An NLP Crosswalk Between the Common Core State Standards and NAEP Item Specifications

TL;DR

The paper develops an NLP-based crosswalk that maps CCSS to NAEP item specifications for grade 4 mathematics, leveraging embedding vectors to quantify semantic similarity and a hybrid regression to capture multivariate coverage. By applying VSURF feature selection followed by hierarchical regression, it derives unique variance contributions (via $R^2$) to assess how well CCSS aligns with NAEP specifications, revealing concentration of coverage in fractions-related domains. The findings show potential for NLP to streamline content-mapping workflows and to provide quantitative guidance for SME deliberations, while cautioning that crosswalks can be unbalanced and should not be used to over-interpret instructional impact or policy inferences. Overall, the approach offers a practical, low-cost toolkit for crosswalks and contributes to understanding semantic versus substantive alignment between standards and assessment specifications within educational measurement.

Abstract

Natural language processing (NLP) is rapidly developing for applications in educational assessment. In this paper, I describe an NLP-based procedure that can be used to support subject matter experts in establishing a crosswalk between item specifications and content standards. This paper extends recent work by proposing and demonstrating the use of multivariate similarity based on embedding vectors for sentences or texts. In particular, a hybrid regression procedure is demonstrated for establishing the match of each content standard to multiple item specifications. The procedure is used to evaluate the match of the Common Core State Standards (CCSS) for mathematics at grade 4 to the corresponding item specifications for the 2026 National Assessment of Educational Progress (NAEP).