Artificial intelligence (AI) is making a room for itself in every industry, and motion-picture entertainment is not an exception. Wherever is a tedious process, AI can be trusted to make it better and more efficient.
Movie ratings, which are typically done by humans manually by viewing the movie and making decisions on the presence of violent acts, drug abuse, and sexual content, is one such task that can now be revolutionized thanks to researchers at the USC Viterbi School of Engineering.
The new AI tool explained
This is especially important since movie ratings are a pretty big deal. Typically located at the end of movie trailers, they offer the needed cues to the viewer to grasp the content of the movie in a short time. When these ratings are given, they might be affected by each individual's biases, which won't be a problem thanks to this new AI tool.
Shrikanth Narayanan, University Professor and Niki & C. L. Max Nikias Chair in Engineering, and a team of researchers from the Signal Analysis and Interpretation Lab (SAIL) at USC Viterbi, demonstrated that linguistic cues can efficiently indicate violent behavior, drug abuse, and sexual content about to be taken by a film's characters.
The AI tool processes the script through a neural network and scans it for semantics and sentiment expressed. By classifying the sentences as positive, negative, aggressive, and other descriptors, it churns out a rating at the end.
Victor Martinez, the lead researcher on the study, said, "Our model looks at the movie script, rather than the actual scenes, including e.g. sounds like a gunshot or explosion that occur later in the production pipeline. This has the benefit of providing a rating long before production to help filmmakers decide e.g. the degree of violence and whether it needs to be toned down."
There were some thought-provoking patterns
Researchers also encountered interesting patterns in their study. One was that there seemed to be a correlation between the amount of content in a typical film focused on substance abuse and the amount of sexual content. "Whether intentionally or not, filmmakers seem to match the level of substance abuse-related content with sexually explicit content," said Martinez.
They also found that filmmakers seem to have compensated for low levels of violence with joint portrayals of drug abuse and sexual content.
Another interesting point was that when there was more sexual content, Motion Picture Association (MPA) appeared to "put less emphasis on violence/substance-abuse content," thus, indicating that regardless of violence or substance abuse content, a movie with a lot of sexual content "will likely receive an R rating."
Narayanan added, "Not only are we interested in the perspective of the storytellers of the narratives they weave, but also in understanding the impact on the audience and the 'take-away' from the whole experience. Tools like these will help raise societally-meaningful awareness, for example, through identifying negative stereotypes."