Proposing a Conceptual Framework for Automated Extraction of Farmers Requirements from Persian Text Using Large Language Models
Proposing a Conceptual Framework for Automated Extraction of Farmers Requirements from Persian Text Using Large Language Models
Hosein Tanabi1
1) PhD student in software engineering, Islamic Azad University, Babol Branch
IOI Code
:
ABFF-ABDHFK
Publication :
9th International Congress of Developing Agriculture, Natural Resources, Environment and Tourism of Iran(9icsda.ir)
Abstract :
The adoption of technological solutions in agriculture is directly contingent upon their alignment with the real needs of farmers. Traditional requirements elicitation methods are incapable of processing the vast volume of informal textual data generated by farmers on platforms such as instant messaging applications and social networks. This research proposes a conceptual framework based on Large Language Models (LLMs) for the automated extraction, classification, and prioritization of farmers requirements from Persian text. By leveraging the natural language processing capabilities of LLMs, the proposed framework demonstrates the feasibility of transitioning from unstructured data to structured requirements. The output of this framework—comprising functional requirements, non-functional requirements, and trust-building specifications—can serve as an evidence-based foundation for the design and improvement of agricultural software and platforms. By creating a bridge between farmers needs and technical solutions, this research takes a step toward the development of more user-friendly and effective digital tools in support of sustainable agriculture.
Keywords : large language models requirements extraction digital agriculture persian natural language processing conceptual framework intelligent needs assessment