Hate Speech
Hate speech, encompassing discriminatory and derogatory language targeting individuals or groups, is a significant online problem. Current research focuses on improving automated hate speech detection, employing various deep learning models like BERT, LSTM, and transformer-based architectures, often incorporating multimodal data (text and images) and addressing challenges like implicit hate, code-mixing, and cross-cultural variations. These efforts aim to enhance the accuracy and fairness of hate speech detection systems, ultimately contributing to safer online environments and informing content moderation strategies. The field also explores methods for generating counterspeech and mitigating biases within detection models.
Papers
Target Span Detection for Implicit Harmful Content
Nazanin Jafari, James Allan, Sheikh Muhammad Sarwar
Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset
Janis Goldzycher, Paul Röttger, Gerold Schneider
NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Data
Manuel Tonneau, Pedro Vitor Quinta de Castro, Karim Lasri, Ibrahim Farouq, Lakshminarayanan Subramanian, Victor Orozco-Olvera, Samuel P. Fraiberger