Online conversations are particularly susceptible to derailment, which can manifest itself in the form of toxic communication patterns including disrespectful comments and abuse. Forecasting conversation derailment predicts signs of derailment in advance enabling proactive moderation of conversations. State-of-the-art approaches to conversation derailment forecasting sequentially encode conversations and use graph neural networks to model dialogue user dynamics. However, existing graph models are not able to capture complex conversational characteristics such as context propagation and emotional shifts. The use of common sense knowledge enables a model to capture such characteristics, thus improving performance. Following this approach, here we derive commonsense statements from a knowledge base of dialogue contextual information to enrich a graph neural network classification architecture. We fuse the multi-source information on utterance into capsules, which are used by a transformer-based forecaster to predict conversation derailment. Our model captures conversation dynamics and context propagation, outperforming the state-of-the-art models on the CGA and CMV benchmark datasets

翻译：在线对话尤其容易发生脱轨现象，其可能表现为包括不尊重性评论和辱骂在内的有害交流模式。对话脱轨预测旨在提前识别脱轨迹象，从而实现对话的主动调控。当前最先进的对话脱轨预测方法通过顺序编码对话内容，并利用图神经网络建模对话用户动态。然而，现有图模型难以捕捉上下文传播与情绪转变等复杂对话特征。常识知识的运用使模型能够捕获此类特征，从而提升预测性能。基于此思路，本研究从对话上下文信息知识库中提取常识陈述，用以增强图神经网络分类架构。我们将话语的多源信息融合至胶囊中，通过基于Transformer的预测器实现对话脱轨预测。该模型能有效捕捉对话动态与上下文传播机制，在CGA和CMV基准数据集上的表现优于现有最优模型。