Edge-centric multi-view network representation for link mining in signed social networks

作者：

Highlights：

• Inverse Square Metric is developed using both positive and negative links.

• Edge-centric multi view networks is proposed to analyze a link from 16 aspects.

• The results demonstrate that negative links are useful and improve the results.

• Unified link and sign prediction is studied and results are explained.

摘要

•Inverse Square Metric is developed using both positive and negative links.•Edge-centric multi view networks is proposed to analyze a link from 16 aspects.•The results demonstrate that negative links are useful and improve the results.•Unified link and sign prediction is studied and results are explained.

论文关键词：Signed social networks,Sign prediction,Link prediction,Direction prediction,Inverse square metric

论文评审过程：Received 27 August 2019, Revised 2 October 2020, Accepted 29 December 2020, Available online 5 January 2021, Version of Record 15 January 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114552