Information genealogy: uncovering the flow of ideas in non-hyperlinked document databases Export

@inproceedings{Information-Geneaology, abstract = {We now have incrementally-grown databases of text documents ranging back for over a decade in areas ranging from personal email, to news-articles and conference proceedings. While accessing individual documents is easy, methods for overviewing and understanding these collections as a whole are lacking in number and in scope. In this paper, we address one such global analysis task, namely the problem of automatically uncovering how ideas spread through the collection over time. We refer to this problem as Information Genealogy . In contrast to bibliometric methods that are limited to collections with explicit citation structure, we investigate content-based methods requiring only the text and timestamps of the documents. In particular, we propose a language-modeling approach and a likelihood ratio test to detect influence between documents in a statistically well-founded way. Furthermore, we show how this method can be used to infer citation graphs and to identify the most influential documents in the collection. Experiments on the NIPS conference proceedings and the Physics ArXiv show that our method is more effective than methods based on document similarity.}, address = {New York, NY, USA}, author = {Shaparenko, Benyah and Joachims, Thorsten}, booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining}, citeulike-article-id = {2304568}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1281192.1281259}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1281192.1281259}, doi = {10.1145/1281192.1281259}, isbn = {978-1-59593-609-7}, keywords = {citation, citationgraph}, location = {San Jose, California, USA}, pages = {619--628}, posted-at = {2008-02-28 14:33:52}, priority = {0}, publisher = {ACM}, title = {Information genealogy: uncovering the flow of ideas in non-hyperlinked document databases}, url = {http://dx.doi.org/10.1145/1281192.1281259}, year = {2007} }

TY - CONF ID - Information-Geneaology L3 - citeulike-article-id:2304568 N2 - We now have incrementally-grown databases of text documents ranging back for over a decade in areas ranging from personal email, to news-articles and conference proceedings. While accessing individual documents is easy, methods for overviewing and understanding these collections as a whole are lacking in number and in scope. In this paper, we address one such global analysis task, namely the problem of automatically uncovering how ideas spread through the collection over time. We refer to this problem as Information Genealogy . In contrast to bibliometric methods that are limited to collections with explicit citation structure, we investigate content-based methods requiring only the text and timestamps of the documents. In particular, we propose a language-modeling approach and a likelihood ratio test to detect influence between documents in a statistically well-founded way. Furthermore, we show how this method can be used to infer citation graphs and to identify the most influential documents in the collection. Experiments on the NIPS conference proceedings and the Physics ArXiv show that our method is more effective than methods based on document similarity. CY - San Jose, California, USA SN - 978-1-59593-609-7 AD - New York, NY, USA EP - 628 TI - Information genealogy: uncovering the flow of ideas in non-hyperlinked document databases PB - ACM T2 - KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining SP - 619 KW - citation KW - citationgraph AU - Shaparenko, Benyah AU - Joachims, Thorsten PY - 2007/// UR - http://dx.doi.org/10.1145/1281192.1281259 ER -