Applying Natural Language Processing to U.S. Food Retail Data to Categorize Foods by Level of Processing
AgEcon Search (University of Minnesota, USA) · 26.07.2026
DOI: 10.22004/ag.econ.404883 ↗Kurz gefasst
Fachartikel in der Zeitschrift AgEcon Search (University of Minnesota, USA), erschienen am 26.07.2026. Verfasst von Mariah D. Ehmke und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Differentiating food products by level of industrial food processing is essential to measuring relationships among food processing, food demand, and public health. The Circana (formerly known as IRI) scanner data lacks identified measures of food product processing, but contains other food product descriptors that can be used to predict the processing of food products. This report specifies procedures to use Natural Language Processing with a Naïve Bayes model in Python’s scikit-learn to efficiently classify retail food purchases by level of food processing according to the NOVA food classification system. This method accurately predicts NOVA classification 94 percent using only the food item descriptions as predictors. Based on this classification we find 60 percent of retail food sales to be ultraprocessed in 2023, an increase from 55 percent in 2020.
Schlagwörter
Zitieren
APA
Ehmke, M. D., Okrent, A. M., Awad, K., McCluskey, J. J., & Restrepo, B. (2026). Applying Natural Language Processing to U.S. Food Retail Data to Categorize Foods by Level of Processing. AgEcon Search (University of Minnesota, USA). https://doi.org/10.22004/ag.econ.404883
Vancouver
Ehmke MD, Okrent AM, Awad K, McCluskey JJ, Restrepo B. Applying Natural Language Processing to U.S. Food Retail Data to Categorize Foods by Level of Processing. AgEcon Search (University of Minnesota, USA). 2026. doi:10.22004/ag.econ.404883
BibTeX
@article{Ehmke2026,
author = {Ehmke, Mariah D. and Okrent, Abigail Mary and Awad, Koroles and McCluskey, Jill J. and Restrepo, Brandon},
title = {Applying Natural Language Processing to U.S. Food Retail Data to Categorize Foods by Level of Processing},
journal = {AgEcon Search (University of Minnesota, USA)},
year = {2026},
doi = {10.22004/ag.econ.404883}
}
EUVIMED