Stance detection for online public opinion awareness: An overview

Abstract

Stance detection, which focuses on users' deep attitudes, is an important way to understand the online public opinion. This paper presents an overview of stance detection. First, we present a general framework for stance detection, and the main steps of the framework are introduced in detail. The state‐of‐the‐art stance detection methods are categorized into three classes: feature‐based methods, deep learning‐based methods, and ensemble learning‐based methods. Moreover, the advantages and limitations of the existing methods are analyzed. The survey findings show that hybrid‐neural network‐based methods are superior to the other methods. In addition, existing methods still need to pay more attention to the sentiment information, user‐interaction, and attempt to merge more external knowledge to help improve the effect of stance detection.

Few-Shot Learning for Cross-Target Stance Detection by Aggregating Multimodal Embeddings

“…Despite a substantial body of research in stance detection in recent years [15], [6], [16], the more challenging task of cross-target stance detection has received less attention. One of the first approaches to cross-target stance detection is Bicond [17], which combined multiple layers of LSTM models in different settings encoding the texts from left to right and from right to left.…”

Dynamic Stance: Modeling Discussions by Labeling the Interactions

“…Stance has been modeled extensively as a static task in which a text is tagged with respect to its attitude towards a specific topic or target (Mohammad et al, 2016;Küçük and Can, 2020;Cao et al, 2022). Methods for stance classification have evolved alongside the developments in Natural Language Processing, moving away from feature-based approaches up to fine-tuning and prompting pretrained models (Ferreira and Vlachos, 2016;Aker et al, 2017;Fang et al, 2019;Zhang et al, 2020;Allaway and McKeown, 2020;Zheng et al, 2022b, among others).…”