Towards generalisable hate speech detection: a review on obstacles and solutions

Wenjie Yin; Arkaitz Zubiaga

doi:10.7717/peerj-cs.598

Towards generalisable hate speech detection: a review on obstacles and solutions

PeerJ Comput Sci. 2021 Jun 17:7:e598. doi: 10.7717/peerj-cs.598. eCollection 2021.

Authors

Wenjie Yin¹, Arkaitz Zubiaga¹

Affiliation

¹ School of Electronic Engineering and Computer Science, Queen Mary University of London, London, United Kingdom.

Abstract

Hate speech is one type of harmful online content which directly attacks or promotes hate towards a group or an individual member based on their actual or perceived aspects of identity, such as ethnicity, religion, and sexual orientation. With online hate speech on the rise, its automatic detection as a natural language processing task is gaining increasing interest. However, it is only recently that it has been shown that existing models generalise poorly to unseen data. This survey paper attempts to summarise how generalisable existing hate speech detection models are and the reasons why hate speech models struggle to generalise, sums up existing attempts at addressing the main obstacles, and then proposes directions of future research to improve generalisation in hate speech detection.

Keywords: Abusive language; Generalisation; Hate speech; Literature review; Social media; Text classification.

Grants and funding

Wenjie Yin is funded by the School of Electronic Engineering and Computer Science, Queen Mary University of London. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.