Keyword-Enhanced Multi-Expert Framework for Hate Speech Detection

The proliferation of hate speech on the Internet is harmful to the psychological health of individuals and society. Thus, establishing and supporting the development of hate speech detection and deploying evasion techniques is a vital task. However, existing hate speech detection methods tend to ignore the sentiment features of target sentences and have difficulty identifying some implicit types of hate speech. The performance of hate speech detection can be significantly improved by gathering more sentiment features from various sources. In the use of external sentiment information, the key information of the sentences cannot be ignored. Thus, this paper proposes a keyword-enhanced multiexperts framework. To begin, the multi-expert module of multi-task learning is utilized to share parameters and thereby introduce sentiment information. In addition, the critical features of the sentences are highlighted by contrastive learning. This model focuses on both the key information of the sentence and the external sentiment information. The final experimental results on three public datasets demonstrate the effectiveness of the proposed model.