Semantic profiling of user as an instrument of personalization in agricultural advisory systems

Yu.V. Rogushina

Abstract


The concept of semantic profiling of user as a key mechanism of personalization in intelligent agro-advisory systems is cosidered. We analysse classical profiling models (demographic, behavioral, cognitive, social) that do not provide sufficient flexibility and explainability, whereas ontological models enable the integration of heterogeneous data sources, the formalization of relations between user characteristics, and the assurance of semantic consistency. We propose a general algorithm for profile construction that combins static and dynamic parameters (identification, behavioral, cognitive, contextual) into a structured format that supports logical inference and alignment of user both with other subjects (e.g., selecting an advisor for a farmer) and objects (agrotechnologies, educational courses, support programs) of agroadvisory system. The advantages and problems of using the proposed approach are considered using the example. We analyze the advantages and challenges of the proposed approach on example of an intelligent ALE system focused on supporting the agroadvisor professional activities. Further research is planned to focus on the creation and alignment of ontological models of individual tasks and the practical validation of the approach within real world agro-advisory platforms. 

Problems in programming 2026; 3: 117-134


Keywords


ontological model; user profile; personalization; agroadvisory system

References


J. R. Anderson, Agricultural Advisory Services: In Agriculture and Rural Development Department. World Bank, Washington, DC, 2007.

R. Sharma, Artificial Intelligence in Agriculture: A Review. 5th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 2021, 937–942.

G. Farnadi, J. Tang, M. De Cock, & M.-F. Moens, User profiling through deep multimodal fusion, In: Proc. 11th ACMInt. Conf.Web Search Data Mining, Feb. 2018, 171-179.

Y. El Allioui, O. El Beqqali, User profie Ontology for the Personalization approach,'' In: Int. J. Comput. Appl., vol. 41, no. 4, pp. 31_40, Jan. 2012.

C. I., Eke, A. A., Norman, L., Shuib, & Nweke, H. F. (2019). A survey of user profiling: State-of-the-art, challenges, and solutions. IEEE Access, 7, 144907-144924.

M., Gao, K., Liu, & Z. Wu, Personalisation in web computing and informatics: Theories, techniques, applications, and future research. Information Systems Frontiers, 12(5), 2010, 607-629.

S., Gauch, M., Speretta, A., Chandramouli, & A. Micarelli, User profiles for personalized information access. The methods and adaptive strategies web personalization, 2007, 54-89.

E. J., Horvitz, J. S., Breese, D., Heckerman, D., Hovel, & K. Rommelse, The Lumiere project: Bayesian user modeling for inferring the goals and needs of software users. 2013, arXiv preprint arXiv:1301.7385.

G., Adomavicius, A. Tuzhilin, Expert-driven validation of rule-based user models in personalization applications. Data Mining and Knowledge Discovery, 5(1), 2001, 33-58.

Middleton, S. E., Shadbolt, N. R., & De Roure, D. C. (2004). Ontological user profiling in recommender systems. ACM Transactions on Information Systems (TOIS), 22(1), 54-88.

J. Rogushina, Fuzzy data in semantic Wiki resources: models, sources and processing methods. In: Problems in programming, (2), 2023, 67-83.

J. Rogushina, K. Yurchenko, Ontological modeling of adult learning ecosystem as a personalization tool. In: Problems programming, (4), 2025, 63-77.

FAO. 2023. Guide on digital agricultural extension and advisory services – Use of smartphone applications by smallholder farmers. Rome.

L. T. H., Sen, L. T. H., P., Chou, F. B., Dacuyan, Y., Nyberg, & J., Wetterlind, The opportunities and barriers in developing interactive digital extension services for smallholder farmers as a pathway to sustainable agriculture: A systematic review. Sustainability, 2025, 17(7), 3007.

European Commission. (2021). AKIS under the CAP Strategic Plans 2023–2027. Brussels.

L., Kranitz, T., Gal, & P. Goda, Multidimensional evaluation of Agricultural Knowledge and Innovation Systems. Studies in Agricultural Economics, 2025, 174-186.

ISO 19115-1:2014 Geographic information Metadata– Part 1: Fundamentals.

L., Hu, L., Di, & P. Yue, Design and Implementation of Geospatial Data Services for Agriculture. In: Agro-geoinformatics: Theory and Practice, 2021, 385-403. Cham: Springer International Publishing.

J., Rogushina, A., Gladun, S., Pryima, , O., Anishchenko & R. Valencia-Garcia, Semantic Expansion of Adult Student Profiles for Professional Support Tool for Andragogues. In International Conference on Technologies and Innovation, 2025, 80-100. Cham: Springer Nature Switzerland.

IMS Global Learning Consortium. IMS Learner Information Package Specification. 2001.

IEEE LTSC. Draft Standard for Learning Technology—Public and Private Information (PAPI) for Learners. IEEE Standards Association. 2001.

S., Weibe,l The Dublin Core: A simple content description model for the web. Journal of Electronic Publishing. 1999. Vol. 6, No 3.

Advanced Distributed Learning Initiative. Experience API Specification. 2013.

Dodds P. SCORM Explained. Advanced Distributed Learning. 2002.

J., Rogushina, A., Gladun, S., Pryima, , A., Savochka, Professionalization of agricultural advisers as andragogues: the role of chatbots. Institute of Pedagogical Education and Adult Education named after Ivan Zyazyun National Academy of Sciences of Ukraine, 357. [in Ukrainian].


Refbacks

  • There are currently no refbacks.