Language Independent Stance Detection: Social Interaction-based Embeddings and Large Language Models

TL;DR

This paper introduces a social interaction-based embedding method for stance detection that leverages social network data, significantly improving performance across multiple languages and datasets, and surpassing existing models.

Contribution

It proposes relational embeddings derived from social interactions, enhancing stance detection beyond text-based methods, and achieves state-of-the-art results on diverse datasets.

Findings

Relational embeddings improve stance detection accuracy.

Combining social interaction data with textual features outperforms LLM baselines.

Method achieves state-of-the-art results on seven datasets across four languages.

Abstract

The large majority of the research performed on stance detection has been focused on developing more or less sophisticated text classification systems, even when many benchmarks are based on social network data such as Twitter. This paper aims to take on the stance detection task by placing the emphasis not so much on the text itself but on the interaction data available on social networks. More specifically, we propose a new method to leverage social information such as friends and retweets by generating Relational Embeddings, namely, dense vector representations of interaction pairs. Our experiments on seven publicly available datasets and four different languages (Basque, Catalan, Italian, and Spanish) show that combining our relational embeddings with discriminative textual methods helps to substantially improve performance, obtaining state-of-the-art results for six out of seven evaluation settings, outperforming strong baselines based on Large Language Models, or other popular interaction-based approaches such as DeepWalk or node2vec.