A new AI tool can assess the level of violence in movies, which may help producers, screenwriters and studios in determining the potential classification of their projects in the future.
The new tool, developed by the Signal Analysis and Interpretation Lab (SAIL) at the University of South California, is considered the first-of-its-kind to use natural language processing to identify violent language and content in movie scripts.
According to the Techxplore website, the new AI tool was developed using a dataset of 732 popular film scripts that had been annotated for violent content. From this information, the team built a neural network machine learning model that can assess the content based on the available data, the German news agency reported.
The AI tool analyzes language in the dialogue of screenplays and detects similarities between the new script and the works in the database, in terms of word choice and psychological implications expressed by the movie's expressions.
Professor Shrikanth Narayanan, who partook in the development of the new tool, said: "Typically when people were studying violent scenes in media, they look for gun shots, screeching cars or crashes, someone fighting and so on.”
“But language is more subtle. These kinds of algorithms can look at and keep track of context, not only what specific words and word choices mean.”
