Zero-Shot Conversational Stance Detection: Dataset and Approaches
This addresses the challenge of detecting stances in online debates for unseen targets, which is crucial for real-world social media applications, though it is incremental as it builds on existing conversational stance detection work.
The authors tackled the problem of conversational stance detection for unseen targets by creating a large-scale zero-shot dataset (ZS-CSD) with 280 targets and proposing a model (SITPCL) that achieves state-of-the-art performance, with an F1-macro score of 43.81%.
Stance detection, which aims to identify public opinion towards specific targets using social media data, is an important yet challenging task. With the increasing number of online debates among social media users, conversational stance detection has become a crucial research area. However, existing conversational stance detection datasets are restricted to a limited set of specific targets, which constrains the effectiveness of stance detection models when encountering a large number of unseen targets in real-world applications. To bridge this gap, we manually curate a large-scale, high-quality zero-shot conversational stance detection dataset, named ZS-CSD, comprising 280 targets across two distinct target types. Leveraging the ZS-CSD dataset, we propose SITPCL, a speaker interaction and target-aware prototypical contrastive learning model, and establish the benchmark performance in the zero-shot setting. Experimental results demonstrate that our proposed SITPCL model achieves state-of-the-art performance in zero-shot conversational stance detection. Notably, the SITPCL model attains only an F1-macro score of 43.81%, highlighting the persistent challenges in zero-shot conversational stance detection.