Scholarlink

<p>Detecting hate speech is challenging because language constantly evolves, often carrying subtle emotional undertones that can be difficult to interpret. While many existing approaches rely on semantic analysis, they frequently miss these emotional cues and struggle to adapt to different contexts. This paper introduces an enhanced Dual Contrastive Learning (DCL) framework, integrating emotion profiling with fine-tuned language models (BERTweet, RoBERTa, TimeLMs) to address these gaps. By using SHAP (SHapley Additive exPlanations) for interpretability, our approach enhances both detection accuracy and explainability. Experiments on SemEval-2019, Davidson, and a Unified Twitter corpus show that our EmotionDCL models outperform baseline methods, with TimeLMs achieving 81.20% accuracy on SemEval and 94.04% on Davidson. Ablation studies confirm the synergy between contrastive learning and emotion integration, highlighting anger, fear, and anticipation as dominant emotional drivers of hate speech. These findings show the importance of emotion-aware, context-adaptive detection systems and the need for strategies to address class imbalance and linguistic evolution.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An emotion aware context adaptive machine learning approach for detecting hate speech in social media

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月11日

查看全文
  • Krishan Chavinda,
  • Pasan Kalansooriya,
  • Thushalya Weerasuriya,
  • Nisansa de Silva,
  • Uthayasanker Thayasivam,
  • Kogul Srikandabala,
  • Kirishnni Prabagar,
  • Damminda Alahakoon

摘要

Detecting hate speech is challenging because language constantly evolves, often carrying subtle emotional undertones that can be difficult to interpret. While many existing approaches rely on semantic analysis, they frequently miss these emotional cues and struggle to adapt to different contexts. This paper introduces an enhanced Dual Contrastive Learning (DCL) framework, integrating emotion profiling with fine-tuned language models (BERTweet, RoBERTa, TimeLMs) to address these gaps. By using SHAP (SHapley Additive exPlanations) for interpretability, our approach enhances both detection accuracy and explainability. Experiments on SemEval-2019, Davidson, and a Unified Twitter corpus show that our EmotionDCL models outperform baseline methods, with TimeLMs achieving 81.20% accuracy on SemEval and 94.04% on Davidson. Ablation studies confirm the synergy between contrastive learning and emotion integration, highlighting anger, fear, and anticipation as dominant emotional drivers of hate speech. These findings show the importance of emotion-aware, context-adaptive detection systems and the need for strategies to address class imbalance and linguistic evolution.