发表机构
LMU Munich（慕尼黑大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文通过大规模比较实验，论证CT-IPE方法应视为可配置测量管道，并量化17种算法的超参数敏感性，发现多数算法对配置不敏感，敏感性集中于少数关键选择。
AI 中文摘要
基于计算文本的理想点估计（CT-IPE）方法通常作为命名算法进行比较，然而应用这些方法涉及众多研究者选择，这些选择决定了政治文本如何转化为立场估计。本文认为，CT-IPE方法应被理解为可配置的测量管道，而非固定的估计器。基于一项涵盖17种CT-IPE算法、5,537次实验运行和约425万个左右立场估计的大规模比较实验，我描述了使这些异构方法能够联合执行的共享基础设施，并量化了其估计对替代超参数选择的敏感程度。方差分解和基于SHAP的敏感性分析表明，对于大多数算法，超参数配置通过共享位移解释的残差方差很小：17种算法中有13种的ICC值低于0.10。在存在这种配置级敏感性的情况下，其集中于少数几个关键的研究者选择，最显著的是底层语言或嵌入模型的选择、锚定构念的种子关键词列表以及主题数量。
英文摘要
Computational text-based ideal point estimation (CT-IPE) methods are usually compared as named algorithms, yet applying them involves numerous researcher choices that configure how political text is turned into position estimates. This paper argues that CT-IPE methods are better understood as configurable measurement pipelines than as fixed estimators. Building on a large-scale comparative experiment spanning 17 CT-IPE algorithms, 5,537 experimental runs, and approximately 4.25 million left-right position estimates, I describe the shared infrastructure that makes these heterogeneous methods jointly executable and quantify how sensitive their estimates are to alternative hyperparameter choices. Variance-partitioning and SHAP-based sensitivity analyses show that, for most algorithms, hyperparameter profiles explain little residual variance through a shared shift: 13 of the 17 algorithms exhibit ICC values below .10. Where this profile-level sensitivity is present, it is concentrated in a small number of consequential researcher choices, most notably the selection of the underlying language or embedding model, the seed keyword lists that anchor the construct, and the number of topics.
CommentsAccepted for the 6th edition of the workshop on Computational Linguistics for the Political and Social Sciences (CPSS)
