Effective and Unsupervised Social Event Detection and Evolution via RAG and Structural Entropy

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Qitong, Peng, Hao, Li, Zuchen, Meng, Xihang, Yang, Ziyu, Li, Jiting, Sun, Li, Yu, Philip S.
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909993354133504
author Liu, Qitong
Peng, Hao
Li, Zuchen
Meng, Xihang
Yang, Ziyu
Li, Jiting
Sun, Li
Yu, Philip S.
author_facet Liu, Qitong
Peng, Hao
Li, Zuchen
Meng, Xihang
Yang, Ziyu
Li, Jiting
Sun, Li
Yu, Philip S.
contents With the growing scale of social media, social event detection and evolution modeling have attracted increasing attention. Graph neural networks (GNNs) and transformer-based pre-trained language models (PLMs) have become mainstream approaches in this area. However, existing methods still face three major challenges. First, the sheer volume of social media messages makes learning resource-intensive. Second, the fragmentation of social media messages often impedes the model's ability to capture a comprehensive view of the events. Third, the lack of structured temporal context has hindered the development of effective models for event evolution, limiting users' access to event information. To address these challenges, we propose a foundation model for unsupervised Social Event Detection and Evolution, namely RagSEDE. Specifically, RagSEDE introduces a representativeness- and diversity-driven sampling strategy to extract key messages from massive social streams, significantly reducing noise and computational overhead. It further establishes a novel paradigm based on Retrieval Augmented Generation (RAG) that enhances PLMs in detecting events while simultaneously constructing and maintaining an evolving event knowledge base. Finally, RagSEDE leverages structural information theory to dynamically model event evolution keywords for the first time. Extensive experiments on two public datasets demonstrate the superiority of RagSEDE in open-world social event detection and evolution.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12035
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Effective and Unsupervised Social Event Detection and Evolution via RAG and Structural Entropy
Liu, Qitong
Peng, Hao
Li, Zuchen
Meng, Xihang
Yang, Ziyu
Li, Jiting
Sun, Li
Yu, Philip S.
Social and Information Networks
With the growing scale of social media, social event detection and evolution modeling have attracted increasing attention. Graph neural networks (GNNs) and transformer-based pre-trained language models (PLMs) have become mainstream approaches in this area. However, existing methods still face three major challenges. First, the sheer volume of social media messages makes learning resource-intensive. Second, the fragmentation of social media messages often impedes the model's ability to capture a comprehensive view of the events. Third, the lack of structured temporal context has hindered the development of effective models for event evolution, limiting users' access to event information. To address these challenges, we propose a foundation model for unsupervised Social Event Detection and Evolution, namely RagSEDE. Specifically, RagSEDE introduces a representativeness- and diversity-driven sampling strategy to extract key messages from massive social streams, significantly reducing noise and computational overhead. It further establishes a novel paradigm based on Retrieval Augmented Generation (RAG) that enhances PLMs in detecting events while simultaneously constructing and maintaining an evolving event knowledge base. Finally, RagSEDE leverages structural information theory to dynamically model event evolution keywords for the first time. Extensive experiments on two public datasets demonstrate the superiority of RagSEDE in open-world social event detection and evolution.
title Effective and Unsupervised Social Event Detection and Evolution via RAG and Structural Entropy
topic Social and Information Networks
url https://arxiv.org/abs/2601.12035