Estimating Nutrient Composition of Packaged Foods Using Natural Language Processing and Optimization Modeling

Mélina Côté, Wiam Hamadi, Catherine Laramée, Sonia Pomerleau, Véronique Provencher, Christian Gagné, Benoît Lamarche · 2026

Read Estimating Nutrient Composition of Packaged Foods Using Natural Language Processing and Optimization Modeling by Mélina Côté, Wiam Hamadi, Catherine Laramée, Sonia Pomerleau, Véronique Provencher, Christian Gagné, Benoît Lamarche (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13310631.txt.

Description

Mélina Côté and colleagues rebuild in 2026 the full nutrient makeup of packaged foods from their labels and ingredient lists, filling a gap in food data banks that mostly cover generic items. The data covered 5,371 packaged products sold in Québec across 17 categories. A language algorithm matched each ingredient to its closest entry in the national nutrient file.

A maths model then solved for ingredient shares that match the declared label values. Over half the ingredients matched their data bank matches with high closeness scores. Median error stayed under twenty percent for energy and the ten label nutrients, within the leeway rule-makers accept for labels. Six food categories did strongly, while three categories gave poor figures on several nutrients. Complete profiles for packaged foods would sharpen dietary studies, since such products supply nearly half the energy in many countries.

Catalog record

CREATORMélina Côté, Wiam Hamadi, Catherine Laramée, Sonia Pomerleau, Véronique Provencher, Christian Gagné, Benoît Lamarche
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE59 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13310631

Browse the full library · About the Tower of Babel