Stance detection is an important task, supporting many downstream tasks such as discourse parsing and modeling the propagation of fake news, rumors, and science denial. In this paper, we propose a novel framework for stance detection. Our framework is unsupervised and domain-independent. Given a claim and a multi-participant discussion - we construct the interaction network from which we derive topological embedding for each speaker. These speaker embedding enjoy the following property: speakers with the same stance tend to be represented by similar vectors, while antipodal vectors represent speakers with opposing stances. These embedding are then used to divide the speakers into stance-partitions. We evaluate our method on three different datasets from different platforms. Our method outperforms or is comparable with supervised models while providing confidence levels for its output. Furthermore, we demonstrate how the structural embedding relate to the valence expressed by the speakers. Finally, we discuss some limitations inherent to the framework.
翻译:发现Stance是一项重要任务,它支持许多下游任务,如对话分析和传播假新闻、流言和科学否定的模型等。在本文中,我们提出一个新的姿态探测框架。我们的框架不受监督,不受域上独立。根据一个主张和多参与者的讨论,我们构建互动网络,我们从中为每个发言者提供地形嵌入。这些嵌入的发言者享有以下属性:持相同立场的发言者往往由类似的矢量代表,而具有相同立场的抗药媒介则代表持相反立场的发言者。然后,这些嵌入被用来将发言者分为立场分裂。我们评估我们在不同平台的三个不同数据集上的方法。我们的方法优于或与监督模型相仿,同时为其产出提供信任度。此外,我们展示了结构嵌入与发言者表达的价值之间的关系。最后,我们讨论了框架固有的一些限制。