@article{bollen2009clickstream,
abstract = {
Background
Intricate maps of science have been created from citation data to visualize the structure of scientific activity. However, most scientific publications are now accessed online. Scholarly web portals record detailed log data at a scale that exceeds the number of all existing citations combined. Such log data is recorded immediately upon publication and keeps track of the sequences of user requests (clickstreams) that are issued by a variety of users across many different domains. Given these advantages of log datasets over citation data, we investigate whether they can produce high-resolution, more current maps of science.
Methodology
Over the course of 2007 and 2008, we collected nearly 1 billion user interactions recorded by the scholarly web portals of some of the most significant publishers, aggregators and institutional consortia. The resulting reference data set covers a significant part of world-wide use of scholarly web portals in 2006, and provides a balanced coverage of the humanities, social sciences, and natural sciences. A journal clickstream model, i.e. a first-order Markov chain, was extracted from the sequences of user interactions in the logs. The clickstream model was validated by comparing it to the Getty Research Institute's Architecture and Art Thesaurus. The resulting model was visualized as a journal network that outlines the relationships between various scientific domains and clarifies the connection of the social sciences and humanities to the natural sciences.
Conclusions
Maps of science resulting from large-scale clickstream data provide a detailed, contemporary view of scientific activity and correct the underrepresentation of the social sciences and humanities that is commonly found in citation data.
},
author = {Bollen, Johan and Van de Sompel, Herbert and Hagberg, Aric and Bettencourt, Luis and Chute, Ryan and Rodriguez, Marko A. and Balakireva, Lyudmila},
doi = {10.1371/journal.pone.0004803},
interhash = {3a371a1ed31d14204770315b52023b96},
intrahash = {f00bfe25b550d999d737ab3362378174},
journal = {PLoS ONE},
month = {03},
number = 3,
pages = {e4803},
publisher = {Public Library of Science},
title = {Clickstream Data Yields High-Resolution Maps of Science},
url = {http://dx.doi.org/10.1371%2Fjournal.pone.0004803},
volume = 4,
year = 2009
}
@article{bollen2009clickstream,
abstract = {Background Intricate maps of science have been created from citation data to visualize the structure of scientific activity. However, most scientific publications are now accessed online. Scholarly web portals record detailed log data at a scale that exceeds the number of all existing citations combined. Such log data is recorded immediately upon publication and keeps track of the sequences of user requests (clickstreams) that are issued by a variety of users across many different domains. Given these advantages of log datasets over citation data, we investigate whether they can produce high-resolution, more current maps of science. Methodology Over the course of 2007 and 2008, we collected nearly 1 billion user interactions recorded by the scholarly web portals of some of the most significant publishers, aggregators and institutional consortia. The resulting reference data set covers a significant part of world-wide use of scholarly web portals in 2006, and provides a balanced coverage of the humanities, social sciences, and natural sciences. A journal clickstream model, i.e. a first-order Markov chain, was extracted from the sequences of user interactions in the logs. The clickstream model was validated by comparing it to the Getty Research Institute's Architecture and Art Thesaurus. The resulting model was visualized as a journal network that outlines the relationships between various scientific domains and clarifies the connection of the social sciences and humanities to the natural sciences. Conclusions Maps of science resulting from large-scale clickstream data provide a detailed, contemporary view of scientific activity and correct the underrepresentation of the social sciences and humanities that is commonly found in citation data.},
author = {Bollen, Johan and van de Sompel, Herbert and Hagberg, Aric and Bettencourt, Luis and Chute, Ryan and Rodriguez, Marko A. and Balakireva, Lyudmila},
doi = {10.1371/journal.pone.0004803},
interhash = {3a371a1ed31d14204770315b52023b96},
intrahash = {e61bd0c26cc1c08cff22a8301d03044f},
journal = {PLoS ONE},
month = mar,
number = 3,
pages = {e4803},
publisher = {Public Library of Science},
title = {Clickstream Data Yields High-Resolution Maps of Science},
url = {http://dx.doi.org/10.1371/journal.pone.0004803},
volume = 4,
year = 2009
}
@inproceedings{vandesompel2010httpbased,
abstract = {Dereferencing a URI returns a representation of the current state of the resource identified by that URI. But, on the Web representations of prior states of a resource are also available, for example, as resource versions in Content Management Systems or archival resources in Web Archives such as the Internet Archive. This paper introduces a resource versioning mechanism that is fully based on HTTP and uses datetime as a global version indicator. The approach allows "follow your nose" style navigation both from the current time-generic resource to associated time-specific version resources as well as among version resources. The proposed versioning mechanism is congruent with the Architecture of the World Wide Web, and is based on the Memento framework that extends HTTP with transparent content negotiation in the datetime dimension. The paper shows how the versioning approach applies to Linked Data, and by means of a demonstrator built for DBpedia, it also illustrates how it can be used to conduct a time-series analysis across versions of Linked Data descriptions.},
author = {Van de Sompel, Herbert and Sanderson, Robert and Nelson, Michael L. and Balakireva, Lyudmila L. and Shankar, Harihar and Ainsworth, Scott},
booktitle = {Proceedings of Linked Data on the Web (LDOW2010)},
interhash = {0c517e7799d2c2da3f9b2a0daff27885},
intrahash = {8f9405e8056dd827d9c72a48e229a65a},
number = {1003.3661},
publisher = {arXiv},
series = {cs.DL},
title = {An HTTP-Based Versioning Mechanism for Linked Data},
url = {http://arxiv.org/abs/1003.3661},
year = 2010
}