Future Movie Rating with AI


Movie rating can decide a movie’s appeal to customers and the size of its potential viewers. It has an impact on a film’s bottom line.

Usually, humans do this long task manually based on viewing the movie and make a decision based on violence, drug abuse, and sexual content present in the Movies. Currently, researchers at the USC Viterbi School of Engineering, provide AI tools that can rate a movie content in a few seconds based on the movie script and before a single scene is finished. It will help the movie executives to design a movie rating in advance and as desired, by making appropriate edits on a script and before capturing a single scene. Beyond the financial impact, this can help storytellers and decision-makers review the content they are creating for the public and the impact such content might have on viewers.

Shrikanth Narayanan, University Professor and a team of researchers from the Signal Analysis and Interpretation Lab (SAIL) at USC Viterbi, applied Artificial Intelligence (AI) to scripts that demonstrate the linguistic can effectively signal behaviors on violent acts, sexual content, and drug abuse about to be taken by film character.

The SAIL research team trained Artificial Intelligence (AI) to recognize corresponding risk behaviors, patterns, and language of movies by using 992 movie script that contains violent, abuse and sexual contents, as decided by Common Sense Media. The created AI tool receive script as input then processes it by a neural network and scans it for semantics and sentiment expressed. During this activity, it organizes sentences and phrases as positive, negative, aggressive, and other descriptors. AI tools organize words and phrases automatically into three groups: violence, drug abuse, and sexual content.

Victor Martinez, a doctoral candidate in computer science at USC Viterbi and the lead researcher on the study, mentioned that model looks at the movie script, rather than the actual scenes such as sounds like a gunshot or explosion that occur later in the production pipeline. This helps the filmmakers to decide the degree of violence and whether it needs to be toned down.

Martinez stated that there seems to be a relationship between the amount of content in a film focused on substance abuse and the amount of sexual content. Whether intended or not, the filmmaker seems to match the level of substance abuse-related content with sexually explicit content. They also founded that filmmakers make up for low levels of violence with joint portrayals of substance abuse and sexual content.

While many movies contain a picture of unchecked drug-abuse and sexual content, the researchers found it highly unexpected for a film to have high levels of all three risky behaviors, perhaps because of MPA (Motion Picture Association) standards. They found a relation between risk behaviors and MPA ratings, as sexual content increases, the MPA appears to put less emphasis on violence/substance-abuse content. Therefore anyhow violent and substance abuse content, a movie with a lot of sexual content will likely receive an R rating.

As mentioned by Narayanan, at SAIL they are designing technologies and tools, based on AI, for all stakeholders in this creative business, writers, film-makers, and producers to raise awareness about the varied important details associated with telling their story on film.


Please enter your comment!
Please enter your name here