Wikipedia’s Big Data Can Be Used to Predict Summer Box-Office Hits

If you turned to Wikipedia for a pre-Avengers deep dive into the Marvel canon or refresher on Harry Potter’s defenses against the dark arts, you are apparently not alone. What’s more, your digital breadcrumbs might be a preview of coming box-office receipts. A team of researchers has shown that Wikipedia data can predict how popular a film will be. A team from the Budapest University of Technology and Economics looked at 312 movies that came out in 2010 (think Inception, Toy Story 3 and Twilight: Eclipse) and built a mathematical model that measured the number of readers and editors for the movie’s Wiki page. The model’s data was juxtaposed with box office earnings and showed almost a 77 percent correlation between popularity on Wikipedia and big opening weekends.