Weibo analysis system for monitoring public sentiment
Top 99.6% on SourcePulse
This system monitors, analyzes, and predicts public opinion trends on social media, specifically Weibo. It targets governments, enterprises, and researchers needing to understand public sentiment, respond to events, and optimize decision-making by processing large volumes of social media data. The system offers real-time data collection, sentiment analysis, topic classification, and trend prediction.
How It Works
The system employs a modular architecture built on Flask, utilizing Scrapy for real-time data collection via web scraping. Preprocessing involves Jieba for Chinese text segmentation and stop word removal. Sentiment analysis is performed using SnowNLP, while BERT models handle topic classification. Advanced AI capabilities are integrated via API keys for OpenAI (GPT), Anthropic (Claude), and DeepSeek models, enabling sophisticated text analysis and prediction. Data is stored in a MySQL database, and results are visualized using Matplotlib.
Quick Start & Requirements
git clone https://github.com/666ghj/Weibo_PublicOpinion_AnalysisSystem.git
followed by pip install -r requirements.txt
.config.py
for MySQL and set environment variables for AI API keys. Start the Flask app with python app.py
.http://localhost:5000
.Highlighted Details
Maintenance & Community
The project welcomes contributions via pull requests. Contact is available through GitHub Issues or email (670939375@qq.com).
Licensing & Compatibility
Licensed under GPL-2.0. This license may impose copyleft restrictions, requiring derivative works to also be open-sourced under the same license, potentially impacting commercial or closed-source integration.
Limitations & Caveats
The system's reliance on a Weibo account for data collection and external AI API keys for advanced features introduces dependencies that could be subject to platform changes or costs. The GPL-2.0 license may restrict its use in proprietary software.
18 hours ago
1 day