Deep Learning in Stance Detection: A Survey

The analysis of an author’s perspective on a given topic within text presents a challenging problem in natural language processing. Stance detection, or the identification of an author’s inclination either in favor, against, or neutral toward some target entity, is an important classification task in this context. Significant progress has been made in stance detection, especially facilitated by deep learning. This survey explores these approaches as applied to the vanilla stance detection problem, as well as its sub-problems, including cross-target, cross-domain, multi-target, cross-lingual, and multi-lingual stance detection. We also overview methods leveraging deep learning for zero- and few-shot learning-based stance detection. The survey also overview generative large language models for stance detection and highlights various research opportunities, including devising models to improve cross-domain learning, advancing models for implicit stance detection, enhancing explainability in stance detection models, addressing scalability and computational cost challenges, and accommodating evolving stance labels.