This paper introduces "Semantic Scaling," a novel method for ideal point estimation from text. I leverage large language models to classify documents based on their expressed stances and extract survey-like data. I then use item response theory to scale subjects from these data. Semantic Scaling significantly improves on existing text-based scaling methods, and allows researchers to explicitly define the ideological dimensions they measure. This represents the first scaling approach that allows such flexibility outside of survey instruments and opens new avenues of inquiry for populations difficult to survey. Additionally, it works with documents of varying length, and produces valid estimates of both mass and elite ideology. I demonstrate that the method can differentiate between policy preferences and in-group/out-group affect. Among the public, Semantic Scaling out-preforms Tweetscores according to human judgement; in Congress, it recaptures the first dimension DW-NOMINATE while allowing for greater flexibility in resolving construct validity challenges.

本文介绍了一种名为“语义缩放”的新方法，用于从文本中进行理想点估计。利用大规模语言模型根据表达的立场对文档进行分类，并提取类似调查的数据。然后使用项目反应理论对这些数据进行尺度化处理。语义缩放显著改进了现有的基于文本的尺度化方法，并允许研究人员明确定义他们所测量的意识形态维度。这是首个在调查工具之外提供此种灵活性的尺度化方法，为难以进行调查的人群开辟了新的研究途径。此外，它适用于不同长度的文档，并生成对大众和精英意识形态的有效估计。作者证明该方法能区分政策偏好和内外群体情感，并根据人类判断在公众中表现出更好的效果。在国会中，它重新捕捉到了第一维DW-NOMINATE，并在解决构建效度挑战方面具有更大的灵活性。

语义缩放：使用大型语言模型的贝叶斯理想点估计