Research

Paper

AI LLM March 17, 2026

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

Authors

Lei Wang, Min Huang, Eduard Dragut

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.

Metadata

arXiv ID: 2603.16546
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-17
Fetched: 2026-03-18 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.16546v1</id>\n    <title>DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis</title>\n    <updated>2026-03-17T14:11:07Z</updated>\n    <link href='https://arxiv.org/abs/2603.16546v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.16546v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-17T14:11:07Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <arxiv:journal_ref>AAAI 2026</arxiv:journal_ref>\n    <author>\n      <name>Lei Wang</name>\n    </author>\n    <author>\n      <name>Min Huang</name>\n    </author>\n    <author>\n      <name>Eduard Dragut</name>\n    </author>\n  </entry>"
}