How Wikipedia Can Accurately Predict A Movie’s Box Office Success

How Wikipedia Can Accurately Predict A Movie’s Box Office Success

Predicting the financial success of a movie is a complicated process involving teams of analysts, focus groups and all manner of complicated pie graphs. However, if new research from Europe is to be believed, the same results can be achieved by simply heading to the film’s Wikipedia page before the movie comes out.

[credit provider=”Miramax Films” url=””]

According to researchers from the University of Oxford, et al, the popularity of upcoming movies can be accurately predicted on Wikipedia via the activity level of editors and the number of viewers the movie page has.

To test their theory, the research team analysed the level of user activity on 312 Wikipedia movie pages in the lead up to the films’ releases. The analysis included the number of views the page received, the number of editors who had contributed to the article, the number of individual edits made and the collaborative rigor of the editing train of the article.

They found that a movie’s box office success was linked intrinsically to an active Wikipedia page.

The analysis presented here can make predictions with reasonable accuracy as early as one month before release. It is evident that the prediction is more precise for more successful movies. Some examples of the movies whose box office receipts were predicted accurately are Iron Man 2, Alice in Wonderland, Toy Story 3, Inception, Clash of the Titans, and Shutter Island.

Moreover, they believe their predictive model is both simpler and more accurate than rival methods, such as Twitter-tracking:

The predicting power of the Wikipedia-based model, despite its simplicity compared to the Twitter, can be explained by the fact that many of the Wikipedia editors are committed followers of movie industry who gather information and edit related articles significantly earlier than the release date, whereas the “mass” production of tweets only occurs very close to the release time, mostly evoked by marketing campaigns.

In addition to helping movie studios balance their books, the researchers claim their model provides proof that socially generated ‘‘big data’’ can be used to access information about collective states of the minds in human societies.

“[Our] results clearly show how simple use of user generated data in a social environment like Wikipedia can enhance our ability to predict the collective reaction of society to a cultural product….The introduced approach can be easily generalized to other fields where mining of public opinion provides valuable insights e.g., financial decisions, policy making, and governance.”

The researchers acknowledge that their model was less accurate with unpopular movies where the volume of related Wikipedia data was smaller. In other words, discovering which movie will become a ‘sleeper hit’ remains as elusive as ever.

See also: What Ten Australian Films Would You Recommend To A Non-Local? | Are Australians Being Rorted By Online Movie Services? [Infographic] | Can The Splendour Of 4K Save A Crap Movie? | Has Pixar Still Got It?


  • Often you can tell if a movie is going to be crap, based on it’s trailer.
    The number of blink shots, explosions, fight scenes and one liners is usually directly inverse to it’s overall quality. For ST: Into Darkness,simply swap out blink shots with lens flares.

    A good movie will typically have contiguous segments of the movie (tasters), whereas a trailer for a crap movie will just have all the action bits spliced together – the trailer for the Lone Ranger is case in point.

    The trailer for White House Down seems to have nothing but excessive blinks shots and explosions, with mediocre quips. From that, I’m guessing it’s going to be steaming pile of shite.
    Anyone know if it is or not ?

Comments are closed.

Log in to comment on this story!