# Is X a good movie? – Forget the critics, pay attention to Internet Chatter

A team of smart folks in Japan have found a mathematical model for the ‘hit’ phenomenon in entertainment. It basically uses the advertisement budget time distribution and also word-of-mouth (WOM) to  work things out. Oh wait, how the heck do you measure WOM? Well they went for the number of posts on social network systems such as Twitter, Facebook, Google+. In their abstract they note …

The unit of time is days. The WOM distribution in time is found to be very close to the revenue distribution in time. Calculations for the Japanese motion picture market based on the mathematical model agree well with the actual revenue distribution in time.

Apparently they started out with an interest in modeling how rumors and word of mouth spread over social networks such as online blogs, Twitter, and Facebook. They focused on the big screen because they learned that daily box office revenue data was available and and because their team leader Akira Ishii of Tottori likes movies. So using actual data from Spider-Man 3The Da Vinci Code, and other imported and Japanese movies, the physicists developed a model that takes daily advertising spending and social network data and “can predict the [daily] revenue of the corresponding movie very well,”

But this is not new, others have done this before … right?

True, but this is the first attempt to include not just direct communication between two individuals but also what they call indirect communications, where someone views a Web page without commenting on it, since Web sites can record the number of its visitors. Ishii likens this to overhearing a conversation in a cafe. “Indirect communications are very important in explaining real market observations,” he says. He thinks his team’s work can be extended to online music sales and other consumer purchases. Ishii even successfully used Internet chatter to pick the winners in several recent elections in Japan. But he says he couldn’t publicize the results because of legal restrictions on publishing projections during campaigns.

Now before you get too excited and start pondering the thought … “Ooooh election predictions”, the answer is “No”. The model can be use only to extrapolate a trend a week or so into the future and as noted by Harold Wilson, a UK Prime Minister in the 1970s, “A week is a long time in politics”.

You can find their paper here in the New Journal of Physics.