Scholarlink

<p>This study addresses the challenge of identifying suspicious citation groups in heterogeneous academic networks comprising both journals and papers. Existing approaches primarily use local structural signals, such as pairwise citation intensity or node-level anomalies, while overlooking global structural roles and citation-flow dynamics within the broader network. Adopting a design science research approach and drawing on Complex Network Theory, we develop a novel framework that integrates local and global structural signals to identify suspicious citation groups. Beyond the artifact itself, the study derives design principles for integrating local and global structural signals in network-based identification of suspicious citation groups, offering important implications for both research and practice.</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

Designing a Computational Framework for Identifying Suspicious Citation Groups in Heterogeneous Academic Networks: A Graph Learning Approach

  • 期刊论文

  • 发表日期：

    2026年6月26日

查看全文
  • Jiaying Liu,
  • Xinrui Cheng,
  • Shengliang Wei,
  • Gongtai Wang

摘要

This study addresses the challenge of identifying suspicious citation groups in heterogeneous academic networks comprising both journals and papers. Existing approaches primarily use local structural signals, such as pairwise citation intensity or node-level anomalies, while overlooking global structural roles and citation-flow dynamics within the broader network. Adopting a design science research approach and drawing on Complex Network Theory, we develop a novel framework that integrates local and global structural signals to identify suspicious citation groups. Beyond the artifact itself, the study derives design principles for integrating local and global structural signals in network-based identification of suspicious citation groups, offering important implications for both research and practice.