Perhaps you’re planing to watch a movie, but will the new release you choose be a blockbuster or a lackluster flop? Well Wikipedia may help predict your choice’s success or failure in the box office, according to a recently published study.
In this study, researchers tracked activity on Wikipedia entries for 312 movies (released in 2010), including aspects like number of views, users, and edits; and compared this activity to the box office success of the movies in a computational model. They found a strong correlation between higher Wikipedia activity before a movie was released, and the box office success of the film.
The study could accurately predict the blockbuster success of movies like Iron Man 2, Shutter Island and Inception, but was unsuccessful with movies such as The Lottery and Animal Kingdom. The scientists attribute the lack of predictability to the amount of data provided for the different types of movies. According to the authors, their analysis can be used to provide reasonable predictions about a movie’s success as early as a month prior to its release.
The study is a foray into using “big data” generated from the social web to predict people’s reactions to a new product- in this case, a movie. Previous studies have used social data, such as tweets related to an event, to estimate public sentiment and reactions. Here, the authors use social data in advance of the ‘event’ to gauge public sentiment after the movie has launched. They conclude, “Our statistical approach, free of any language based or sentiment analysis, can be easily generalized to non-English speaking movie markets or even other kinds of products.”
- Mestyán M, Yasseri T, Kertész J (2013) Early Prediction of Movie Box Office Success Based on Wikipedia Activity Big Data. PLoS ONE 8(8): e71226. doi:10.1371/journal.pone.0071226