Saved in:
Bibliographic Details
Main Authors: White, Benjamin, Shimorina, Anastasia
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.10389
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913943287496704
author White, Benjamin
Shimorina, Anastasia
author_facet White, Benjamin
Shimorina, Anastasia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10389
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-domain Multilingual Sentiment Analysis in Industry: Predicting Aspect-based Opinion Quadruples
White, Benjamin
Shimorina, Anastasia
Computation and Language
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.
title Multi-domain Multilingual Sentiment Analysis in Industry: Predicting Aspect-based Opinion Quadruples
topic Computation and Language
url https://arxiv.org/abs/2505.10389