Tackling Online Abuse: A Survey of Automated Abuse Detection Methods

TL;DR

This survey reviews automated abuse detection methods in NLP, analyzing datasets, approaches, trends, challenges, and ethical considerations to guide future research in combating online abuse.

Contribution

It provides a comprehensive overview of existing NLP-based abuse detection methods, highlighting strengths, limitations, and ethical guidelines for future development.

Findings

Identification of key datasets used in abuse detection

Analysis of computational approaches and their effectiveness

Discussion of challenges and ethical considerations

Abstract

Abuse on the Internet represents an important societal problem of our time. Millions of Internet users face harassment, racism, personal attacks, and other types of abuse on online platforms. The psychological effects of such abuse on individuals can be profound and lasting. Consequently, over the past few years, there has been a substantial research effort towards automated abuse detection in the field of natural language processing (NLP). In this paper, we present a comprehensive survey of the methods that have been proposed to date, thus providing a platform for further development of this area. We describe the existing datasets and review the computational approaches to abuse detection, analyzing their strengths and limitations. We discuss the main trends that emerge, highlight the challenges that remain, outline possible solutions, and propose guidelines for ethics and explainability