Cross-Platform Chinese Offensive Comment Detection via Dual-Threshold Hard Example Mining
For practitioners deploying offensive comment detection across Chinese social media platforms, this work addresses the domain shift problem with a cost-effective solution.
The paper tackles performance degradation in cross-platform Chinese offensive comment detection. The proposed dual-threshold hard example mining strategy achieves significant performance gains across four social media platforms (Weibo, Xiaohongshu, Tieba, Zhihu) with low-cost domain adaptation.
Cross-platform deployment of offensive comment detection for Chinese social media suffers performance degradation. The paper proposes a dual-threshold hard mining method to address this. First, the clean-Chinese-base RoBERTa is finetuned on COLD to establish a binary baseline for fair comparison. Second, a three-class fine-labeled test set covering Weibo, Xiaohongshu, Tieba, and Zhihu is constructed, domain distances from the source are quantified using Jaccard and Proxy-A Distance, as well as the degradation bottleneck of the baseline under domain shift is systematically revealed. Herein, a dual threshold hard example mining strategy is proposed. High- and low-confidence error-prone samples are filtered from unlabeled corpora by prediction confidence. The model is secondarily finetuned under implicit contexts with merely a small set of manually labeled hard examples, realizing low-cost cross-platform domain adaptation. Experiments reveal significant performance gains of the optimized model across four platforms.