Can AI automatically analyze public opinion? A LLM agents-based agentic pipeline for timely public opinion analysis

TL;DR

This paper introduces an innovative LLM agents-based pipeline for automated, end-to-end public opinion analysis that is accessible, resource-efficient, and effective in real-world scenarios like the US-China tariff dispute.

Contribution

It presents the first fully automated LLM agents-based pipeline for multi-task public opinion analysis that requires no domain-specific training or manual annotation.

Findings

Successfully analyzed 1,572 Weibo posts in a case study.

Demonstrated relationships between public opinion and government decisions.

Provided a practical, low-cost framework for timely public opinion monitoring.

Abstract

This study proposes and implements the first LLM agents based agentic pipeline for multi task public opinion analysis. Unlike traditional methods, it offers an end-to-end, fully automated analytical workflow without requiring domain specific training data, manual annotation, or local deployment. The pipeline integrates advanced LLM capabilities into a low-cost, user-friendly framework suitable for resource constrained environments. It enables timely, integrated public opinion analysis through a single natural language query, making it accessible to non-expert users. To validate its effectiveness, the pipeline was applied to a real world case study of the 2025 U.S. China tariff dispute, where it analyzed 1,572 Weibo posts and generated a structured, multi part analytical report. The results demonstrate some relationships between public opinion and governmental decision-making. These contributions represent a novel advancement in applying generative AI to public governance, bridging the gap between technical sophistication and practical usability in public opinion monitoring.