Paul Röttger

Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media

2021

Language use differs between domains and even within a domain, language use changes over time. For pre-trained language models like BERT, domain adaptation through continued pre-training has been shown to improve performance on in-domain downstream …

Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages

2022

Hate speech is a global phenomenon, but most hate speech datasets so far focus on English-language content. This hinders the development of more effective hate speech detection models in hundreds of languages spoken by billions …

HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter

2024 · arXiv (Cornell University)

To address the global challenge of online hate speech, prior research has developed detection models to flag such content on social media. However, due to systematic biases in evaluation datasets, the real-world effectiveness of these …

AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages

2025

Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Abinew Ali Ayele, David Ifeoluwa Adelani, Ibrahim Said Ahmad, Saminu Mohammad Aliyu, Paul Röttger, Abigail Oppong, Andiswa Bukula, Chiamaka Ijeoma Chukwuneke, Ebrahim Chekol Jibril, Elyas Abdi Ismail, Esubalew Alemneh, Hagos …