What Makes a Quote Memorable? An Analytical Look at Your Favorite Movie Quotes

text mining

text mining, Quantified Communications, analytics

“You had me at Hello;” “I love the smell of napalm in the morning;” “Hello, my name is Inigo Montoya.” Why do these particular quotes stick in our heads while the rest of the scripts are quickly forgotten?

The answer lies in “Culturomics,” a term that refers to the use of quantitative metrics to analyze the social sciences and humanities. The term was coined by Jean-Baptiste Michel and Erez Lieberman Aiden, developers of the Google n-gram viewer, whose research started with algorithms to find patterns among literary texts dating back hundreds of years. They applied their culturomics analysis to answer such questions as: which authors were most influential in the 19th century (answer: Jane Austen and Sir Walter Scott); when did women start to become more prevalent than men in literature (answer: 1985); and when we refer to the past, how far back do we mean (answer: formerly 32 years, now 10 years).

The foundation of the n-gram viewer literature measurement system is an analysis of written communication, meaning we can also apply culturomics to analyze modern day phrases such as movie scripts. Jon Kleinberg, the pioneering computer scientist at Cornell who specializes in networks, recently set out to discover what makes a movie quote memorable. What is it about a line of dialogue – the words used, the syntax, and the context – that causes people to leave with that particular quote lingering in their memories? Using quantitative analytics, the researchers found that “In aggregate, memorable quotes use less common word choices, but at the same time are built upon a scaffolding of common syntactic patterns”. By using algorithms to compare memorable movie quotes (based on IMDb and search engine hits) to the entire movie scripts, as well as to text from news articles, they were able to find key patterns to differentiate memorable quotes from non-memorable ones, including:

  • Use of complex, distinctive words
  • Generality/portability of quote (can it be used out of context?)

What makes this kind of research so exciting is that it can be applied not just to movie quotes, but to advertising, social media (think influential tweets), newspapers, and anywhere you need a “hook” to draw in your audience.