首页 > AI前沿 > Making Political Text Scaling Comparable: Infrastructure and Hyperparameter Sensitivity for 17 Algorithms

Making Political Text Scaling Comparable: Infrastructure and Hyperparameter Sensitivity for 17 Algorithms

arXiv自然语言 2026-09-13 18:27 3 阅读 查看原文

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

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

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.