Multi-domain Multilingual Sentiment Analysis in Industry: Predicting Aspect-based Opinion Quadruples

2025/05/15 by Benjamin W. White, White, Benjamin, Anastasia Shimorina +1
Computer Science · #Advanced Text Analysis Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Sentiment Analysis and Opinion Mining

paper · pdf · doi:10.48550/arxiv.2505.10389

openalex publication_date 2025/05/15 · openalex created_date 2025/10/15 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis
• Qwen2.5 Technical Report
• Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction
• BvSP: Broad-view Soft Prompting for Few-Shot Aspect Sentiment Quad Prediction
• BioXP-0.5B: Explainable Medical-AI via RL-GRPO
• MEMD-ABSA: A Multi-Element Multi-Domain Dataset for Aspect-Based Sentiment Analysis
• Reasoning Implicit Sentiment with Chain-of-Thought Prompting
• InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis
• Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure
• Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation
• Aspect Sentiment Quad Prediction as Paraphrase Generation
• A More Fine-Grained Aspect-Sentiment-Opinion Triplet Extraction Task
• Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis

Related

• Exploring Large Language Models for Multimodal Sentiment Analysis: Challenges, Benchmarks, and Future Directions
• Large language models for aspect-based sentiment analysis
• Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models
• From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models
• LLaMA-Based Models for Aspect-Based Sentiment Analysis