Analyzing Gender Polarity in Short Social Media Texts with BERT: The Role of Emojis and Emoticons

TL;DR

This paper fine-tunes BERT-based models to detect gender polarity in Twitter accounts, emphasizing the influence of emojis and emoticons on classification accuracy in short social media texts.

Contribution

It introduces an analysis of how emojis and emoticons affect gender detection performance in BERT models on Twitter data.

Findings

Emojis and emoticons improve gender classification accuracy.

Inclusion of non-word inputs enhances model performance.

Short social media texts benefit from emoji/emoticon analysis.

Abstract

In this effort we fine tuned different models based on BERT to detect the gender polarity of twitter accounts. We specially focused on analyzing the effect of using emojis and emoticons in performance of our model in classifying task. We were able to demonstrate that the use of these none word inputs alongside the mention of other accounts in a short text format like tweet has an impact in detecting the account holder's gender.