This paper explores the design of an aspect-based sentiment analysis system using large language models (LLMs) for real-world use. We focus on quadruple opinion extraction -- identifying aspect categories, sentiment polarity, targets, and opinion expressions from text data across different domains and languages. Using internal datasets, we investigate whether a single fine-tuned model can effectively handle multiple domain-specific taxonomies simultaneously. We demonstrate that a combined multi-domain model achieves performance comparable to specialized single-domain models while reducing operational complexity. We also share lessons learned for handling non-extractive predictions and evaluating various failure modes when developing LLM-based systems for structured prediction tasks.
View on arXiv@article{white2025_2505.10389,
title={ Multi-domain Multilingual Sentiment Analysis in Industry: Predicting Aspect-based Opinion Quadruples },
author={ Benjamin White and Anastasia Shimorina },
journal={arXiv preprint arXiv:2505.10389},
year={ 2025 }
}