Modeling Deliberative Argumentation Strategies on Wikipedia
Modeling Deliberative Argumentation Strategies on Wikipedia
复制标题
DOI：
10.18653/v1/p18-1237
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Khalid Al Khatib;Henning Wachsmuth;Kevin Lang;J. Herpel;Matthias Hagen;Benno Stein
中科院分区：
文献类型：
--
作者：
Khalid Al Khatib;Henning Wachsmuth;Kevin Lang;J. Herpel;Matthias Hagen;Benno Stein
本文研究了参与者在协商讨论中的论证策略如何得到计算支持。我们的最终目标是预测每个参与者的最佳下一个审议举动。在本文中，我们提出了一个审议讨论的模型，并说明了其运营化。先前的模型是根据一小部分讨论手动构建的，从而导致了不适合移动建议的抽象水平。相比之下，我们从统计学上得出模型，可用于移动描述的几种类型的元数据。我们的方法适用于Wikipedia Talk Pages的600万个讨论，我们的方法沿着三个维度的13个类别进行了模型：话语行为，辩论关系和框架。在此基础上，我们会自动生成一个大约200,000圈的语料库，标记为13个类别。然后，我们使用三个监督分类器对模型进行操作，并提供证据表明可以预测所提出的类别。
This paper studies how the argumentation strategies of participants in deliberative discussions can be supported computationally. Our ultimate goal is to predict the best next deliberative move of each participant. In this paper, we present a model for deliberative discussions and we illustrate its operationalization. Previous models have been built manually based on a small set of discussions, resulting in a level of abstraction that is not suitable for move recommendation. In contrast, we derive our model statistically from several types of metadata that can be used for move description. Applied to six million discussions from Wikipedia talk pages, our approach results in a model with 13 categories along three dimensions: discourse acts, argumentative relations, and frames. On this basis, we automatically generate a corpus with about 200,000 turns, labeled for the 13 categories. We then operationalize the model with three supervised classifiers and provide evidence that the proposed categories can be predicted.