DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis

2026-03-17

AI Summary

This work addresses the challenge of extracting aspect-category-opinion-sentiment-intensity (ACOSI) tuples for document-level fine-grained aspect-based sentiment intensity analysis (ABSIA) in informal texts. To tackle this complex task, the authors propose DanceHA, a multi-agent framework that decomposes the problem via a divide-and-conquer strategy, assigning specialized agents to subtasks and integrating human-in-the-loop collaboration to ensure high-quality annotation. The study introduces Inf-ABSIA, the first multi-domain document-level ABSIA dataset tailored for informal writing styles, and establishes a transferable multi-agent collaboration paradigm that combines large language model fine-tuning with knowledge distillation. Experimental results demonstrate that DanceHA significantly advances ABSIA performance, underscores the critical role of informal language in expressing sentiment intensity, and successfully transfers multi-agent knowledge to a lightweight student model.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Humans and AI: Human-AI Collaboration / Human-AI Teaming

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Aspect-Based Sentiment Intensity Analysis (ABSIA) has garnered increasing attention, though research largely focuses on domain-specific, sentence-level settings. In contrast, document-level ABSIA--particularly in addressing complex tasks like extracting Aspect-Category-Opinion-Sentiment-Intensity (ACOSI) tuples--remains underexplored. In this work, we introduce DanceHA, a multi-agent framework designed for open-ended, document-level ABSIA with informal writing styles. DanceHA has two main components: Dance, which employs a divide-and-conquer strategy to decompose the long-context ABSIA task into smaller, manageable sub-tasks for collaboration among specialized agents; and HA, Human-AI collaboration for annotation. We release Inf-ABSIA, a multi-domain document-level ABSIA dataset featuring fine-grained and high-accuracy labels from DanceHA. Extensive experiments demonstrate the effectiveness of our agentic framework and show that the multi-agent knowledge in DanceHA can be effectively transferred into student models. Our results highlight the importance of the overlooked informal styles in ABSIA, as they often intensify opinions tied to specific aspects.

Problem

• Aspect-Based Sentiment Intensity Analysis
• document-level ABSIA
• informal writing styles
• ACOSI tuples
• multi-agent framework

Innovation

• multi-agent framework
• document-level ABSIA
• aspect-based sentiment intensity analysis
• human-AI collaboration
• informal text