用大模型量化政客对对手的敌意，揭示政党精英对立的新维度。
Elite Polarization in European Parliamentary Speeches: a Novel Measurement Approach Using Large Language Models
- 基于大模型识别议会发言中的政治人物与攻击对象，计算跨党派负面情绪。
- 在英、匈、意三国数据中验证，该方法误差仅约量表范围的10%。
- 可跨语言、免训练，适合大规模跨国比较研究，尤其适合关注政治极化的学者。
民主稳定、民粹主义与政党体系危机理论常指向一种少有直接测量的极化形式：政治精英间的敌对关系。现有比较研究多捕捉大众情感极化或精英意识形态距离，却未衡量政党间定向的相互评价。本文提出「精英极化得分」，通过大语言模型识别议会辩论中提及的政治人物，提取发言者-目标配对，估算针对各目标的语气倾向，将异质引用统一为政党二元关系，并聚合生成政党及议会层级的互相对立负面情绪度量。该方法在英国、匈牙利和意大利议会语料库上验证，涵盖长达四十年的辩论记录。结果表明，该度量在概念上区别于大众情感极化、精英意识形态极化、不文明言论、负面竞选及总体情绪。英国案例显示其亦与上述三者无显著相关。极端负面评价可用于定位有害极化话语。三国验证显示无误报发现，语气估计误差约为量表范围的10%，且在两项设置中，人工智能敏感度达到或超过人工标注者水平。算法支持多语言、无需任务微调，可按政党与季度聚合，为未来跨国研究精英极化的成因及其影响提供可扩展基础。
原文摘要 · Abstract (English)
Theories of democratic stability, populism, and party-system crisis often point to a form of polarization that comparative research rarely measures directly: hostile relations among political elites. Existing comparative measures capture adjacent phenomena, including mass affective polarization, or elite ideological distance, but not directed mutual elite evaluation. This paper introduces the Elite Polarization Score, a measurement of out-party evaluations in parliamentary speech. Large Language Models identify political actors mentioned in parliamentary debates, recover speaker-target pairs, estimate the sentiment directed at each actor, standardize heterogeneous references into party dyads, and aggregate these evaluations into party- and parliament-level measures of mutual out-party negativity. The validity of the approach is demonstrated on parliamentary corpora from the United Kingdom, Hungary, and Italy, covering up to four decades of debate. The resulting measure is conceptually distinct from mass affective polarization, elite ideological polarization, incivility, negative campaigning, and general sentiment. Evidence from the UK case study shows that it is also empirically distinct from mass affective polarization, elite ideological polarization, and incivility. Extreme negative evaluations can also be used to locate pernicious polarization rhetoric. Validation across three countries finds no false discoveries, sentiment estimates accurate to roughly 10 percent of the scale range, and AI sensitivity that meets or exceeds that of human coders in two of three settings. Because the algorithm is multilingual, requires no task-specific training, and can be aggregated by party and quarter, it provides a scalable basis for future cross-national research on what produces elite polarization and what elite polarization itself produces
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。