A SHAP-Enhanced Voice-Based Conversational Agent for Agriculture Using BERT

Year : 2026 | Volume : 17 | Issue : 01 | Page : 94 102
By

Sirapani D,

Revathi J,

Ramadevi C,

  1. Student, Department of EEE, St. Joseph’s College of Engineering, Tamil Nadu, India
  2. Student, Department of EEE, St. Joseph’s College of Engineering, Tamil Nadu, India
  3. Assistant Professor, Department of EEE, St. Joseph’s College of Engineering, Tamil Nadu, India

Abstract

The integration of advanced artificial intelligence technologies into modern agriculture has become increasingly important for narrowing the persistent knowledge gap faced by farmers, especially in regions with limited access to expert advisory services. While state-of-the-art language models such as BERT (Bidirectional Encoder Representations from Transformers) demonstrate exceptional performance in understanding and generating natural language, their opaque “black box” nature often limits user confidence, trust, and widespread adoption. Farmers may hesitate to rely on recommendations when the reasoning behind system responses is unclear or difficult to interpret. To address this challenge, this paper presents a novel voice-enabled conversational agent specifically designed for the agricultural domain, built on a fine-tuned BERT model capable of accurately understanding and answering complex, context-rich farming queries. To overcome transparency and trust barriers, the proposed system integrates SHAP (SHapley Additive exPlanations), a widely recognized Explainable Artificial Intelligence (XAI) technique. SHAP provides clear, post-hoc explanations for each prediction by highlighting the key words and phrases that influenced the model’s response. This enables farmers to verify and understand the logic behind the advice provided, thereby fostering confidence in the system. Additionally, the conversational agent incorporates a voice-based interface that supports local languages, making it accessible to users with varying literacy levels. By combining robust natural language understanding, explainable reasoning, and user-friendly voice interaction, the system functions as a dependable digital advisory assistant. Ultimately, this approach has the potential to enhance decision-making, boost agricultural productivity, and support sustainable farming practices.

Keywords: Agriculture, BERT, conversational agent, explainable AI (XAI), natural language processing (NLP), SHAP, voice interface

[This article belongs to Journal of Computer Technology & Applications ]

How to cite this article: Sirapani D, Revathi J, Ramadevi C. A SHAP-Enhanced Voice-Based Conversational Agent for Agriculture Using BERT. Journal of Computer Technology & Applications. 2026; 17(01):94-102.
How to cite this URL: Sirapani D, Revathi J, Ramadevi C. A SHAP-Enhanced Voice-Based Conversational Agent for Agriculture Using BERT. Journal of Computer Technology & Applications. 2026; 17(01):94-102. Available from: https://journals.stmjournals.com/jocta/article=2026/view=260442

References

  1. Devlin J, Chang MW, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. In: Proc NAACL-HLT; 2019 Jun. p. 4171–4186.
  2. Sarkar S, Babar MF, Hassan MM, Hasan M, Karmaker Santu SK. Processing natural language on embedded devices: how well do transformer models perform? In: Proc ACM/SPEC Int Conf Perform Eng; 2024 May 7. p. 211–222.
  3. Chen H, Jiao F, Li X, Qin C, Ravaut M, Zhao R, et al. ChatGPT’s one-year anniversary: are open-source large language models catching up? arXiv. 2023;arXiv:2311.16989.
  4. Wang D, Liu C, Zhao Z, Shen S, Liu L, Li B, et al. GujiBERT and GujiGPT: construction of intelligent information processing foundation language models for ancient texts. arXiv. 2023;arXiv:2307.05354.
  5. Chen T, Lv L, Wang D, Zhang J, Yang Y, Zhao Z, et al. Revolutionizing agrifood systems with artificial intelligence: a survey. arXiv. 2023;arXiv:2305.01899.
  6. Usip PU, Udo EN, Asuquo DE, James OR. A machine learning-based mobile chatbot for crop farmers. In: Proc Int Conf Electron Gov Emerg Technol; 2022 Sep 12. p. 192–211.
  7. Gardezi M, Joshi B, Rizzo DM, Ryan M, Prutzer E, Brugler S, et al. Artificial intelligence in farming: challenges and opportunities for building trust. Agron J. 2024;116(3):1217–1228.
  8. Min W, Zhou P, Xu L, Liu T, Li T, Huang M, et al. From plate to production: artificial intelligence in modern consumer-driven food systems. arXiv. 2023;arXiv:2311.02400.
  9. Salih AM, Raisi-Estabragh Z, Galazzo IB, Radeva P, Petersen SE, Lekadir K, et al. A perspective on explainable artificial intelligence methods: SHAP and LIME. Adv Intell Syst. 2025;7(1):2400304.
  10. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30.
  11. Zhao H, Chen H, Yang F, Liu N, Deng H, Cai H, et al. Explainability for large language models: a survey. ACM Trans Intell Syst Technol. 2024;15(2):1–38.
  12. Vainio-Pekka H, Agbese MO, Jantunen M, Vakkuri V, Mikkonen T, Rousi R, et al. The role of explainable AI in the research field of AI ethics. ACM Trans Interact Intell Syst. 2023;13(4):1–39.
  13. Qasim M, Zia HB, Athar A, Habib T, Raza AA. Personalized weather information for low-literate farmers using multimodal dialog systems. Int J Speech Technol. 2021;24(2):455–471.
  14. Pratap V, Tjandra A, Shi B, Tomasello P, Babu A, Kundu S, et al. Scaling speech technology to 1,000+ languages. J Mach Learn Res. 2024;25(97):1–52.
  15. Ngulube P. Leveraging information and communication technologies for sustainable agriculture and environmental protection among smallholder farmers in tropical Africa. Discover Environ. 2025;3(1):9
Regular Issue Subscription Original Research
Volume 17
Issue 01
Received 18/12/2025
Accepted 07/01/2026
Published 20/02/2026
Publication Time 64 Days

Login

My IP

PlumX Metrics

Support