Analyzing and Predicting Emoji Usages in Social Media

Abstract

Emojis can be regarded as a language for graphical expression of emotions, and have been widely used in social media. They can express more delicate feelings beyond textual information and improve the effectiveness of computer-mediated communication. Recent advances in machine learning make it possible to automatic compose text messages with emojis. However, the usages of emojis can be complicated and subtle so that analyzing and predicting emojis is a challenging problem. In this paper, we first construct a benchmark dataset of emojis with tweets and systematically investigate emoji usages in terms of tweet content, tweet structure and user demographics. Inspired by the investigation results, we further propose a multitask multimodality gated recurrent unit (mmGRU) model to predict the categories and positions of emojis. The model leverages not only multimodality information such as text, image and user demographics, but also the strong correlations between emoji categories and their positions. Our experimental results show that the proposed method can significantly improve the accuracy for predicting emojis for tweets (+9.0% in F1-value for category and +4.6% in F1-value for position). Based on the experimental results, we further conduct a series of case studies to unveil how emojis are used in social media.