Multi-domain Multilingual Sentiment Analysis in Industry: Predicting Aspect-based Opinion Quadruples
This work addresses the need for efficient sentiment analysis in industry settings, though it is incremental as it builds on existing LLM methods for structured prediction.
The paper tackles the problem of aspect-based sentiment analysis across multiple domains and languages by designing a system that extracts opinion quadruples using large language models, achieving performance comparable to specialized single-domain models while reducing operational complexity.
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. 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.