2026-10-28 · ArXiv
arXiv:2411.05819v2 Announce Type: replace-cross
Abstract: Hate speech detectors must separate hateful posts from the far more common offensive but non-hateful ones, and two popular ideas for doing so are hierarchical (coarse-to-fine) classification and sentiment features. We revisit our earlier transformer-based framework, which combines both ideas, and test each component in a controlled study on two public benchmarks (Davidson et al., 24,783 tweets; HateXplain, 19,229 posts) with five random splits, validation-based tuning, and paired bootstrap tests. With linear models over word and character n-grams, the dominant-class-first hierarchy used in our framework lowered macro-F1 by 1.1-1.5 points relative to a flat classifier (p
原文链接：https://arxiv.org/abs/2411.05819
查看更多资讯请见 AI 行业资讯。