Stance detection is a subproblem of sentiment analysis, commonly defined as classifying the stance of a text toward a certain target: {Favor, Against, Neither}. As an important research problem, reliance on high-quality annotated data poses a significant challenge. However, in the real world, with the rapid development of social media, it is impossible to annotate the massive amount of text on diverse topics, a universal framework for stance detection is expected. Consequently, zero-shot stance detection methods that do not require annotated data have attracted researchers’ attention. In this survey, we review and introduce the early research and definition of stance detection, with a focus on summarizing the current research status of ZSSD, discuss datasets and the most advanced models. Finally, based on the above research, we explore possible future directions.