MasonPerplexity at Multimodal Hate Speech Event Detection 2024: Hate Speech and Target Detection Using Transformer Ensembles

TL;DR

This paper presents a multimodal hate speech detection system using transformer ensembles, achieving high F1-scores and ranking third in a shared task at EACL 2024.

Contribution

It introduces an ensemble approach combining multiple transformer models for detecting hate speech and targets in multimodal content during political events.

Findings

Achieved 0.8347 F1-score in hate speech detection

Achieved 0.6741 F1-score in target detection

Ranked 3rd in both sub-tasks at EACL 2024

Abstract

The automatic identification of offensive language such as hate speech is important to keep discussions civil in online communities. Identifying hate speech in multimodal content is a particularly challenging task because offensiveness can be manifested in either words or images or a juxtaposition of the two. This paper presents the MasonPerplexity submission for the Shared Task on Multimodal Hate Speech Event Detection at CASE 2024 at EACL 2024. The task is divided into two sub-tasks: sub-task A focuses on the identification of hate speech and sub-task B focuses on the identification of targets in text-embedded images during political events. We use an XLM-roBERTa-large model for sub-task A and an ensemble approach combining XLM-roBERTa-base, BERTweet-large, and BERT-base for sub-task B. Our approach obtained 0.8347 F1-score in sub-task A and 0.6741 F1-score in sub-task B ranking 3rd on both sub-tasks.