Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement
This addresses the problem of scalable content moderation for social media platforms, offering an incremental improvement over existing methods by handling evolving slang and platform-specific peculiarities without requiring labeled data.
The paper tackled cross-platform hate speech detection by proposing HATE WATCH, a weakly supervised causal disentanglement framework that eliminates the need for explicit target labels, achieving superior performance in empirical tests across platforms.
Content moderation faces a challenging task as social media's ability to spread hate speech contrasts with its role in promoting global connectivity. With rapidly evolving slang and hate speech, the adaptability of conventional deep learning to the fluid landscape of online dialogue remains limited. In response, causality inspired disentanglement has shown promise by segregating platform specific peculiarities from universal hate indicators. However, its dependency on available ground truth target labels for discerning these nuances faces practical hurdles with the incessant evolution of platforms and the mutable nature of hate speech. Using confidence based reweighting and contrastive regularization, this study presents HATE WATCH, a novel framework of weakly supervised causal disentanglement that circumvents the need for explicit target labeling and effectively disentangles input features into invariant representations of hate. Empirical validation across platforms two with target labels and two without positions HATE WATCH as a novel method in cross platform hate speech detection with superior performance. HATE WATCH advances scalable content moderation techniques towards developing safer online communities.