Information network contains abundant knowledge about relationships among people or entities. Unfortunately, such kind of knowledge is often hidden in a network where different kinds of relationships are not explicitly categorized. For example, in a research publication network, the advisor-advisee relationships among researchers are hidden in the coauthor network. Discovery of those relationships can benefit many interesting applications such as expert finding and research community analysis. In this paper, we take a computer science bibliographic network as an example, to analyze the roles of authors and to discover the likely advisor-advisee relationships. In particular, we propose a time-constrained probabilistic factor graph model (TPFG), which takes a research publication network as input and models the advisor-advisee relationship mining problem using a jointly likelihood objective function. We further design an efficient learning algorithm to optimize the objective function. Based on that our model suggests and ranks probable advisors for every author. Experimental results show that the proposed approach infer advisor-advisee relationships efficiently and achieves a state-of-the-art accuracy (80-90%). We also apply the discovered advisor-advisee relationships to bole search, a specific expert finding task and empirical study shows that the search performance can be effectively improved (+4.09% by NDCG@5).
%0 Conference Paper
%1 wang2010mining
%A Wang, Chi
%A Han, Jiawei
%A Jia, Yuntao
%A Tang, Jie
%A Zhang, Duo
%A Yu, Yintao
%A Guo, Jingyi
%B Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
%C New York, NY, USA
%D 2010
%I ACM
%K collaboration_network master_thesis
%P 203--212
%R 10.1145/1835804.1835833
%T Mining Advisor-advisee Relationships from Research Publication Networks
%U http://doi.acm.org/10.1145/1835804.1835833
%X Information network contains abundant knowledge about relationships among people or entities. Unfortunately, such kind of knowledge is often hidden in a network where different kinds of relationships are not explicitly categorized. For example, in a research publication network, the advisor-advisee relationships among researchers are hidden in the coauthor network. Discovery of those relationships can benefit many interesting applications such as expert finding and research community analysis. In this paper, we take a computer science bibliographic network as an example, to analyze the roles of authors and to discover the likely advisor-advisee relationships. In particular, we propose a time-constrained probabilistic factor graph model (TPFG), which takes a research publication network as input and models the advisor-advisee relationship mining problem using a jointly likelihood objective function. We further design an efficient learning algorithm to optimize the objective function. Based on that our model suggests and ranks probable advisors for every author. Experimental results show that the proposed approach infer advisor-advisee relationships efficiently and achieves a state-of-the-art accuracy (80-90%). We also apply the discovered advisor-advisee relationships to bole search, a specific expert finding task and empirical study shows that the search performance can be effectively improved (+4.09% by NDCG@5).
%@ 978-1-4503-0055-1
@inproceedings{wang2010mining,
abstract = {Information network contains abundant knowledge about relationships among people or entities. Unfortunately, such kind of knowledge is often hidden in a network where different kinds of relationships are not explicitly categorized. For example, in a research publication network, the advisor-advisee relationships among researchers are hidden in the coauthor network. Discovery of those relationships can benefit many interesting applications such as expert finding and research community analysis. In this paper, we take a computer science bibliographic network as an example, to analyze the roles of authors and to discover the likely advisor-advisee relationships. In particular, we propose a time-constrained probabilistic factor graph model (TPFG), which takes a research publication network as input and models the advisor-advisee relationship mining problem using a jointly likelihood objective function. We further design an efficient learning algorithm to optimize the objective function. Based on that our model suggests and ranks probable advisors for every author. Experimental results show that the proposed approach infer advisor-advisee relationships efficiently and achieves a state-of-the-art accuracy (80-90%). We also apply the discovered advisor-advisee relationships to bole search, a specific expert finding task and empirical study shows that the search performance can be effectively improved (+4.09% by NDCG@5).},
acmid = {1835833},
added-at = {2014-10-01T22:31:54.000+0200},
address = {New York, NY, USA},
author = {Wang, Chi and Han, Jiawei and Jia, Yuntao and Tang, Jie and Zhang, Duo and Yu, Yintao and Guo, Jingyi},
biburl = {https://www.bibsonomy.org/bibtex/23c61272cb6af5677dbc55fa773fafbc1/subhashpujari},
booktitle = {Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
doi = {10.1145/1835804.1835833},
interhash = {17efdb3e06fea715bd30d2eba2a0c217},
intrahash = {3c61272cb6af5677dbc55fa773fafbc1},
isbn = {978-1-4503-0055-1},
keywords = {collaboration_network master_thesis},
location = {Washington, DC, USA},
numpages = {10},
pages = {203--212},
publisher = {ACM},
series = {KDD '10},
timestamp = {2014-10-01T22:31:54.000+0200},
title = {Mining Advisor-advisee Relationships from Research Publication Networks},
url = {http://doi.acm.org/10.1145/1835804.1835833},
year = 2010
}