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

TL;DR

This paper enhances a news media analysis pipeline by integrating fine-tuned Large Language Models and Wikidata-based actor descriptions to better classify political viewpoints in news articles, especially in complex debates.

Contribution

It introduces a combined approach of LLM fine-tuning and semantic actor enrichment, improving viewpoint classification accuracy in news media analysis.

Findings

Combined methods outperform individual approaches.

Long-input capable LLMs yield better classification results.

Enrichment with Wikidata descriptions enhances semantic understanding.

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.