A Survey on Stance Detection for Mis- and Disinformation Identification
Momchil Hardalov1,2 Arnav Arora1,3 Preslav Nakov1,4 Isabelle Augenstein1,3 1Checkstep Research 2Sofia University “St. Kliment Ohridski”, Bulgaria 3University of Copenhagen, Denmark 4Qatar Computing Research Institute, HBKU, Doha, Qatar {momchil, arnav, preslav.nakov,
Abstract
Understanding attitudes expressed in texts, also known as stance detection, plays an important role in systems for detecting false information online, be it misinformation (unintentionally false) or disinformation (intentionally false information). Stance detection has been framed in different ways, including (a) as a component of fact-checking, rumour detection, and detecting previously fact-checked claims, or (b) as a task in its own right. While there have been prior efforts to contrast stance detection with other related tasks such as argumentation mining and sentiment analysis, there is no existing survey on examining the relationship between stance detection and mis- and disinformation detection. Here, we aim to bridge this gap by reviewing and analysing existing work in this area, with mis- and disinformation in focus, and discussing lessons learnt and future challenges.
中文速览
网络上虚假信息泛滥，自动判断一段文字对某个说法持"支持""反对"还是"中立"态度——即立场检测（stance detection）——被认为是核实谣言、辅助事实核查的关键技术，但学界此前从未系统梳理它与虚假信息检测之间的关系。这篇综述填补了这一空白，全面回顾了立场检测在事实核查、谣言识别、虚假新闻判别等场景中的任务定义、公开数据集和建模方法，既涵盖"把立场检测本身当作真假判定"的直接用法，也涵盖"把立场作为流水线中一个组件"的间接用法。梳理结果显示，早期方法依赖人工特征，近年来预训练语言模型大幅提升了性能，但跨语言覆盖不足、标注体系不统一、可解释性欠缺等问题仍制约着实际应用。这项工作为研究者提供了清晰的任务全景图，指出了现有方法的局限，并为未来在多语言、多模态和更强鲁棒性方向上的探索提供了路线参考。
原文 arXiv:2103.00242;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2103.00242v3