EUVIMEDEUVIMED entdecken
Crossref

Design and Evaluation of a Natural Language-Based Chatbot for Smart Farming Advisory Services

Mahesh Reddy Aenugu, Ramana Reddy N

Journals Fringe Multi-Engineering Proceedings · 2025

DOI: 10.69996/fmep.2025018 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journals Fringe Multi-Engineering Proceedings, 2025. Verfasst von Mahesh Reddy Aenugu und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Agricultural farming is the backbone of many economies, particularly in rural and developing regions, where it serves as the primary source of livelihood and food production. It involves the cultivation of crops and the rearing of animals to meet both local consumption and market demands. Farming practices vary widely based on climate, soil conditions, technology availability, and cultural traditions, ranging from traditional subsistence farming to modern, mechanized agriculture. This research paper presents the development and evaluation of an intelligent Agriculture Assistant Chatbot designed to support farmers by providing real-time, accurate, and relevant agricultural information through natural language interaction. The chatbot leverages n-gram-based Natural Language Processing (NLP) to understand user queries, identify intent, and extract key entities related to crops, fertilizers, and farming practices. Built with a user-friendly interface and integrated with expert knowledge and a feedback-driven learning mechanism, the system enhances communication between farmers and agricultural advisory services. The architecture allows for multilingual support and incorporates modules for crop and fertilizer details, user registration, and sentiment-based feedback analysis. Experimental results show that out of a total of 83 registered users, 56 users actively logged in, and 62 successful bot interactions were recorded, indicating a strong engagement rate of approximately 74.7%. User satisfaction metrics, derived from the feedback system, showed that 60% of users rated their experience as very positive, 25% expressed neutral sentiment, while only 15% provided negative feedback. Furthermore, analysis of problem-solving efficiency demonstrated that the chatbot-assisted queries had a resolution success rate increase of over 40% compared to those without bot interaction. Response time was consistently below 2 seconds on average, contributing to a seamless user experience.

Zitieren

APA

Aenugu, M. R., & N, R. R. (2025). Design and Evaluation of a Natural Language-Based Chatbot for Smart Farming Advisory Services. Journals Fringe Multi-Engineering Proceedings. https://doi.org/10.69996/fmep.2025018

Vancouver

Aenugu MR, N RR. Design and Evaluation of a Natural Language-Based Chatbot for Smart Farming Advisory Services. Journals Fringe Multi-Engineering Proceedings. 2025. doi:10.69996/fmep.2025018

BibTeX
@article{Aenugu2025,
  author = {Aenugu, Mahesh Reddy and N, Ramana Reddy},
  title = {Design and Evaluation of a Natural Language-Based Chatbot for Smart Farming Advisory Services},
  journal = {Journals Fringe Multi-Engineering Proceedings},
  year = {2025},
  doi = {10.69996/fmep.2025018}
}
Kostenlos starten →