MT2-CSD: A New Dataset and Multi-Semantic Knowledge Fusion Method for Conversational Stance Detection

TL;DR

This paper introduces MT2-CSD, the largest multi-turn conversational stance detection dataset, and proposes LLM-CRAN, a model leveraging large language models to improve understanding and detection of stance in social media discussions.

Contribution

The paper presents the MT2-CSD dataset for multi-turn conversational stance detection and introduces LLM-CRAN, a novel model that utilizes LLM reasoning for enhanced performance.

Findings

LLM-CRAN outperforms baseline models in stance detection accuracy.

MT2-CSD is the largest dataset for multi-turn conversational stance detection.

The dataset presents new challenges for stance detection models.

Abstract

In the realm of contemporary social media, automatic stance detection is pivotal for opinion mining, as it synthesizes and examines user perspectives on contentious topics to uncover prevailing trends and sentiments. Traditional stance detection research often targets individual instances, thereby limiting its capacity to model multi-party discussions typical in real social media scenarios. This shortcoming largely stems from the scarcity of datasets that authentically capture the dynamics of social media interactions, hindering advancements in conversational stance detection. In this paper, we introduce MT2-CSD, a comprehensive dataset for multi-target, multi-turn conversational stance detection. To the best of our knowledge, MT2-CSD is the largest dataset available for this purpose, comprising 24,457 annotated instances and exhibiting the greatest conversational depth, thereby presenting new challenges for stance detection. To address these challenges, we propose the Large Language model enhanced Conversational Relational Attention Network (LLM-CRAN), which exploits the reasoning capabilities of LLMs to improve conversational understanding. We conduct extensive experiments to evaluate the efficacy of LLM-CRAN on the MT2-CSD dataset. The experimental results indicate that LLM-CRAN significantly outperforms strong baseline models in the task of conversational stance detection.