Recognising Agreement and Disagreement between Stances with Reason Comparing Networks

TL;DR

This paper introduces a reason comparing network (RCN) that leverages reasoning behind stance statements to improve detection of agreement and disagreement in non-dialogic utterances, outperforming existing methods.

Contribution

The paper extends stance agreement detection to non-dialogic utterances by incorporating reason comparison, a novel approach that improves accuracy over previous dialog-focused methods.

Findings

RCN outperforms baseline models in stance (dis)agreement detection

Reason comparison effectively captures backing for stance decisions

Method demonstrates robustness on a well-known stance corpus

Abstract

We identify agreement and disagreement between utterances that express stances towards a topic of discussion. Existing methods focus mainly on conversational settings, where dialogic features are used for (dis)agreement inference. We extend this scope and seek to detect stance (dis)agreement in a broader setting, where independent stance-bearing utterances, which prevail in many stance corpora and real-world scenarios, are compared. To cope with such non-dialogic utterances, we find that the reasons uttered to back up a specific stance can help predict stance (dis)agreements. We propose a reason comparing network (RCN) to leverage reason information for stance comparison. Empirical results on a well-known stance corpus show that our method can discover useful reason information, enabling it to outperform several baselines in stance (dis)agreement detection.