DoubleH: Twitter User Stance Detection via Bipartite Graph Neural Networks

TL;DR

This paper introduces DoubleH, a bipartite graph neural network that effectively detects user stance on social media by leveraging both homogeneous and heterogeneous relationships in a large-scale dataset from the 2020 US presidential election.

Contribution

The paper proposes a novel bipartite GNN model, DoubleH, which better utilizes diverse social media relationships for stance detection, outperforming existing methods.

Findings

DoubleH outperforms state-of-the-art methods on benchmark datasets.

The model demonstrates stability and efficiency across different layer configurations.

Utilizes large-scale Twitter data with manually tagged hashtags for stance classification.

Abstract

Given the development and abundance of social media, studying the stance of social media users is a challenging and pressing issue. Social media users express their stance by posting tweets and retweeting. Therefore, the homogeneous relationship between users and the heterogeneous relationship between users and tweets are relevant for the stance detection task. Recently, graph neural networks (GNNs) have developed rapidly and have been applied to social media research. In this paper, we crawl a large-scale dataset of the 2020 US presidential election and automatically label all users by manually tagged hashtags. Subsequently, we propose a bipartite graph neural network model, DoubleH, which aims to better utilize homogeneous and heterogeneous information in user stance detection tasks. Specifically, we first construct a bipartite graph based on posting and retweeting relations for two kinds of nodes, including users and tweets. We then iteratively update the node's representation by extracting and separately processing heterogeneous and homogeneous information in the node's neighbors. Finally, the representations of user nodes are used for user stance classification. Experimental results show that DoubleH outperforms the state-of-the-art methods on popular benchmarks. Further analysis illustrates the model's utilization of information and demonstrates stability and efficiency at different numbers of layers.