Detection of Conspiracy Theories Beyond Keyword Bias in German-Language Telegram Using Large Language Models

Milena Pustet, Elisabeth Steffen, Helena Mihaljevic


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 dataset for testing the behaviors of automated content moderators against content policies. First, we engage 28 annotators and GPT in a six-step annotation process, resulting in a list of hateful and non-hateful test suites matching each of Facebook’s 41 hate speech policies. Second, we test the performance of state-of-the-art hate speech detectors against HateModerate, revealing substantial failures these models have in their conformity to the policies. Third, using HateModerate, we augment the training data of a top-downloaded hate detector on HuggingFace. We observe significant improvement in the models’ conformity to content policies while having comparable scores on the original test data. Our dataset and code can be found in the attachment.
Anthology ID:
2024.woah-1.2
Volume:
Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Yi-Ling Chung, Zeerak Talat, Debora Nozza, Flor Miriam Plaza-del-Arco, Paul Röttger, Aida Mostafazadeh Davani, Agostina Calabrese
Venues:
WOAH | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13–27
Language:
URL:
https://aclanthology.org/2024.woah-1.2
DOI:
10.18653/v1/2024.woah-1.2
Bibkey:
Cite (ACL):
Milena Pustet, Elisabeth Steffen, and Helena Mihaljevic. 2024. Detection of Conspiracy Theories Beyond Keyword Bias in German-Language Telegram Using Large Language Models. In Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024), pages 13–27, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Detection of Conspiracy Theories Beyond Keyword Bias in German-Language Telegram Using Large Language Models (Pustet et al., WOAH-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.woah-1.2.pdf