Class Projects - Spring 2016

emojify

emojify translates English sentences into emoji.

What it does

As digital media evolves and publishers strive to include the language of the web in their work, a pure or mixed emoji headline may be one way to help publishers capture audience attention.

The emojify interface is simple, offering a single input field for an English headline, followed by an output of emoji that’s based on the English. Though designed with editors in mind, emojify may also entertain everyday web users just as easily.


How it works

Emojify takes plain English and runs it through a Flask server. The technology determines root words, trims punctuation, performs synonym lookups (via WordNet), handles negation, and converts all text to lowercase. Emojify searched for bigrams first because many of emoji definitions (e.g. New York) contain two words. The system follows with a unigram lookup. The Flask server accesses a json file containing emojis, their definitions, and some synonyms. This file is lemmatized before it returns to the user. After all these tasks run, the emoji translation goes back through Flask and returns a string of emojis to the user.

Key Technologies

  • Flask
  • Lemmatization
  • Word-Net
  • JSON Dictionary

Next Steps

On of the biggest hurdles facing this project is the lack of emojis for many words and phrases. An expanded emoji library would be a great help to the project. We’d also like to improve consistency between Apple and non-Apple systems, which sometimes use different icons and can affect context.

Connect

Diane Liu

Colin Mo

Dara Rubin 

Chenhui Zhou