Journalism-Guided Agentic In-Context Learning for News Stance Detection
This addresses the problem of filter bubbles and polarization in news recommendations for Korean-language journalism by enabling viewpoint-aware systems, though it is incremental as it adapts in-context learning to a new domain and dataset.
The paper tackled stance detection in long-form Korean news articles by introducing K-News-Stance, a dataset with 2,000 articles and 21,650 segment-level annotations, and proposing JoA-ICL, a framework that uses a language model agent to predict segment stances and aggregate them, which outperformed existing methods.
As online news consumption grows, personalized recommendation systems have become integral to digital journalism. However, these systems risk reinforcing filter bubbles and political polarization by failing to incorporate diverse perspectives. Stance detection -- identifying a text's position on a target -- can help mitigate this by enabling viewpoint-aware recommendations and data-driven analyses of media bias. Yet, existing stance detection research remains largely limited to short texts and high-resource languages. To address these gaps, we introduce \textsc{K-News-Stance}, the first Korean dataset for article-level stance detection, comprising 2,000 news articles with article-level and 21,650 segment-level stance annotations across 47 societal issues. We also propose \textsc{JoA-ICL}, a \textbf{Jo}urnalism-guided \textbf{A}gentic \textbf{I}n-\textbf{C}ontext \textbf{L}earning framework that employs a language model agent to predict the stances of key structural segments (e.g., leads, quotations), which are then aggregated to infer the overall article stance. Experiments showed that \textsc{JoA-ICL} outperforms existing stance detection methods, highlighting the benefits of segment-level agency in capturing the overall position of long-form news articles. Two case studies further demonstrate its broader utility in promoting viewpoint diversity in news recommendations and uncovering patterns of media bias.