Zero-Shot Conversational Stance Detection: Dataset and Approaches

TL;DR

This paper introduces ZS-CSD, a large-scale dataset for zero-shot conversational stance detection, and proposes SITPCL, a novel model that achieves state-of-the-art results but still faces significant challenges in the zero-shot setting.

Contribution

The paper presents a new high-quality dataset ZS-CSD for zero-shot stance detection and a novel contrastive learning model SITPCL that advances the state-of-the-art.

Findings

SITPCL achieves an F1-macro score of 43.81%.

ZS-CSD contains 280 targets across two target types.

Zero-shot stance detection remains a challenging task.

Abstract

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.