Slashdot Mirror
20th Century Fox Is Using AI To Analyze Movie Trailers, Find Out What Films Audiences Will Like (theverge.com)
20th Century Fox is using AI to predict what films people will want to see. According to a recently published paper, researchers from the company are using machine learning to examine trailer footage and compare the objects and events it identifies with data generated for other trailers. "The idea is that movies with similar sets of labels will attract similar sets of people," The Verge reports. From the report: As the researchers explain in the paper, this is exactly the sort of data movie studios love. (They already produce lots of similar data using traditional methods like interviews and questionnaires.) "Understanding detailed audience composition is important for movie studios that invest in stories of uncertain commercial," they write. In other words, if they know who watches what, they will know what movies to make.
To create their "experimental movie attendance prediction and recommendation system" (named Merlin), 20th Century Fox partnered with Google to use the company's servers and open-source AI framework TensorFlow. In an accompanying blog post, the search giant explains Merlin's analysis of Logan. First, Merlin scans the trailer, labeling objects like "facial hair," "car," and "forest" (taking into account how long these objects appear on-screen and when they show up the trailer). By comparing this information with analyses of other trailers, Merlin can try to predict what films might interest the people who saw Logan.
To create their "experimental movie attendance prediction and recommendation system" (named Merlin), 20th Century Fox partnered with Google to use the company's servers and open-source AI framework TensorFlow. In an accompanying blog post, the search giant explains Merlin's analysis of Logan. First, Merlin scans the trailer, labeling objects like "facial hair," "car," and "forest" (taking into account how long these objects appear on-screen and when they show up the trailer). By comparing this information with analyses of other trailers, Merlin can try to predict what films might interest the people who saw Logan.
:format(webp):no_upscale()/cdn.vox-cdn.com/uploads/chorus_asset/file/13375641/Foxs_tool.max_1600x1600.png){kind=link}
:format(webp):no_upscale()/cdn.vox-cdn.com/uploads/chorus_asset/file/13375771/Results_output.max_1900x1900.png){kind=link}
by analyzing movie trailers. Modern trailers for upcoming movies usually spoil anything possibly good or interesting about new movies. I seriously avoid watching trailers for movies I want to see. Although for other movies, trailers can convince me which movies to absolutely avoid.
Data analysis of movie revenue based on actors/scriptwriters/directors would be a better start, but that would cost way more money, because you'd have to work around "Hollywood Accounting" practices to figure out how much money movies actually created.
This type of analysis will create another miasma of Spiderman//Superman movie "reboots" because "This Time for Sure" Isn't there another Robin Hood movie coming out soon?