%0 Journal Article %1 an2004characterizing %A An, Yuan %A Janssen, Jeannette %A Milios, Evangelos E. %C London %D 2004 %I Springer %J Knowledge and Information Systems %K %N 6 %P 664--678 %R 10.1007/s10115-003-0128-3 %T Characterizing and Mining the Citation Graph of the Computer Science Literature %U http://dx.doi.org/10.1007/s10115-003-0128-3 %V 6 %X Citation graphs representing a body of scientific literature convey measures of scholarly activity and productivity. In this work we present a study of the structure of the citation graph of the computer science literature. Using a web robot we built several topic-specific citation graphs and their union graph from the digital library ResearchIndex. After verifying that the degree distributions follow a power law, we applied a series of graph theoretical algorithms to elicit an aggregate picture of the citation graph in terms of its connectivity. We discovered the existence of a single large weakly-connected and a single large biconnected component, and confirmed the expected lack of a large strongly-connected component. The large components remained even after removing the strongest authority nodes or the strongest hub nodes, indicating that such tight connectivity is widespread and does not depend on a small subset of important nodes. Finally, minimum cuts between authority papers of different areas did not result in a balanced partitioning of the graph into areas, pointing to the need for more sophisticated algorithms for clustering the graph.

@article{an2004characterizing, abstract = {Citation graphs representing a body of scientific literature convey measures of scholarly activity and productivity. In this work we present a study of the structure of the citation graph of the computer science literature. Using a web robot we built several topic-specific citation graphs and their union graph from the digital library ResearchIndex. After verifying that the degree distributions follow a power law, we applied a series of graph theoretical algorithms to elicit an aggregate picture of the citation graph in terms of its connectivity. We discovered the existence of a single large weakly-connected and a single large biconnected component, and confirmed the expected lack of a large strongly-connected component. The large components remained even after removing the strongest authority nodes or the strongest hub nodes, indicating that such tight connectivity is widespread and does not depend on a small subset of important nodes. Finally, minimum cuts between authority papers of different areas did not result in a balanced partitioning of the graph into areas, pointing to the need for more sophisticated algorithms for clustering the graph.}, acmid = {1031388}, added-at = {2011-12-21T22:49:38.000+0100}, address = {London}, author = {An, Yuan and Janssen, Jeannette and Milios, Evangelos E.}, biburl = {https://www.bibsonomy.org/bibtex/22fe1a8e5fdeb537973491ad334acb0ea/jaeschke}, doi = {10.1007/s10115-003-0128-3}, interhash = {73fdd0592c1641d05da5d2323d9f59ae}, intrahash = {2fe1a8e5fdeb537973491ad334acb0ea}, issn = {0219-1377}, issue = {6}, journal = {Knowledge and Information Systems}, keywords = {}, month = nov, number = 6, numpages = {15}, pages = {664--678}, publisher = {Springer}, timestamp = {2011-12-21T22:49:38.000+0100}, title = {Characterizing and Mining the Citation Graph of the Computer Science Literature}, url = {http://dx.doi.org/10.1007/s10115-003-0128-3}, volume = 6, year = 2004 }