Detecting Hierarchical Ties Using Link-Analysis Ranking at Different\n Levels of Time Granularity Article Swipe
YOU?
·
· 2017
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.1701.06861
· OA: W4295598379
Social networks contain implicit knowledge that can be used to infer\nhierarchical relations that are not explicitly present in the available data.\nInteraction patterns are typically affected by users' social relations. We\npresent an approach to inferring such information that applies a link-analysis\nranking algorithm at different levels of time granularity. In addition, a\nvoting scheme is employed for obtaining the hierarchical relations. The\napproach is evaluated on two datasets: the Enron email data set, where the goal\nis to infer manager-subordinate relationships, and the Co-author data set,\nwhere the goal is to infer PhD advisor-advisee relations. The experimental\nresults indicate that the proposed approach outperforms more traditional\napproaches to inferring hierarchical relations from social networks.\n
