🗽🍎🚕

How New York are you?

So you think you're a real New Yorker? Well, here's your chance to quantify how cool and cynical you are by comparing your opinions with those of all other New Yorkers—at least, those active on Twitter in 2018.

How to play:

Speakers, a microphone (laptop built-ins are fine), and the Chrome browser are required. The computer will volley hot topic keywords from the past year, and two players will have one shot per topic to prove how aligned they are with most common New York opinions. But you have to be quick, because nothing is less cool than trying too hard.

Click here to test your mic.

Click here to view a demo.

How it works:

Each topic has a corresponding word2vec model that's trained on relevant tweets that originated in NYC from the past year. Word2vec analyzes corpora to find relationships among its words and embed them into a multidimensional space; the closer words are in this space, the more frequently they appear near each other in the corpus—thus, you can get a sense of what New Yorkers are tweeting, about which subjects, and with what frequency. Tensorflow.js then calculates the distances between words, which serves as the basis for the scoring system. The closer your responses are to the topic—and the faster you respond—the higher you score. For more details, see my documentation.