How New York Are You?

How New York are you? is a voice-controlled browser game where two players compete to be crowned the realest New Yorker. The computer volleys hot topic keywords from the past year, and each player will have one shot per topic to prove how aligned they are with most common New York opinions. The quicker and closer the response, the higher your New York Quotient.

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 the documentation here.