Evolution of document networks Export

@article{citeulike:885123, abstract = {10.1073/pnas.0307554100 How does a network of documents grow without centralized control? This question is becoming crucial as we try to explain the emergent scale-free topology of the World Wide Web and use link analysis to identify important information resources. Existing models of growing information networks have focused on the structure of links but neglected the content of nodes. Here I show that the current models fail to reproduce a critical characteristic of information networks, namely the distribution of textual similarity among linked documents. I propose a more realistic model that generates links by using both popularity and content. This model yields remarkably accurate predictions of both degree and similarity distributions in networks of web pages and scientific literature.}, address = {School of Informatics, Indiana University, Bloomington, IN 47408, USA. fil@indiana.edu}, author = {Menczer, Filippo}, citeulike-article-id = {885123}, citeulike-linkout-0 = {http://dx.doi.org/10.1073/pnas.0307554100}, citeulike-linkout-1 = {http://www.pnas.org/content/101/suppl.1/5261.abstract}, citeulike-linkout-2 = {http://www.pnas.org/content/101/suppl.1/5261.full.pdf}, citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/14747653}, citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=14747653}, day = {6}, doi = {10.1073/pnas.0307554100}, issn = {0027-8424}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, keywords = {information\_retrieval, networks, web}, month = {April}, number = {Suppl 1}, pages = {5261--5265}, posted-at = {2006-10-05 16:14:12}, priority = {2}, title = {Evolution of document networks}, url = {http://dx.doi.org/10.1073/pnas.0307554100}, volume = {101}, year = {2004} }

TY - JOUR ID - citeulike:885123 L3 - citeulike-article-id:885123 N2 - 10.1073/pnas.0307554100 How does a network of documents grow without centralized control? This question is becoming crucial as we try to explain the emergent scale-free topology of the World Wide Web and use link analysis to identify important information resources. Existing models of growing information networks have focused on the structure of links but neglected the content of nodes. Here I show that the current models fail to reproduce a critical characteristic of information networks, namely the distribution of textual similarity among linked documents. I propose a more realistic model that generates links by using both popularity and content. This model yields remarkably accurate predictions of both degree and similarity distributions in networks of web pages and scientific literature. IS - Suppl 1 JF - Proceedings of the National Academy of Sciences of the United States of America SN - 0027-8424 AD - School of Informatics, Indiana University, Bloomington, IN 47408, USA. fil@indiana.edu EP - 5265 TI - Evolution of document networks VL - 101 SP - 5261 KW - information_retrieval KW - networks KW - web AU - Menczer, Filippo PY - 2004/04/06/ UR - http://dx.doi.org/10.1073/pnas.0307554100 ER -