STANCY: Stance Classification Based on Consistency Cues

TL;DR

This paper introduces a neural network model for stance classification that uses BERT representations combined with a novel consistency constraint, improving analysis of online claims and perspectives.

Contribution

The work presents a new stance classification model that incorporates a consistency constraint into BERT-based representations, enhancing performance on debate data.

Findings

Outperforms state-of-the-art baselines on Perspectrum dataset

Effective in capturing supporting and opposing perspectives

Demonstrates robustness across diverse online debate data

Abstract

Controversial claims are abundant in online media and discussion forums. A better understanding of such claims requires analyzing them from different perspectives. Stance classification is a necessary step for inferring these perspectives in terms of supporting or opposing the claim. In this work, we present a neural network model for stance classification leveraging BERT representations and augmenting them with a novel consistency constraint. Experiments on the Perspectrum dataset, consisting of claims and users' perspectives from various debate websites, demonstrate the effectiveness of our approach over state-of-the-art baselines.