Research Article
Food Derived Biostimulants Technology Revealed and Retrieved by Natural Language Processing
@ARTICLE{10.4108/eetsis.10654, author={Yoshiyuki Kobayashi and Kakeru Ota and Maya Iwano and Itsuki Kageyama and Kota Kodama and Kazuhiko Tsuda}, title={Food Derived Biostimulants Technology Revealed and Retrieved by Natural Language Processing}, journal={EAI Endorsed Transactions on Scalable Information Systems}, volume={12}, number={5}, publisher={EAI}, journal_a={SIS}, year={2025}, month={11}, keywords={Biostimulants, Sustainable agriculture, Health information science, Text mining, Patent analysis}, doi={10.4108/eetsis.10654} }- Yoshiyuki Kobayashi
Kakeru Ota
Maya Iwano
Itsuki Kageyama
Kota Kodama
Kazuhiko Tsuda
Year: 2025
Food Derived Biostimulants Technology Revealed and Retrieved by Natural Language Processing
SIS
EAI
DOI: 10.4108/eetsis.10654
Abstract
Food-derived biostimulants support sustainable agriculture; however, the scale and heterogeneity of the field hinder their synthesis. We profiled 2005–2025 innovation by mining 2,586 PATENTSCOPE filings and Web of Science articles; texts were analyzed with KH Coder and topic models, with large language models assisting in interpretation. Patent activity surged after 2018, emphasizing plant growth promotion, yield stability, and abiotic stress tolerance (amino acids, seaweed extracts, polyphenols, humic substances, and microbial consortia). In parallel, academic papers have shifted from descriptive trials to mechanism-level work on drought/salinity responses, gene expression, and metabolomics. Together, these signals outline a translation path in which deployable biological inputs converge with mechanistic evidence. Our NLP pipeline distilled heterogeneous texts into actionable indicators, yielding a reproducible map from patent/literature trends to testable hypotheses for formulation, dose, and seed stage delivery.
Copyright © Yoshiyuki Kobayashi et al., licensed to EAI. This is an open access article distributed under the terms of the CC BY NC SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
