PartisanLens: A Multilingual Dataset of Hyperpartisan and Conspiratorial Immigration Narratives in European Media

2026-01-07

arXiv.org

AI Summary

This study addresses the paucity of systematic analyses of extreme partisanship and the “great replacement” conspiracy theory in European multilingual political discourse, as existing research has predominantly focused on English-language contexts. The authors construct the first multilingual dataset comprising 1,617 news headlines in Spanish, Italian, and Portuguese, annotated across multiple dimensions of political rhetoric. For the first time, they integrate socioeconomic and ideological profiles to guide large language models (LLMs) in simulating human annotation behavior from diverse political standpoints. By combining human-annotated benchmarks with automated classification, the project establishes a robust baseline to evaluate the capabilities and limitations of LLMs in detecting inflammatory narratives. The dataset and evaluation framework are publicly released to advance research on political discourse in European linguistic contexts.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Detecting hyperpartisan narratives and Population Replacement Conspiracy Theories (PRCT) is essential to addressing the spread of misinformation. These complex narratives pose a significant threat, as hyperpartisanship drives political polarisation and institutional distrust, while PRCTs directly motivate real-world extremist violence, making their identification critical for social cohesion and public safety. However, existing resources are scarce, predominantly English-centric, and often analyse hyperpartisanship, stance, and rhetorical bias in isolation rather than as interrelated aspects of political discourse. To bridge this gap, we introduce \textsc{PartisanLens}, the first multilingual dataset of \num{1617} hyperpartisan news headlines in Spanish, Italian, and Portuguese, annotated in multiple political discourse aspects. We first 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. In addition, we assess the viability of using LLMs as automatic annotators for this task, analysing their ability to approximate human annotation. Results highlight both their potential and current limitations. Next, moving beyond standard judgments, we explore whether LLMs can emulate human annotation patterns by conditioning them on socio-economic and ideological profiles that simulate annotator perspectives. At last, we provide our resources and evaluation, \textsc{PartisanLens} supports future research on detecting partisan and conspiratorial narratives in European contexts.

Problem

• hyperpartisan narratives
• Population Replacement Conspiracy Theories
• misinformation
• political polarisation
• multilingual dataset

Innovation

• multilingual dataset
• hyperpartisan narratives
• conspiracy theories
• large language models
• automatic annotation