Hollywood’s obsessions

Data mining movie themes.

obsessions02As Oscar Wilde once quipped, “The good ended happily, and the bad unhappily. That is what fiction means.” The same could be said of Hollywood: films present a distorted perspective on the human experience.

Marko Plahuta, a user interface specialist at Telekom Slovenia with a hobbyists’ interest in data visualization, recently attempted to study Hollywood’s obsessions in a novel way. He collected data on 15,000 movies from IMDB, the popular online database of information on films, TV shows and video games. The database categorizes every film one of ten genres (such as “Drama” or “Comedy”) and also by tags. There are hundreds of tags, which often pertain to elements in the plot (“spaceship crash,” “axe murderer” or “Great White Shark”). Plahuta plotted all this on an interactive map that attempts to draw connections between films. Genres and tags associated with larger numbers of movies appear larger. Related categories also appear in the same color.

Check out the result.

Plahuta claims his creation sheds light on Hollywood’s values, as reflected in its films. Among his conclusions: “It seems that most of Hollywood romance takes place in New York City, and that there’s a lot of sex going on there at the same time,” he writes. “There is some friendship involved, but not much…On the other hand, California, as represented in movies, seems much more family-oriented. There’s a lot of boys, children, girls and babies around it. There’s also a lot of dreams and female nudity.” Plahuta’s methodology should provoke considerable head-scratching and quibbling, but the visual appeal of his creation is difficult to deny.