Zero-Shot Stance Detection via Sentiment-Stance Contrastive Learning

Zero-shot stance detection (ZSSD) is an important research problem that requires algorithms to have good stance detection capability even for unseen targets. In general, stance features can be grouped into two types: target-invariant and target-specific. Target-invariant features express the same stance regardless of the targets they are associated with, and such features are general and transferable. On the contrary, targetspecific features will only be directly associated with specific targets. Therefore, it is crucial to effectively mine target-invariant features in texts in ZSSD. In this paper, we develop a method based on contrastive learning to mine certain transferable targetinvariant expression features in texts from two dimensions of sentiment and stance and then generalize them to unseen targets. Specifically, we first grouped all texts into several types in terms of two orthogonal dimensions: sentiment polarity and stance polarity. Then we devise a supervised contrastive learningbased strategy to capture each type's common and transferable expressive features. Finally, we fuse the above-mentioned expressive features with the semantic features of the original texts about specific targets to deal with the stance detection for unseen targets. Extensive experiments on three benchmark datasets show that our proposed model achieves the state-of-theart performance on most datasets. Code and other resources are available on GitHub (1).