Integrating Large Language Models and Knowledge Graphs to Capture Political Viewpoints in News Media

2025-12-16

AI Summary

This paper addresses the challenge of fine-grained political stance identification in news texts. Methodologically, it proposes a perspective classification framework integrating large language models (LLMs) with knowledge graphs, featuring a novel co-modeling mechanism that synergizes LLM long-context fine-tuning with Wikidata-based entity semantic enhancement, alongside hybrid human-AI annotation, semantically consistent perspective definitions, and a multi-module ensemble architecture. Key contributions include: (i) the first deep integration of Wikidata embeddings into LLM fine-tuning—significantly improving discrimination accuracy for ideological claims (e.g., stances on economic impacts of immigration); and (ii) an end-to-end classification pipeline supporting long-text understanding. Evaluated on a UK immigration discourse benchmark, the integrated approach achieves an F1 score of 89.6%, outperforming single-module baselines by 4.2 percentage points, thereby validating the efficacy of knowledge-guided LLM fine-tuning for political discourse analysis.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Argumentation

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

News sources play a central role in democratic societies by shaping political and social discourse through specific topics, viewpoints and voices. Understanding these dynamics is essential for assessing whether the media landscape offers a balanced and fair account of public debate. In earlier work, we introduced a pipeline that, given a news corpus, i) uses a hybrid human-machine approach to identify the range of viewpoints expressed about a given topic, and ii) classifies relevant claims with respect to the identified viewpoints, defined as sets of semantically and ideologically congruent claims (e.g., positions arguing that immigration positively impacts the UK economy). In this paper, we improve this pipeline by i) fine-tuning Large Language Models (LLMs) for viewpoint classification and ii) enriching claim representations with semantic descriptions of relevant actors drawn from Wikidata. We evaluate our approach against alternative solutions on a benchmark centred on the UK immigration debate. Results show that while both mechanisms independently improve classification performance, their integration yields the best results, particularly when using LLMs capable of processing long inputs.

Problem

• Integrating LLMs and knowledge graphs for viewpoint classification
• Improving classification of political viewpoints in news media
• Enhancing claim representation with semantic actor descriptions

Innovation

• Fine-tuned LLMs for viewpoint classification
• Enriched claim representations with Wikidata semantics
• Integrated LLMs and knowledge graphs for best performance