SocialED:A Python Library for Social Event Detection

What is Social Event Detection?
Social Event Detection (SED) is a cutting-edge research area in AI and NLP that focuses on:

🔍 Automatically identifying and analyzing events from social media platforms (Twitter, Facebook, etc.)
🌎 Covering diverse event types from natural disasters to viral phenomena
🤖 Leveraging AI to understand real-world events through social data

You can find it from https://github.com/RingBDStack/SocialED
About SocialED
SocialED is your all-in-one Python toolkit for Social Event Detection that offers:

📊 Rich Resources
19 detection algorithms
14 diverse datasets
Unified API with detailed documentation
🛠️ Key Capabilities
Comprehensive preprocessing (graph construction, tokenization)
Standardized interfaces for training & prediction
Easy-to-extend modular architecture
⚡ Technical Excellence
Deep learning framework integration
CPU & GPU support for high performance
Production-grade code quality with testing & CI/CD
Key Features
🤖 Comprehensive Algorithm Collection: Integrates 19 detection algorithms and supports 14 widely-used datasets, with continuous updates to include emerging methods
📝 Unified API Design: Implements algorithms with a consistent interface, allowing seamless data preparation and integration across all models
🔧 Modular Components: Provides customizable components for each algorithm, enabling users to adjust models to specific needs
🛠️ Rich Utility Functions: Offers tools designed to simplify the construction of social event detection workflows
✨ Robust Implementation: Includes comprehensive documentation, examples, unit tests, and maintainability features
SocialED includes 19 social event detection algorithms. For consistency and accessibility, SocialED is developed on top of DGL and PyTorch, and follows the API design of PyOD and PyGOD. See examples below for detecting outliers with SocialED in 7 lines!

SocialED plays a crucial role in various downstream applications, including:

Crisis management
Public opinion monitoring
Fake news detection
And more...

@misc{zhang2024socialedpythonlibrarysocial,
title={SocialED: A Python Library for Social Event Detection},
author={Kun Zhang and Xiaoyan Yu and Pu Li and Hao Peng and Philip S. Yu},
year={2024},
eprint={2412.13472},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2412.13472},
}