Disentangled VAD Representations via a Variational Framework for Political Stance Detection

TL;DR

This paper introduces PoliStance-VAE, a variational autoencoder-based framework that disentangles emotional features from political discourse to improve stance detection accuracy and interpretability.

Contribution

It presents a novel VAE-based approach that explicitly models VAD emotional features for stance detection, outperforming existing models on benchmark datasets.

Findings

Achieves state-of-the-art results on P-STANCE and SemEval-2016 datasets.

Effectively disentangles emotional features for better interpretability.

Surpasses models like BERT, BERTweet, and GPT-4o in performance.

Abstract

The stance detection task aims to categorise the stance regarding specified targets. Current methods face challenges in effectively integrating sentiment information for stance detection. Moreover, the role of highly granular sentiment labelling in stance detection has been largely overlooked. This study presents a novel stance detection framework utilizing a variational autoencoder (VAE) to disentangle latent emotional features-value, arousal, and dominance (VAD)-from political discourse on social media. This approach addresses limitations in current methods, particularly in in-target and cross-target stance detection scenarios. This research uses an advanced emotional annotation tool to annotate seven-class sentiment labels for P-STANCE. Evaluations on benchmark datasets, including P-STANCE and SemEval-2016, reveal that PoliStance-VAE achieves state-of-the-art performance, surpassing models like BERT, BERTweet, and GPT-4o. PoliStance-VAE offers a robust and interpretable solution for stance detection, demonstrating the effectiveness of integrating nuanced emotional representations. This framework paves the way for advancements in natural language processing tasks, particularly those requiring detailed emotional understanding.