Movie ratings to a large extent, determine how a movie can appeal to its consumers and the potential size of its audience. Usually, humans do the tiresome job of manually rating the movie based on factors such as violence, drug use, language etc.
Now, researchers at the USC Viterbi School of Engineering, with the aid of artificial intelligence tools can rate the content of a movie in mere seconds. They can do this based on just the movie script and before any scenes are even shot. This could give movie executives the power to predict a movie’s rating, by editing the movie script appropriately and prior to the shooting of scenes. Apart from the money it would save them, this speedy feedback would give the decision-makers and creators the chance to think properly about their content and its possible impact on its viewers.
Making use of artificial intelligence that is applied to scripts, University Professor Shrinkanth Narayanan, Niki & C. L. Max Nikias, Chair in Engineering and a team of researchers from the Signal Analysis and Interpretation Lab (SAIL) at USC Viterbi, have demonstrated that linguistic cues can efficiently predict behaviors on drug use, language, violent acts, sexual content (factors that usually determine a movie’s ratings) that is about to be taken by a character in a film.
The SAIL research team trained artificial intelligence to identify corresponding language, patterns and behaviours using about 992 movie scripts that contained drug use (abuse), sexual and violent content. These scripts were chosen by Common Sense Media, a non-profit organization that rates and recommends movies for families and schools.
The AI tool that was created collects the movie script as input, uses a neural network to process it and scans it for semantics and expression of sentiment. During this process, it categorizes phrases and sentences used as negative, positive, calm, aggressive and other descriptors. It then classifies the phrases and words into three groups: violence, drug abuse and sexual content.
Victor Martinez, a doctoral candidate in Computer Science at USC Viterbi said, “Our model looks at the movie script, rather than the actual scenes, including e.g. sounds like a gunshot or explosion that occurs 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.”
Some other personalities in the research team include Narayanan, a Professor of Electrical and Computer Engineering, Computer Science and Linguistics; Krishna Somandepalli, a Ph.D. candidate in Electrical and Computing Engineering at USC Viterbi; and Professor Yalda T. Uhls of the Department of Psychology in UCLA. They came across numerous fascinating links between the portrayals of risky behaviours.
Martinez said, “There seems to be a correlation in 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.”
Although a lot of movies possess portrayals of widespread drug abuse and sexual content, the research team found that it is very unlikely for a movie to have high levels of all the three risky behaviors, probably due to the standards of the Motion Picture Association (MPA).
Another thing they found was an eye-catching link between risk behaviours and MPA ratings. With the increase of sexual content, there is apparently less emphasis on violence/substance abuse content by the MPA. This means that despite the content of violence and substance abuse in a movie, a movie with substantial sexual content will probably get an R-rating.
Narayanan calls media, “a rich avenue for studying human communication, interaction and behaviour, since it provides a window into society. At SAIL, we are designing technologies and tools, based on AI, for all stakeholders in this creative business— the writers, filmmakers and producers— to raise awareness about the varied important details associated in telling their story on film.”
Not only are we interested in the perspective of the storytellers of the narratives they weave,” Narayanan said, “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.”
Martinez added, “In the future, I’m interested in studying minorities and how they are represented, particularly in cases of sex, violence and drugs.”
By Marvellous Iwendi.
Source: Science Daily