Social media platforms are rich sources of opinionated content. Stance detection allows the automatic extraction of users' opinions on various topics from such content. We focus on zero-shot stance detection, where the model's success relies on (a) having knowledge about the target topic; and (b) learning general reasoning strategies that can be employed for new topics. We present Stance Reasoner, an approach to zero-shot stance detection on social media that leverages explicit reasoning over background knowledge to guide the model's inference about the document's stance on a target. Specifically, our method uses a pre-trained language model as a source of world knowledge, with the chain-of-thought in-context learning approach to generate intermediate reasoning steps. Stance Reasoner outperforms the current state-of-the-art models on 3 Twitter datasets, including fully supervised models. It can better generalize across targets, while at the same time providing explicit and interpretable explanations for its predictions.

翻译：社交媒体平台是观点性内容的丰富来源。立场检测技术能够从这类内容中自动提取用户对各种话题的观点。我们聚焦于零样本立场检测，该场景下模型成功依赖于：(a) 具备目标话题的相关知识；(b) 学习可应用于新话题的通用推理策略。我们提出立场推理器——一种基于显式背景知识推理的社交媒体零样本立场检测方法，该方法通过引导模型对文档在目标话题上的立场进行推理。具体而言，我们的方法利用预训练语言模型作为世界知识来源，采用思维链上下文学习范式生成中间推理步骤。立场推理器在三个推特数据集上（包括全监督模型）均超越了当前最先进模型。该方法不仅能更好地实现跨目标泛化，同时为其预测提供显式且可解释的推理说明。