Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces VFStance, a novel approach for article-level news stance detection that utilizes image generation to enhance the visibility of implicit stance cues within complex news texts. By leveraging visual framing, VFStance significantly improves stance detection performance compared to existing methods, as evidenced by evaluation experiments. Additionally, a user study with 200 participants shows that VFStance effectively makes stance signals more salient in snippet-based news consumption, suggesting broader applications beyond automated detection.
Visual framing can transform implicit news stances into explicit signals, enhancing detection accuracy and user comprehension.
Article-level news stance detection aims to identify the perspective of news articles toward social issues. Despite advances in stance detection and its importance for trustworthy media environments, news articles pose distinct challenges because their stances are often implicit, subtly conveyed through journalistic framing, and embedded in long, structurally complex texts. To address these challenges, we introduce VFStance, which leverages visual framing to make implicit stance cues more explicit via image generation. In evaluation experiments, we demonstrate the effectiveness of VFStance over existing methods and the contribution of visual framing to its performance. Finally, a controlled user study (N=200) in a snippet-based news consumption setting further demonstrates that VFStance can make stance signals visually salient and highlights its potential use beyond automated stance detection.