用图神经网络建模对话结构，提升社交媒体辱骂检测准确率
Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights
- 将评论构建为图结构，节点是评论，边表示回复关系
- 在多个数据集上实现显著更高的F1分数，最高提升9.2%
- 适合研究社交对话理解与内容安全的工程师和学者
社交媒体中的辱骂语言检测面临挑战，因判断是否辱骂往往依赖上下文，包括前序评论的内容与回复拓扑结构。传统辱骂检测模型常忽略此上下文，导致性能不可靠。近期融合上下文的NLP方法多采用简化的表示方式，结果不一致。本文提出新方法，利用图神经网络（GNN）将社交对话建模为图：节点代表评论，边捕捉回复关系。系统性地探究多种图表示与上下文窗口，找到最优配置。所提GNN模型优于无上下文基线与线性上下文方法，在多个数据集上显著提升F1分数，验证了结构化上下文的重要性，并确立GNN作为上下文感知辱骂检测的稳健框架。
原文摘要 · Abstract (English)
Detecting abusive language in social media conversations poses significant challenges, as identifying abusiveness often depends on the conversational context, characterized by the content and topology of preceding comments. Traditional Abusive Language Detection (ALD) models often overlook this context, which can lead to unreliable performance metrics. Recent Natural Language Processing (NLP) methods that integrate conversational context often depend on limited and simplified representations, and report inconsistent results. In this paper, we propose a novel approach that utilize graph neural networks (GNNs) to model social media conversations as graphs, where nodes represent comments, and edges capture reply structures. We systematically investigate various graph representations and context windows to identify the optimal configuration for ALD. Our GNN model outperform both context-agnostic baselines and linear context-aware methods, achieving significant improvements in F1 scores. These findings demonstrate the critical role of structured conversational context and establish GNNs as a robust framework for advancing context-aware abusive language detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。