[논문 리뷰] Cross-National Evidence of Disproportionate Media Visibility for the Radical Right in the 2024 European Elections

Íris Damião, João Franco외 4명|arXiv (Cornell University)|2026. 01. 09.

Social Media and Politics인용 수 0

한 줄 요약

본 논문은 다섯 개의 유럽 국가에 걸친 약 21,500건의 온라인 뉴스 기사를 체계적으로 분석하여 Radical Right가 선거 성과에 비해 언론 노출이 불균형적으로 높았음을 보이고, 이러한 패턴은 국가 간에 일관되며 선거 마지막 캠페인 주에 더욱 확대되었다.

ABSTRACT

This study provides a systematic comparative analysis of media visibility of different political families during the 2024 European Parliament elections. We analyzed close to 21,500 unique news from leading national outlets in Austria, Germany, Ireland, Poland, and Portugal - countries with diverse political contexts and levels of media trust. Combining computational and human classification, we identified parties, political leaders, and groups from the article's URLs and titles, and clustered them according to European Parliament political families and broad political leanings. Cross-country comparison shows that the Mainstream and the Radical Right were mentioned more often than the other political groups. Moreover, the Radical Right received disproportionate attention relative to electoral results (from 2019 or 2024) and electoral projections, particularly in Austria, Germany, and Ireland. This imbalance increased in the final weeks of the campaign, when media influence on undecided voters is greatest. Outlet-level analysis shows that coverage of right-leaning entities dominated across news sources, especially those generating the highest traffic, suggesting a structural rather than outlet-specific pattern. Media visibility is a central resource, and this systematic mapping of online coverage highlights how traditional media can contribute to structural asymmetries in democratic competition.

연구 동기 및 목표

• Assess how media visibility of political families varies across five European countries ahead of the 2024 European Parliament elections.
• Identify which political leanings are most mentioned in online news and how this correlates with electoral results and polls.
• Map national parties to European parliamentary groups and broad ideological leanings to compare cross-country patterns.

제안 방법

• Build a comprehensive online news database using Media Cloud for Austria, Ireland, Germany, Poland, and Portugal during the two months before the 2024 EU elections.
• Identify political entities (politicians, parties, leanings) in headlines and URLs via large-language-model extraction (ChatGPT-4o) and fuzzy matching, followed by manual validation.
• Map national parties to 2019–2024 European Parliament groups and to 10 ideological categories, then aggregate mentions by five broad leanings: Radical Left, Mainstream Left, Greens, Mainstream Right, Radical Right.
• Compute country-level proportions of mentions by leaning and create weighted average across countries based on seats.
• Compare mention frequencies with 2019 results, pre-election polling, and 2024 results; assess deviations by standard deviation thresholds.

Figure 2: Methodological Pipeline - News Collection. Media Sources were selected from Semrush Top 20 Newspapers for each country and excluding social media and search engine pages (e.g., “YouTube.com”). News articles were collected from these sources using two sets of queries (yellow and blue), deri

실험 결과

연구 질문

• RQ1 What is the distribution of media mentions across five broad political leanings in each country during the 2024 EU elections?
• RQ2 Do Radical Right entities receive disproportionate media attention relative to prior representation or expected electoral performance, and does this vary by country and over time?
• RQ3 How does media visibility relate to electoral results and polling, and are there cross-country patterns suggesting structural media biases?
• RQ4 How robust is the leanings classification when mapping national parties to European Parliament groups and to broader ideological categories?

주요 결과

• Radical Right entities were mentioned more often than other groups across countries, with disproportionate attention relative to 2019 and 2024 results.
• The Radical Right emerged as the most frequently mentioned segment even in Ireland, where it had no parliamentary representation.
• Coverage dominated by right-leaning entities across outlets and countries, especially among high-traffic sources, indicating a structural pattern rather than outlet-specific bias.
• The disproportionate visibility intensified in the final weeks of the campaign when media influence on undecided voters is greatest.
• The study analyzed 21,528 news items from top outlets in five countries, using a combined LLM and fuzzy-matching approach with manual validation to identify political entities and align them with European groups and ideologies.

Figure 3: Methodological Pipeline - Entities Extraction. A) All news headlines and their respective URLs were processed using the ChatGPT-4o API to identify political entities – such as politicians (e.g., Hildergard Bentele), political parties (e.g., AfD), and political leanings (e.g., the left). B)