Scholarlink

<p>Although incremental methods are widely used in community detection, their error accumulation problem remains unresolved. Additionally, current methods typically identify events only after community detection has been completed for all time snapshots, lacking consideration of the impact of events on community structure during evolution. Therefore, this paper proposes a framework called <b>Tra</b>cking dy<b>n</b>amic community evolution based on <b>S</b>oc<b>i</b>al Relevance and Strong <b>E</b>ve<b>nt</b>s(<b>TranSiEnt</b>). For the first time, TranSiEnt integrates evolution event identification with dynamic community updating, classifying evolution events into ordinary events and Strong Events based on the influence of the relevant communities. During dynamic community updating, TranSiEnt employs a path diffusion strategy to determine core nodes for community detection, establishing the initial community structure. Using an incremental approach, the framework expands the influence range of incremental nodes in communities experiencing Strong Events. It again conducts precise community detection on all affected nodes to reduce error accumulation, ultimately optimizing community partitioning. TranSiEnt was subjected to objective accuracy experiments on real and synthetic datasets, using modularity, NMI, and EMA as performance evaluation metrics. <i>T</i>-tests were used to verify the significance of the performance improvement of the TranSiEnt algorithm. The experimental results show that TranSiEnt performs better in dynamic community detection and evolution event tracking, significantly improving over existing methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Tracking dynamic community evolution based on Social Relevance and Strong Events

  • 期刊论文

  • 发表日期：

    2025年4月21日

查看全文
  • Ling Wu,
  • Xiaohua Xie,
  • Chengkai Chen,
  • Yingjie Yang,
  • Kun Guo

摘要

Although incremental methods are widely used in community detection, their error accumulation problem remains unresolved. Additionally, current methods typically identify events only after community detection has been completed for all time snapshots, lacking consideration of the impact of events on community structure during evolution. Therefore, this paper proposes a framework called Tracking dynamic community evolution based on Social Relevance and Strong Events(TranSiEnt). For the first time, TranSiEnt integrates evolution event identification with dynamic community updating, classifying evolution events into ordinary events and Strong Events based on the influence of the relevant communities. During dynamic community updating, TranSiEnt employs a path diffusion strategy to determine core nodes for community detection, establishing the initial community structure. Using an incremental approach, the framework expands the influence range of incremental nodes in communities experiencing Strong Events. It again conducts precise community detection on all affected nodes to reduce error accumulation, ultimately optimizing community partitioning. TranSiEnt was subjected to objective accuracy experiments on real and synthetic datasets, using modularity, NMI, and EMA as performance evaluation metrics. T-tests were used to verify the significance of the performance improvement of the TranSiEnt algorithm. The experimental results show that TranSiEnt performs better in dynamic community detection and evolution event tracking, significantly improving over existing methods.