Japanese Scientists Produce Mathematical Model to Predict Box Office From Social Media Activity
Study published in physics journal also found advertising timing more important than spending, but less crucial to success than online buzz.
TOKYO – Japanese scientists have devised a mathematical formula that can predict the box office performance of a movie based on the level of related activity on social networks and other websites before and during its release.
The study, led by Professor Akira Ishii from the Department of Applied Mathematics and Physics at Tottori University, also found that when advertising was placed was more important than overall promotional budgets.
Collecting revenue data on 25 Hollywood and local movies released in Japan, including Avatar, The Da Vinci Code, Crows Zero and Always: Sunset on Third Street 3, the group compared it with advertising spending and online activity on social networks and blogs.
“We found a direct correlation between the number of social media postings about a movie on a given day, and the number of people who intended to purchase tickets,” Professor Ishii told The Hollywood Reporter.
“However, there was no direct relationship between the advertising spending and the purchasing intention. The timing of the advertising campaign is important though, with two weeks to ten days before opening being the optimum time,” explained the professor.
The model was not developed to predict the success or failure of films and the use of data from online social activities and movie revenue was “an experiment to test the equation,” according to Ishii.
The availability of daily revenue data from the film industry was an important factor for the team’s research.
The theory is published in this month’s New Journal of Physics in a paper titled “The 'hit' phenomenon: a mathematical model of human dynamics interactions as a stochastic process.”
“The model should be applicable to movie releases in other markets and also to other products,” said Ishii.