Cross-Platform and Cross-Domain Abusive Language Detection with Supervised Contrastive Learning
This addresses the problem of detecting abusive language across diverse online platforms for content moderation, though it is incremental as it builds on existing contrastive and meta-learning methods.
The paper tackled cross-platform abusive language detection by proposing SCL-Fish, a supervised contrastive learning integrated meta-learning algorithm, which outperformed ERM and state-of-the-art models on unseen platforms and achieved comparable performance to large-scale pre-trained models with data efficiency.
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.