← Back to Publications List
Understanding Pesticide Effectiveness Through Transformer-Based Sentiment Analysis: A Comparative Study of BERT and RoBERTa
Students & Supervisors
Student Authors
Foysal Ahmed Neloy
Bachelor of Science in Computer Science & Engineering, FST
Faiza Mahmood Aroni
Bachelor of Science in Computer Science & Engineering, FST
Chayti Rani Mondal
Bachelor of Science in Computer Science & Engineering, FST
Supervisors
Prof. Dr. Kamruddin Nur
Professor, Faculty, FST
Aminun Nahar
Assistant Professor, Faculty, FST
Abstract
Pesticides are a necessity in modern agriculture, but safety issues suggest that decisions need to be rational as well. This study deploys a dataset from Mendeley to do transformer based sentiment analysis of online pesticide reviews. The analysis was performed with text cleaning and sentiment classification into positive, neutral, and negative by BERT and RoBERTa models. Results showed that RoBERTa outperformed BERT with 97.3% accuracy and 99.3% AUC. This study provides a benchmark for transformer-based sentiment analysis of pesticide reviews and shows how RoBERTa can be used to extract actionable insights for sustainable pesticide management.
Keywords
Sentiment analysis
Transformer model
BERT
RoBERTa
Pesticide review
Agricultural NLP
Publication Details
- DOI: 10.1109/QPAIN69676.2026.11545684
- Type of Publication:
- Conference Name: 2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking
- Date of Conference: 16/04/2026 - 16/04/2026
- Venue: Chittagong University of Engineering and Technology (CUET), Chattogram, Bangladesh.