Predict Emoji Combination with Retrieval Strategy

TL;DR

This paper introduces a Retrieval Strategy algorithm to predict emoji combinations based on short text context, significantly improving prediction accuracy by treating emoji sequences as language phrases.

Contribution

The paper presents a novel retrieval-based algorithm for emoji combination prediction, enhancing accuracy over existing methods.

Findings

F1 score improved from 0.141 to 0.204

Treats emoji sequences as language phrases for better prediction

Significant accuracy improvement demonstrated

Abstract

As emojis are widely used in social media, people not only use an emoji to express their emotions or mention things but also extend its usage to represent complicate emotions, concepts or activities by combining multiple emojis. In this work, we study how emoji combination, a consecutive emoji sequence, is used like a new language. We propose a novel algorithm called Retrieval Strategy to predict what emoji combination follows given a short text as context. Our algorithm treats emoji combinations as phrase in language, ranking sets of emoji combinations like retrieving words from dictionary. We show that our algorithm largely improves the F1 score from 0.141 to 0.204 on emoji combination prediction task.