In this paper we use a Unified Relationship Matrix (URM) to represent a set of heterogeneous data objects (e.g., web pages, queries) and their interrelationships (e.g., hyperlinks, user click-through sequences). We claim that iterative computations over the URM can help overcome the data sparseness problem and detect latent relationships among heterogeneous data objects, thus, can improve the quality of information applications that require com- bination of information from heterogeneous sources. To support our claim, we present a unified similarity-calculating algorithm, SimFusion. By iteratively computing over the URM, SimFusion can effectively integrate relationships from heterogeneous sources when measuring the similarity of two data objects. Experiments based on a web search engine query log and a web page collection demonstrate that SimFusion can improve similarity measurement of web objects over both traditional content based algorithms and the cutting edge SimRank algorithm.
%0 Conference Paper
%1 xi2005
%A Xi, W.
%A Fox, E. A.
%A Fan, W.
%A Zhang, B.
%A Chen, Z.
%A Yan, J.
%A Zhuang, D.
%B SIGIR '05: Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
%C New York, NY, USA
%D 2005
%I ACM
%K MUSTREAD folksonomy networks reading-group search tagging tools
%P 130--137
%R http://doi.acm.org/10.1145/1076034.1076059
%T SimFusion: measuring similarity using unified relationship matrix
%U http://portal.acm.org/citation.cfm?id=1076034.1076059
%X In this paper we use a Unified Relationship Matrix (URM) to represent a set of heterogeneous data objects (e.g., web pages, queries) and their interrelationships (e.g., hyperlinks, user click-through sequences). We claim that iterative computations over the URM can help overcome the data sparseness problem and detect latent relationships among heterogeneous data objects, thus, can improve the quality of information applications that require com- bination of information from heterogeneous sources. To support our claim, we present a unified similarity-calculating algorithm, SimFusion. By iteratively computing over the URM, SimFusion can effectively integrate relationships from heterogeneous sources when measuring the similarity of two data objects. Experiments based on a web search engine query log and a web page collection demonstrate that SimFusion can improve similarity measurement of web objects over both traditional content based algorithms and the cutting edge SimRank algorithm.
%@ 1-59593-034-5
@inproceedings{xi2005,
abstract = {In this paper we use a Unified Relationship Matrix (URM) to represent a set of heterogeneous data objects (e.g., web pages, queries) and their interrelationships (e.g., hyperlinks, user click-through sequences). We claim that iterative computations over the URM can help overcome the data sparseness problem and detect latent relationships among heterogeneous data objects, thus, can improve the quality of information applications that require com- bination of information from heterogeneous sources. To support our claim, we present a unified similarity-calculating algorithm, SimFusion. By iteratively computing over the URM, SimFusion can effectively integrate relationships from heterogeneous sources when measuring the similarity of two data objects. Experiments based on a web search engine query log and a web page collection demonstrate that SimFusion can improve similarity measurement of web objects over both traditional content based algorithms and the cutting edge SimRank algorithm.},
added-at = {2009-07-01T09:26:27.000+0200},
address = {New York, NY, USA},
author = {Xi, W. and Fox, E. A. and Fan, W. and Zhang, B. and Chen, Z. and Yan, J. and Zhuang, D.},
biburl = {https://www.bibsonomy.org/bibtex/28b0de27fbcccb1140d4edfb734ee6fbc/mstrohm},
booktitle = {SIGIR '05: Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval},
description = {on URM (Unified Relationship Matrix)},
doi = {http://doi.acm.org/10.1145/1076034.1076059},
interhash = {97f605e95fe572fa66e8587a08cda6f4},
intrahash = {8b0de27fbcccb1140d4edfb734ee6fbc},
isbn = {1-59593-034-5},
keywords = {MUSTREAD folksonomy networks reading-group search tagging tools},
location = {Salvador, Brazil},
pages = {130--137},
publisher = {ACM},
timestamp = {2009-07-01T09:26:27.000+0200},
title = {SimFusion: measuring similarity using unified relationship matrix},
url = {http://portal.acm.org/citation.cfm?id=1076034.1076059},
year = 2005
}