Llm Public Opinion Analytics

This is a production-ready public opinion monitoring system that scrapes 26 ranking lists across 15 Chinese platforms including Weibo, Bilibili, and Douyin, then runs LLM analysis on top. You get topic clustering, sentiment analysis, and automated alerts through WeChat Work, Telegram, or email. The architecture is solid: Scrapy for data collection, MySQL for storage, FastAPI for the web interface, and OpenAI-compatible APIs for analysis. It even handles video content extraction and includes keyboard shortcuts for crawler control. If you're monitoring Chinese social media trends or building a brand reputation system, this gives you the full stack. Setup requires some work with browser drivers and environment variables, but the documentation walks through database schemas and API endpoints clearly enough.

skills.sh installs: 1.7K
GitHub stars: 2
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/data-skills --skill llm-public-opinion-analytics --agent claude-code

Installs into .claude/skills of the current project.

Files

LLM-Based Public Opinion Analytics Assistant

Skill by ara.so — Data Skills collection.

Overview

This project is an intelligent public opinion analysis assistant that integrates real-time data from 15 mainstream platforms across 26 ranking lists with large language model (LLM) analysis capabilities. It provides conversational hot search queries, topic-specific searches, topic clustering, and sentiment analysis. The system supports: