Emojis usage in social media by demographics

In this project, we want to know if emojis are used differently by different personas.


The main categories of analysis are:

  1. Gender: Males, Females
  2. Race: White, Black, Asian, Hispanic

For each group of persona, the following analysis is applied:

  1. Percentage of usage of emojis
  2. Top used emojis
  3. Distinctive emojis

Machine learning models are built for gender and race detection of users using emoji.

Work steps contain the following:

  1. Collecting millions of tweets with emojis
  2. Trying different methods for gender and race estimation of Twitter users
  3. Performing statistical analysis for data
  4. Building user gender and race detection models using only emoji usage in users’ timeline