Mathieu Roche
Brett M. Drury- 1CIRAD, UMR TETIS, Montpellier, France
- 2TETIS, Univ. de Montpellier, AgroParisTech, CIRAD, INRAE, Montpellier, France
- 3Liverpool Hope University, Hope Park, Liverpool, United Kingdom
Editorial on the Research Topic
Semantics and natural language processing in agriculture
1 Introduction
The application of data science in agriculture enables the analysis of diverse datasets using methods such as machine learning, deep learning, computer vision, text mining (Drury and Roche, 2019), and large language models (LLMs) (Li et al., 2025; Shaikh et al., 2024). These techniques support tasks such as crop yield prediction and the early detection of plant and animal diseases by integrating heterogeneous data sources, including sensor readings, textual reports, satellite imagery, and plant images (Jabed et al., 2024). For practitioners and decision makers, data-driven insights provide a robust evidence base for promoting more efficient and sustainable agricultural practices (Rozenstein et al., 2024).
Within digital agriculture, the management of textual data and semantic information remains a major challenge. Semantics assigns unique identifiers to concepts, reducing ambiguity and enabling data integration across the agricultural value chain. This enhances interoperability and strengthens agricultural information systems. In this context, Agrisemantics has emerged as a dedicated field focusing on the application of semantic technologies in agriculture (Drury et al., 2019).
The urgency of this research is underscored by global challenges such as rising food prices, diminishing arable land due to climate change, and growing population pressures. This Research Topic brings together four contributions, including original research, brief reports, and data studies, each illustrating recent advances in semantics and text mining for agricultural applications.
2 Semantics and text mining studies
The Research Topic is organised into four principal themes: Semantics for Agri-food Systems, Semantic Analysis for Food Safety, Text Mining for Plant Health, and Lexicon Construction for Organic Residue Valorization. Each theme is represented by a single contribution.
2.1 Semantics for agri-food systems
Chaib et al. proposed a systematic methodology for developing agricultural ontologies by combining the Godet and MyChoice approaches. Drawing on stakeholder interviews and extending to complementary construction techniques, their study demonstrates the value of integrating multiple methodologies to enhance ontology design in agriculture.
2.2 Semantic analysis or food safety
Food safety remains a global concern, exemplified by incidents such as Operao Carne Fraca in Brazil and the 2008 Chinese Milk Scandal. However, even uncontaminated food products can generate perceptions of risk among consumers. Aline et al. investigated subjective consumer beliefs regarding the risks of infant food through a cross-national study. Their findings revealed intra-cultural variations in risk perception, providing insights that may inform governmental communication strategies to mitigate public concern.
2.3 Text mining for plant health
Addressing data sparsity in agricultural text classification, Jiang et al. utilised unlabelled data and Generative Adversarial Networks to fine-tune a pre-trained language model (PLM). Their approach achieved improved performance compared with traditional methods across multiple tasks. By reducing dependence on costly labelled datasets, this method lowers barriers to adopting text mining in agricultural research.
2.4 Lexicon construction for organic residue valorization
Rakotomalala et al. created a domain-specific lexicon to support research on organic residue valorization in developing countries. Combining expert knowledge with NLP techniques, the authors identified 2,079 relevant terms, which are publicly available (https://doi.org/10.18167/DVN1/HNZZSI). The lexicon has since enabled semantically driven analyses of a large corpus compiled from multiple scientific databases and repositories.
3 Conclusion
Text mining and semantic approaches are playing an increasingly significant role in agricultural research. Since the launch of this Research Topic, the contributions have collectively attracted more than 11,000 views. These studies also lay the groundwork for future applications of LLMs in addressing agricultural challenges (De et al., 2025; Li et al., 2025). The continued support of organizations such as GODAN (Global Open Data for Agriculture and Nutrition) and the FAO will be essential for advancing research that integrates semantics and text mining at the forefront of agricultural innovation and practice.
Author contributions
MR: Writing – original draft, Writing – review & editing. BD: Writing – original draft, Writing – review & editing.
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Generative AI statement
The author(s) declare that Gen AI was used in the creation of this manuscript. Generative AI was used to improve the grammar and writing style of the original text written by the author(s).
Any alternative text (alt text) provided alongside figures in this article has been generated by Frontiers with the support of artificial intelligence and reasonable efforts have been made to ensure accuracy, including review by the authors wherever possible. If you identify any issues, please contact us.
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
De, S., Sanyal, D. K., and Mukherjee, I. (2025). Fine-tuned encoder models with data augmentation beat chatgpt in agricultural named entity recognition and relation extraction. Expert Syst. Applic. 277:127126. doi: 10.1016/j.eswa.2025.127126
Drury, B., Fernandes, R., Moura, M.-F., and de Andrade Lopes, A. (2019). A survey of semantic web technology for agriculture. Inform. Process. Agric. 6, 487–501. doi: 10.1016/j.inpa.2019.02.001
Drury, B., and Roche, M. (2019). A survey of the applications of text mining for agriculture. Comput. Electr. Agric. 163:104864. doi: 10.1016/j.compag.2019.104864
Jabed, M., and Azmi Murad, M. A. (2024). Crop yield prediction in agriculture: a comprehensive review. Heliyon. 10:e40836. doi: 10.1016/j.heliyon.2024.e40836
Li, H., Wu, H., Li, Q., and Zhao, C. (2025). A review on enhancing agricultural intelligence with large language models. Artif. Intell. Agric. 15, 671–685. doi: 10.1016/j.aiia.2025.05.006
Rozenstein, O., Cohen, Y., Alchanatis, V., Behrendt, K., Bonfil, D. J., Eshel, G., et al. (2024). Data-driven agriculture and sustainable farming: friends or foes? Agric. Syst. 69–75. doi: 10.1163/9789004725232_007
Keywords: semantics, nlp, text mining, ontology, lexical resources
Citation: Roche M and Drury BM (2025) Editorial: Semantics and natural language processing in agriculture. Front. Artif. Intell. 8:1718114. doi: 10.3389/frai.2025.1718114
Received: 03 October 2025; Accepted: 03 November 2025;
Published: 25 November 2025.
Edited and reviewed by: Ruopu Li, Southern Illinois University Carbondale, United States
Copyright © 2025 Roche and Drury. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Brett M. Drury, ZHJ1cnliQGhvcGUuYWMudWs=