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

• URL: http://arxiv.org/abs/2512.14887v1
• Date: Tue, 16 Dec 2025 20:10:55 GMT
• Title: Integrating Large Language Models and Knowledge Graphs to Capture Political Viewpoints in News Media
• Authors: Massimiliano Fadda, Enrico Motta, Francesco Osborne, Diego Reforgiato Recupero, Angelo Salatino,
• Abstract summary: We develop a pipeline to identify the range of viewpoints expressed about a given topic.<n>We also enrich claim representations with semantic descriptions drawn from Wikidata.<n>We evaluate our approach against alternative solutions on a benchmark centred on the UK immigration debate.
• Score: 3.509771256227556
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• PartisanLens: A Multilingual Dataset of Hyperpartisan and Conspiratorial Immigration Narratives in European Media [5.72412714580848]
  We introduce textscPartisanLens, the first multilingual dataset of num1617 hyperpartisan news headlines in Spanish, Italian, and Portuguese.<n>We evaluate the classification performance of widely used Large Language Models (LLMs) on this dataset, establishing robust baselines for the classification of hyperpartisan and PRCT narratives.<n>At last, we provide our resources and evaluation, textscPartisanLens supports future research on detecting partisan and conspiratorial narratives in European contexts.
  arXiv  Detail & Related papers  (2026-01-07T12:18:14Z)
• Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy [59.44168425139687]
  BayesVLA is a Bayesian factorization that decomposes the policy into a visual-action prior, supporting seeing-to-act, and a language-conditioned likelihood, enabling prompt-to-specify.<n>Experiments show superior generalization to unseen instructions, objects, and environments compared to existing methods.
  arXiv  Detail & Related papers  (2025-12-12T01:59:23Z)
• Latent Topic Synthesis: Leveraging LLMs for Electoral Ad Analysis [51.95395936342771]
  We introduce an end-to-end framework for automatically generating an interpretable topic taxonomy from an unlabeled corpus.<n>We apply this framework to a large corpus of Meta political ads from the month ahead of the 2024 U.S. Presidential election.<n>Our approach uncovers latent discourse structures, synthesizes semantically rich topic labels, and annotates topics with moral framing dimensions.
  arXiv  Detail & Related papers  (2025-10-16T20:30:20Z)
• Talking Point based Ideological Discourse Analysis in News Events [62.18747509565779]
  We propose a framework motivated by the theory of ideological discourse analysis to analyze news articles related to real-world events.<n>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.<n>We evaluate our framework's ability to generate these perspectives through automated tasks - ideology and partisan classification tasks, supplemented by human validation.
  arXiv  Detail & Related papers  (2025-04-10T02:52:34Z)
• "Whose Side Are You On?" Estimating Ideology of Political and News Content Using Large Language Models and Few-shot Demonstration Selection [5.277598111323805]
  Existing approaches to classifying ideology are limited in that they require extensive human effort, the labeling of large datasets, and are not able to adapt to evolving ideological contexts.<n>This paper explores the potential of Large Language Models for classifying the political ideology of online content in the context of the two-party US political spectrum through in-context learning.
  arXiv  Detail & Related papers  (2025-03-23T02:32:25Z)
• Synchronization between media followers and political supporters during an election process: towards a real time study [0.18749305679160366]
  We present an analysis of the dynamics of discussions in Twitter (before it became X) among supporters of various candidates in the 2022 French presidential election.<n>Our study demonstrates that we can automatically detect the synchronization of interest among different groups around specific topics at particular times.
  arXiv  Detail & Related papers  (2025-03-07T16:25:58Z)
• Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models [0.08246494848934444]
  We focus on dialogues within Tunisian social networks during the Coronavirus Pandemic and other notable themes like sports and politics. We start by aggregating a varied multilingual corpus of comments relevant to these subjects. We then introduce our No-English-to-English Machine Translation approach to handle linguistic differences.
  arXiv  Detail & Related papers  (2024-03-18T00:01:10Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems [133.13117064357425]
  We propose a new evaluation metric GRADE, which stands for Graph-enhanced Representations for Automatic Dialogue Evaluation. Specifically, GRADE incorporates both coarse-grained utterance-level contextualized representations and fine-grained topic-level graph representations to evaluate dialogue coherence. Experimental results show that our GRADE significantly outperforms other state-of-the-art metrics on measuring diverse dialogue models.
  arXiv  Detail & Related papers  (2020-10-08T14:07:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.