Discovering Key Nodes in a Temporal Social Network

TL;DR

This paper introduces a novel, sensitive PageRank-like algorithm that considers temporal and categorical user actions to more effectively identify key nodes in dynamic social networks, improving understanding of social event dissemination.

Contribution

The paper presents a new algorithm that incorporates temporal and categorical data for more accurate key node detection in evolving social networks.

Findings

The new algorithm outperforms baseline PageRank in identifying influential nodes.

Key nodes identified by the new method lead to better disease spread simulation results.

The approach enhances understanding of social event dissemination over networks.

Abstract

[Background]Discovering key nodes plays a significant role in Social Network Analysis(SNA). Effective and accurate mining of key nodes promotes more successful applications in fields like advertisement and recommendation. [Methods] With focus on the temporal and categorical property of users' actions - when did they re-tweet or reply a message, as well as their social intimacy measured by structural embeddings, we designed a more sensitive PageRank-like algorithm to accommodate the growing and changing social network in the pursue of mining key nodes. [Results] Compared with our baseline PageRank algorithm, key nodes selected by our ranking algorithm noticeably perform better in the SIR disease simulations with SNAP Higgs dataset. [Conclusion] These results contributed to a better understanding of disseminations of social events over the network.