Cross-Platform and Cross-Domain Abusive Language Detection with Supervised Contrastive Learning

TL;DR

This paper introduces SCL-Fish, a novel supervised contrastive learning meta-learning approach for cross-platform abusive language detection, outperforming existing models and being data-efficient.

Contribution

The paper proposes SCL-Fish, a new contrastive learning based meta-learning method that improves cross-platform abusive language detection, addressing domain generalization challenges.

Findings

SCL-Fish outperforms ERM and state-of-the-art models.

SCL-Fish is data-efficient and comparable to large-scale pre-trained models.

The approach enhances detection on unseen platforms.

Abstract

The prevalence of abusive language on different online platforms has been a major concern that raises the need for automated cross-platform abusive language detection. However, prior works focus on concatenating data from multiple platforms, inherently adopting Empirical Risk Minimization (ERM) method. In this work, we address this challenge from the perspective of domain generalization objective. We design SCL-Fish, a supervised contrastive learning integrated meta-learning algorithm to detect abusive language on unseen platforms. Our experimental analysis shows that SCL-Fish achieves better performance over ERM and the existing state-of-the-art models. We also show that SCL-Fish is data-efficient and achieves comparable performance with the large-scale pre-trained models upon finetuning for the abusive language detection task.