代理假设:从语义嵌入到有效的社会测量
The Proxy Presumption: From Semantic Embeddings to Valid Social Measures
AI总结:
本文提出Construct Validity Protocol,通过因果表示学习和心理测量学,提供从概念化到量化验证的严谨流程,利用Counterfactual Neutralization方法减少嵌入空间中的混淆因素,构建标准化的效度套件以提升社会测量的科学性。
摘要:
自然语言处理正迅速发展为计算社会科学的主要工具,研究者越来越多地使用嵌入来测量潜在构念如新颖性、创造力和偏见。然而,这一转变面临根本的效度挑战:'代理假设',即依赖几何属性(如余弦距离)作为社会概念的直接测量。我们主张在显式验证之前,无监督表示仍混杂了目标构念(C)和混淆属性(Z)如主题、风格和作者身份。为弥合语义嵌入与有效社会测量之间的差距,我们引入了构念效度协议(CVP)。借助因果表示学习和心理测量学,CVP提供了一个从概念化到量化验证的严谨流程。我们进一步提出反事实中性化,一种利用大语言模型(LLMs)在嵌入空间中减少混淆因素的新方法。通过提供标准化的效度套件——包括区分效度、增量效度和预测效度的测试——本文为社区提供了一套工具,将启发式代理转变为稳健、科学上可辩护的工具。
英文摘要:
Natural Language Processing is rapidly evolving into a primary instrument for Computational Social Science, with researchers increasingly using embeddings to measure latent constructs such as novelty, creativity, and bias. However, this transition faces a fundamental validity challenge: the ''Proxy Presumption,'' or the reliance on geometric properties (e.g., cosine distance) as direct measures of social concepts. We argue that without explicit validation, unsupervised representations remain entangled mixtures of the target construct ($C$) and confounding attributes ($Z$) like topic, style, and authorship. To bridge the gap between semantic embeddings and valid social measures, we introduce the Construct Validity Protocol (CVP). Drawing on causal representation learning and psychometrics, the CVP offers a rigorous pipeline from conceptualization to quantitative verification. We further propose Counterfactual Neutralization, a novel method using LLMs to reduce confounding in embedding space. By providing a standardized Validity Suite -- including tests for discriminant, incremental, and predictive validity -- this work offers the community a toolkit to transform heuristic proxies into robust, scientifically defensible instruments.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。