@inproceedings{conf/ai/ShafieiM08, author = {Shafiei, M. Mahdi and Milios, Evangelos E.}, booktitle = {Canadian Conference on AI}, crossref = {conf/ai/2008}, editor = {Bergler, Sabine}, ee = {http://dx.doi.org/10.1007/978-3-540-68825-9_27}, interhash = {1ed1fddf0ac4762ea8debac2ee80b936}, intrahash = {80e27cd4ea288b0ab6bcc1c67841364e}, isbn = {978-3-540-68821-1}, pages = {283-295}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {A Statistical Model for Topic Segmentation and Clustering.}, url = {http://dblp.uni-trier.de/db/conf/ai/ai2008.html#ShafieiM08}, volume = 5032, year = 2008 } @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}, address = {London}, author = {An, Yuan and Janssen, Jeannette and Milios, Evangelos E.}, doi = {10.1007/s10115-003-0128-3}, interhash = {73fdd0592c1641d05da5d2323d9f59ae}, intrahash = {2fe1a8e5fdeb537973491ad334acb0ea}, issn = {0219-1377}, issue = {6}, journal = {Knowledge and Information Systems}, month = nov, number = 6, numpages = {15}, pages = {664--678}, publisher = {Springer}, 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 } @article{an2004characterizing, acmid = {1031388}, address = {New York, NY, USA}, author = {An, Yuan and Janssen, Jeannette and Milios, Evangelos E.}, doi = {http://dx.doi.org/10.1007/s10115-003-0128-3}, interhash = {73fdd0592c1641d05da5d2323d9f59ae}, intrahash = {60e0c625f5765a05c588c6765a8cd93c}, issn = {0219-1377}, issue = {6}, journal = {Knowl. Inf. Syst.}, month = {November}, numpages = {15}, pages = {664--678}, publisher = {Springer-Verlag New York, Inc.}, 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 } @inproceedings{shafiei_milios06, address = {Washington, DC, USA}, author = {Shafiei, M. Mahdi and Milios, Evangelos E.}, bdsk-url-1 = {http://dx.doi.org/10.1109/ICDM.2006.94}, booktitle = {ICDM '06: Proceedings of the Sixth International Conference on Data Mining}, doi = {http://dx.doi.org/10.1109/ICDM.2006.94}, interhash = {5850c178c4393ec9c7ea8b0f7f9271c5}, intrahash = {f36c376d49e03acd1cae83c758327943}, isbn = {0-7695-2701-9}, owner = {gregor}, pages = {542--551}, publisher = {IEEE Computer Society}, timestamp = {2008.04.25}, title = {Latent {D}irichlet Co-Clustering}, year = 2006 }