Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

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.

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

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.
Paper Structure (14 sections, 1 equation, 3 figures, 6 tables, 1 algorithm)

This paper contains 14 sections, 1 equation, 3 figures, 6 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Dataset Construction
  4. Method
  5. Dance: Divide-and-Conquer Teamwork for Document-level ABSIA
  6. HA: Human-AI Collaboration for Annotation
  7. Knowledge Distillation with Reasoning Chain
  8. Evaluation Methods
  9. Experiments
  10. Experimental Setting and Details
  11. Results
  12. Conclusion
  13. Limitations
  14. Acknowledgments

Figures (3)

  • Figure 1: Overview of DanceHA, consisting of two key components: (1) Dance (Divide-and-Conquer Teamwork) for open-ended document-level ABSIA and (2) HA (Human-AI collaboration) for label annotation. Figure \ref{['fig:Dance_case']} illustrates Dance with an example.
  • Figure 2: An example of Dance for document-level ABSIA.
  • Figure 3: SIS scores for ACOSI tuples with informal and formal styles among different baselines. Error bars indicate standard deviation score. Results demonstrate the influence of informal styles on sentiment intensity and the capability of advanced models to interpret informal expressions.