Graph building as a mining activity: finding links in the small
A. Badia, and M. Kantardzic. LinkKDD '05: Proceedings of the 3rd international workshop on Link discovery, page 17--24. New York, NY, USA, ACM, (2005)
Abstract
Many analysis of data proceed by building a graph out of
the data set and then using social network theory and similar
tools on the result. However, there is no theory concerning
the construction of the graph itself, even though this is a
very important process. In this paper, we attempt to pro-
vide a framework in which the graph building process is
formalized and studied. We show the parameters (choices)
involved in constructing a graph from raw data, and pro-
pose some new ways to combine and analyze the data. We
also argue the importance of this approach in several domain
applications, including criminal/terrorist investigations.
%0 Conference Paper
%1 paper:badia:2005
%A Badia, Antonio
%A Kantardzic, Mehmed
%B LinkKDD '05: Proceedings of the 3rd international workshop on Link discovery
%C New York, NY, USA
%D 2005
%I ACM
%K 2005 RG-done analysis framework graph link-analysis mining networks similiarity
%P 17--24
%T Graph building as a mining activity: finding links in the small
%X Many analysis of data proceed by building a graph out of
the data set and then using social network theory and similar
tools on the result. However, there is no theory concerning
the construction of the graph itself, even though this is a
very important process. In this paper, we attempt to pro-
vide a framework in which the graph building process is
formalized and studied. We show the parameters (choices)
involved in constructing a graph from raw data, and pro-
pose some new ways to combine and analyze the data. We
also argue the importance of this approach in several domain
applications, including criminal/terrorist investigations.
@inproceedings{paper:badia:2005,
abstract = {Many analysis of data proceed by building a graph out of
the data set and then using social network theory and similar
tools on the result. However, there is no theory concerning
the construction of the graph itself, even though this is a
very important process. In this paper, we attempt to pro-
vide a framework in which the graph building process is
formalized and studied. We show the parameters (choices)
involved in constructing a graph from raw data, and pro-
pose some new ways to combine and analyze the data. We
also argue the importance of this approach in several domain
applications, including criminal/terrorist investigations.},
added-at = {2008-05-27T10:07:44.000+0200},
address = {New York, NY, USA},
author = {Badia, Antonio and Kantardzic, Mehmed},
biburl = {https://www.bibsonomy.org/bibtex/253fb57b6c54debd70ee873751acfcf15/mschuber},
booktitle = {LinkKDD '05: Proceedings of the 3rd international workshop on Link discovery},
interhash = {05902fcb6d19dcc90de264efb24e7da4},
intrahash = {53fb57b6c54debd70ee873751acfcf15},
keywords = {2005 RG-done analysis framework graph link-analysis mining networks similiarity},
pages = {17--24},
publisher = {ACM},
timestamp = {2008-09-09T12:57:34.000+0200},
title = {Graph building as a mining activity: finding links in the small},
year = 2005
}