SARC: Sentiment-Augmented Deep Role Clustering for Fake News Detection

TL;DR

SARC, a Sentiment-Augmented Role Clustering framework which utilizes sentiment-enhanced deep clustering to identify user roles for improved fake news detection and proposes a joint optimization objective integrating role clustering and fake news detection to further improve the model performance.

Abstract

Fake news detection has been a long-standing research focus in social networks. Recent studies suggest that incorporating sentiment information from both news content and user comments can enhance detection performance. However, existing approaches typically treat sentiment features as auxiliary signals, overlooking role differentiation, that is, the same sentiment polarity may originate from users with distinct roles, thereby limiting their ability to capture nuanced patterns for effective detection. To address this issue, we propose SARC, a Sentiment-Augmented Role Clustering framework which utilizes sentiment-enhanced deep clustering to identify user roles for improved fake news detection. The framework first generates user features through joint comment text representation (with BiGRU and Attention mechanism) and sentiment encoding. It then constructs a differentiable deep clustering module to automatically categorize user roles. Finally, unlike existing approaches which take fake news label as the unique supervision signal, we propose a joint optimization objective integrating role clustering and fake news detection to further improve the model performance. Experimental results on two benchmark datasets, RumourEval-19 and Weibo-comp, demonstrate that SARC achieves superior performance across all metrics compared to baseline models. The code is available at: https://github.com/jxshang/SARC.

Figures (11)

• Figure 1: Motivational example showing two pieces of fake news and user comments from the Weibo-comp dataset.
• Figure 2: The proposed SARC framework which consists of four components: (1) Initial Feature Representation Module, (2) Text encoding module, (3) User Role Clustering Module, (4) News Classification Module.
• Figure 3: Performance comparison of SARC and its variant models on the RumourEval-19 dataset.
• Figure 4: Performance comparison of SARC and its variant models on the Weibo-comp dataset.
• Figure 5: The impact of parameter $k$ on model performance.