Towards Generalized Offensive Language Identification

TL;DR

This paper evaluates how well offensive language detection models and datasets perform across diverse domains, highlighting their generalizability and robustness in real-world applications.

Contribution

It introduces a novel benchmark to empirically assess the cross-domain generalizability of offensive language detection models and datasets.

Findings

Models vary significantly in cross-domain performance

Certain datasets improve generalizability when used for training

The benchmark reveals gaps in current offensive language detection systems

Abstract

The prevalence of offensive content on the internet, encompassing hate speech and cyberbullying, is a pervasive issue worldwide. Consequently, it has garnered significant attention from the machine learning (ML) and natural language processing (NLP) communities. As a result, numerous systems have been developed to automatically identify potentially harmful content and mitigate its impact. These systems can follow two approaches; (1) Use publicly available models and application endpoints, including prompting large language models (LLMs) (2) Annotate datasets and train ML models on them. However, both approaches lack an understanding of how generalizable they are. Furthermore, the applicability of these systems is often questioned in off-domain and practical environments. This paper empirically evaluates the generalizability of offensive language detection models and datasets across a novel generalized benchmark. We answer three research questions on generalizability. Our findings will be useful in creating robust real-world offensive language detection systems.