Problem
Research questions and friction points this paper is trying to address.
Lack structured investigation of perceived news intent
Need framework for understanding news intent applications
Improve fake news detection using intent analysis
Understanding News Creation Intents: Frame, Dataset, and Method
🤖 AI Summary
News intent research has long suffered from a lack of structured theoretical frameworks and empirical foundations, leading to a deviation from public-interest orientation. To address this, we propose NINT—the first interdisciplinary (philosophy/psychology/cognitive science)-driven, componential framework for news intent understanding—formally defining the intent identification task. We construct the first fine-grained, human-annotated news intent dataset featuring multidimensional intent categories, and design intent-aware representation learning and supervised baselines. Empirically, NINT achieves a +12.3% F1-score improvement over prior methods in intent classification. Moreover, it demonstrates strong generalization and interpretability in downstream tasks—including fake news detection and stance analysis—thereby advancing news intent research from qualitative discourse toward a systematic, modelable, and evaluable paradigm.
📝 Abstract
As the disruptive changes in the media economy and the proliferation of alternative news media outlets, news intent has progressively deviated from ethical standards that serve the public interest. News intent refers to the purpose or intention behind the creation of a news article. While the significance of research on news intent has been widely acknowledged, the absence of a systematic news intent understanding framework hinders further exploration of news intent and its downstream applications. To bridge this gap, we propose News INTent (NINT) frame, the first component-aware formalism for understanding the news creation intent based on research in philosophy, psychology, and cognitive science. Within this frame, we define the news intent identification task and provide a benchmark dataset with fine-grained labels along with an efficient benchmark method. Experiments demonstrate that NINT is beneficial in both the intent identification task and downstream tasks that demand a profound understanding of news. This work marks a foundational step towards a more systematic exploration of news creation intents.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Conceptual deconstruction-based news intent framework
New intent perception dataset creation
Intent assistance improves fake news detection
🔎 Similar Papers
No similar papers found.
