There has been a long history of research into the structure and evolution of
mankind's scientific endeavor. However, recent progress in applying the tools
of science to understand science itself has been unprecedented because only
recently has there been access to high-volume and high-quality data sets of
scientific output (e.g., publications, patents, grants), as well as computers
and algorithms capable of handling this enormous stream of data. This paper
reviews major work on models that aim to capture and recreate the structure and
dynamics of scientific evolution. We then introduce a general process model
that simultaneously grows co-author and paper-citation networks. The
statistical and dynamic properties of the networks generated by this model are
validated against a 20-year data set of articles published in the Proceedings
of the National Academy of Science. Systematic deviations from a power law
distribution of citations to papers are well fit by a model that incorporates a
partitioning of authors and papers into topics, a bias for authors to cite
recent papers, and a tendency for authors to cite papers cited by papers that
they have read. In this TARL model (for Topics, Aging, and Recursive Linking),
the number of topics is linearly related to the clustering coefficient of the
simulated paper citation network.
To our knowledge there exists no algorithmic approach that simultaneously models the evolution of different networks such as co-author and paper citation networks within an ecology of multiple interacting networks. Here we argue that to fully understand the structure, evolution, and utilization of networks, co-author and paper citation networks need to be considered simultaneously. For example, to understand how knowledge diffuses across authors via their papers at the same time that new authors and papers are accumulated; it is essential to model the coupled growth of both network structures.
%0 Generic
%1 citeulike:221097
%A Börner, Katy
%A Maru, Jeegar T.
%A Goldstone, Robert L.
%D 2003
%K science skillinference socialnets
%T The Simultaneous Evolution of Author and Paper Networks
%U http://arxiv.org/abs/cond-mat/0311459
%X There has been a long history of research into the structure and evolution of
mankind's scientific endeavor. However, recent progress in applying the tools
of science to understand science itself has been unprecedented because only
recently has there been access to high-volume and high-quality data sets of
scientific output (e.g., publications, patents, grants), as well as computers
and algorithms capable of handling this enormous stream of data. This paper
reviews major work on models that aim to capture and recreate the structure and
dynamics of scientific evolution. We then introduce a general process model
that simultaneously grows co-author and paper-citation networks. The
statistical and dynamic properties of the networks generated by this model are
validated against a 20-year data set of articles published in the Proceedings
of the National Academy of Science. Systematic deviations from a power law
distribution of citations to papers are well fit by a model that incorporates a
partitioning of authors and papers into topics, a bias for authors to cite
recent papers, and a tendency for authors to cite papers cited by papers that
they have read. In this TARL model (for Topics, Aging, and Recursive Linking),
the number of topics is linearly related to the clustering coefficient of the
simulated paper citation network.
@misc{citeulike:221097,
abstract = {There has been a long history of research into the structure and evolution of
mankind's scientific endeavor. However, recent progress in applying the tools
of science to understand science itself has been unprecedented because only
recently has there been access to high-volume and high-quality data sets of
scientific output (e.g., publications, patents, grants), as well as computers
and algorithms capable of handling this enormous stream of data. This paper
reviews major work on models that aim to capture and recreate the structure and
dynamics of scientific evolution. We then introduce a general process model
that simultaneously grows co-author and paper-citation networks. The
statistical and dynamic properties of the networks generated by this model are
validated against a 20-year data set of articles published in the Proceedings
of the National Academy of Science. Systematic deviations from a power law
distribution of citations to papers are well fit by a model that incorporates a
partitioning of authors and papers into topics, a bias for authors to cite
recent papers, and a tendency for authors to cite papers cited by papers that
they have read. In this TARL model (for Topics, Aging, and Recursive Linking),
the number of topics is linearly related to the clustering coefficient of the
simulated paper citation network.},
added-at = {2006-06-16T10:34:37.000+0200},
author = {B{\"o}rner, Katy and Maru, Jeegar T. and Goldstone, Robert L.},
biburl = {https://www.bibsonomy.org/bibtex/2275b56a4cd17f14e737c7076cd0aae4b/ldietz},
citeulike-article-id = {221097},
comment = {To our knowledge there exists no algorithmic approach that simultaneously models the evolution of different networks such as co-author and paper citation networks within an ecology of multiple interacting networks. Here we argue that to fully understand the structure, evolution, and utilization of networks, co-author and paper citation networks need to be considered simultaneously. For example, to understand how knowledge diffuses across authors via their papers at the same time that new authors and papers are accumulated; it is essential to model the coupled growth of both network structures.},
eprint = {cond-mat/0311459},
interhash = {d04057831ec4e552c313e30e78bdac63},
intrahash = {275b56a4cd17f14e737c7076cd0aae4b},
keywords = {science skillinference socialnets},
month = {November},
priority = {4},
timestamp = {2006-06-16T10:34:37.000+0200},
title = {The Simultaneous Evolution of Author and Paper Networks},
url = {http://arxiv.org/abs/cond-mat/0311459},
year = 2003
}