Readability of U.S. food handler training materials: A natural language processing analysis of worker study guides and the federal Food Code

This archive contains the analysis code and computed results for the study "Readability of U.S. Food Handler Training Materials: A Natural Language Processing Analysis of Worker Study Guides and the Federal Food Code" by Morris Brako and Anirudh R. Naig (Iowa State University). The study used a natural language processing pipeline to measure the reading difficulty of six U.S. food safety documents: the 2022 FDA Food Code and five worker-facing food handler study guides from Oregon and California. For each document it computed five readability indices, complex-word percentage, lexical density, and full sentence-length distributions, and it compared the federal code with the pooled worker guides at the sentence level. The archive includes four documented Python scripts (corpus download, readability analysis, sentence-level statistical tests, and figure generation), the computed result files, and the two manuscript figures. The analyzed source documents are public records issued by U.S. federal, state, and county authorities and are referenced by URL rather than redistributed. Running the included scripts reproduces all reported metrics, tests, and figures. See README.md for full instructions and source links.