HateModerate: Testing Hate Speech Detectors against Content Moderation Policies

arXiv:2307.12418v2 Announce Type: replace-cross
Abstract: To protect users from massive hateful content, existing works studied automated hate speech detection. Despite the existing efforts, one question remains: do automated hate speech detectors conform to social media content policies? A platform's content policies are a checklist of content moderated by the social media platform. Because content moderation rules are often uniquely defined, existing hate speech datasets cannot directly answer this question.
This work seeks to answer this question by creating HateModerate, a …

abstract arxiv automated checklist content moderation cs.cl cs.se detection hate speech hate speech detection massive media moderation platform protect question social social media speech testing type