I Beg to Differ: A study of constructive disagreement in online conversations
I Beg to Differ: A study of constructive disagreement in online conversations
复制标题
DOI：
10.18653/v1/2021.eacl-main.173
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Christine de Kock;Andreas Vlachos
中科院分区：
文献类型：
--
作者：
Christine de Kock;Andreas Vlachos
分歧在人类交流中无处不在。在本文中，我们将探讨是什么使分歧具有建设性。为此，我们构建了WikiDisputes，一个包含7425个包含内容争议的维基百科讨论页面对话的语料库，并定义了预测分歧是否会升级为调解的任务。我们评估了基于特征的模型与语言标记从以前的工作，并证明他们的性能得到改善，通过使用功能，捕捉语言标记的变化，在整个对话中，而不是平均值。我们开发了各种神经模型，并表明考虑到对话的结构提高了预测准确性，超过了基于特征的模型。我们通过评估其仅暴露于对话开始时的行为来评估我们最好的神经模型的预测准确性和不确定性，发现随着模型暴露于更多信息，模型准确性提高，不确定性降低。
Disagreements are pervasive in human communication. In this paper we investigate what makes disagreement constructive. To this end, we construct WikiDisputes, a corpus of 7425 Wikipedia Talk page conversations that contain content disputes, and define the task of predicting whether disagreements will be escalated to mediation by a moderator. We evaluate feature-based models with linguistic markers from previous work, and demonstrate that their performance is improved by using features that capture changes in linguistic markers throughout the conversations, as opposed to averaged values. We develop a variety of neural models and show that taking into account the structure of the conversation improves predictive accuracy, exceeding that of feature-based models. We assess our best neural model in terms of both predictive accuracy and uncertainty by evaluating its behaviour when it is only exposed to the beginning of the conversation, finding that model accuracy improves and uncertainty reduces as models are exposed to more information.