Talking Point based Ideological Discourse Analysis in News Events

2025-04-10

AI Summary

Existing large language models (LLMs) struggle to identify ideologically driven elements underlying news narratives, particularly lacking the capacity to model relationships among entities, actors, media frames, and issues, and failing to integrate context essential for abstract ideological reasoning. Method: We propose the “Talking Points” relational representation framework—the first formalization of ideological discourse theory as a computable structure—integrating repetitive theme mining with partisan-aware clustering to generate ideology-specific viewpoints and support event-level snapshot visualization. Our approach combines relational modeling, multi-task classification, and human-in-the-loop validation. Contribution/Results: Experiments demonstrate significant improvements over LLM baselines on ideological and partisan classification tasks; human evaluation confirms viewpoint validity and interpretability. We publicly release annotated datasets and models to advance explainable, parseable research on news discourse.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Knowledge Representation and Reasoning: Reasoning with Beliefs
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Topic discovery and tracking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Analyzing ideological discourse even in the age of LLMs remains a challenge, as these models often struggle to capture the key elements that shape real-world narratives. Specifically, LLMs fail to focus on characteristic elements driving dominant discourses and lack the ability to integrate contextual information required for understanding abstract ideological views. To address these limitations, we propose a framework motivated by the theory of ideological discourse analysis to analyze news articles related to real-world events. Our framework represents the news articles using a relational structure - talking points, which captures the interaction between entities, their roles, and media frames along with a topic of discussion. It then constructs a vocabulary of repeating themes - prominent talking points, that are used to generate ideology-specific viewpoints (or partisan perspectives). We evaluate our framework's ability to generate these perspectives through automated tasks - ideology and partisan classification tasks, supplemented by human validation. Additionally, we demonstrate straightforward applicability of our framework in creating event snapshots, a visual way of interpreting event discourse. We release resulting dataset and model to the community to support further research.

Problem

• Analyzing ideological discourse in news using LLMs
• Identifying key elements shaping real-world narratives
• Generating ideology-specific viewpoints from news articles

Innovation

• Relational structure for news article representation
• Vocabulary of repeating themes generation
• Automated ideology and partisan classification