科学美国人60秒 SSS 大数据揭示史上最具影响力电影

（单词翻译）

大数据揭示史上最具影响力电影

This is Scientific American — 60-Second Science. I'm Christopher Intagliata.

If you go by ticket sales, the most popular film of all time is Gone With the Wind. (GONE WITH THE WIND CLIP: "Frankly¹ my dear, I don't give a damn.") That is adjusting for inflation, by the way.

But a movie's take at the box office is influenced by ad budgets, distribution, reviews—so box office may not be the best measure of a movie's cultural influence. To address that question, researchers gave movies the big data treatment—by analyzing² the complex network of connections between 47,000 movies on the Internet Movie Database, IMDb.

The popular movie site tracks every time a film has been referenced or spoofed, featured or remade: all factors that indicate a movie's influence on subsequent films. And by analyzing those connections with a handful of algorithms—including Google's PageRank algorithm—the data scientists came up with a new number one: it's another 1939 flick³ by the same director of Gone With the Wind which has been spoofed more than 300 times, and referenced by nearly 3000 movies:

The Wizard of Oz. (WIZARD OF OZ CLIP: "Toto, I have a feeling we're not in Kansas anymore.") Dorothy’s adventure was followed by the original Star Wars, the original Psycho, King Kong, and 2001: A Space Odyssey⁴. The full ranking is in the journal Applied⁵ Network Science.

The analysis does have limitations: It favors older films, and the underlying⁶ IMDb data has been shown to be biased⁷ towards Western movies. That is, the products of western civilization, not shoot-em-ups.

As for Rhett Butler and Scarlett O'Hara? They still made the list, but down at number 19. (GONE WITH THE WIND CLIP: "After all, tomorrow is another day!")

Thanks for listening for Scientific American — 60-Second Science. I'm Christopher Intagliata.