designing technologies and tools, based on AI, for all stakeholders in this creative business – the writers, film-makers, and producers – to raise awareness about the varied important details associated in telling their story on film.”