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

2025-05-16

AI Summary

Public opinion analysis in resource-constrained settings faces critical barriers—including dependence on labeled data, domain expertise, and local infrastructure—hindering accessibility for non-experts. Method: This paper introduces the first end-to-end, LLM-agent-based framework for automated public opinion analysis. It leverages zero-shot prompting, multi-stage task orchestration, and lightweight inference to enable non-expert users to initiate comprehensive analysis—including sentiment detection, topic evolution tracking, policy linkage, and data collection—via a single natural-language query. Contribution/Results: The framework eliminates the need for domain-specific training data, manual annotation, or local deployment, drastically lowering technical barriers. Evaluated on 1,572 Weibo posts from the 2025 U.S.–China tariff dispute, it autonomously generated structured, multidimensional reports that uncovered latent temporal associations between public discourse and governmental decision-making—bridging a key gap between generative AI capabilities and practical public governance applications.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Application Domains: Humanities & Computational Social Science
• Humans and AI: Voting

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
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

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.

Problem

• Automating public opinion analysis using LLM agents
• Enabling end-to-end analysis without domain-specific data
• Providing low-cost, accessible opinion monitoring for non-experts

Innovation

• LLM agents-based automated opinion analysis pipeline
• End-to-end workflow without domain-specific data
• Low-cost framework for resource-constrained environments