PageRank without hyperlinks: reranking with PubMed related article networks for biomedical text retrieval

@article{citeulike:2870248, abstract = {BACKGROUND:Graph analysis algorithms such as PageRank and HITS have been successful in Web environments because they are able to extract important inter-document relationships from manually-created hyperlinks. We consider the application of these techniques to biomedical text retrieval. In the current PubMed search interface, a MEDLINE citation is connected to a number of related citations, which are in turn connected to other citations. Thus, a MEDLINE record represents a node in a vast content-similarity network. This article explores the hypothesis that these networks can be exploited for text retrieval, in the same manner as hyperlink graphs on the Web.RESULTS:We conducted a number of reranking experiments using the TREC 2005 genomics track test collection in which scores extracted from PageRank and HITS analysis were combined with scores returned by an off-the-shelf retrieval engine. Experiments demonstrate that incorporating PageRank scores yields significant improvements in terms of standard ranked-retrieval metrics.CONCLUSIONS:The link structure of content-similarity networks can be exploited to improve the effectiveness of information retrieval systems. These results generalize the applicability of graph analysis algorithms to text retrieval in the biomedical domain.}, author = {Lin, Jimmy }, citeulike-article-id = {2870248}, doi = {http://dx.doi.org/10.1186/1471-2105-9-270}, journal = {BMC Bioinformatics}, keywords = {literature, network, pagerank, publication, pubmed}, number = {1}, posted-at = {2008-06-08 08:57:17}, priority = {2}, title = {PageRank without hyperlinks: reranking with PubMed related article networks for biomedical text retrieval}, url = {http://dx.doi.org/10.1186/1471-2105-9-270}, volume = {9}, year = {2008} }

TY - JOUR ID - citeulike:2870248 L3 - citeulike-article-id:2870248 N2 - BACKGROUND:Graph analysis algorithms such as PageRank and HITS have been successful in Web environments because they are able to extract important inter-document relationships from manually-created hyperlinks. We consider the application of these techniques to biomedical text retrieval. In the current PubMed search interface, a MEDLINE citation is connected to a number of related citations, which are in turn connected to other citations. Thus, a MEDLINE record represents a node in a vast content-similarity network. This article explores the hypothesis that these networks can be exploited for text retrieval, in the same manner as hyperlink graphs on the Web.RESULTS:We conducted a number of reranking experiments using the TREC 2005 genomics track test collection in which scores extracted from PageRank and HITS analysis were combined with scores returned by an off-the-shelf retrieval engine. Experiments demonstrate that incorporating PageRank scores yields significant improvements in terms of standard ranked-retrieval metrics.CONCLUSIONS:The link structure of content-similarity networks can be exploited to improve the effectiveness of information retrieval systems. These results generalize the applicability of graph analysis algorithms to text retrieval in the biomedical domain. IS - 1 JF - BMC Bioinformatics TI - PageRank without hyperlinks: reranking with PubMed related article networks for biomedical text retrieval VL - 9 KW - literature KW - network KW - pagerank KW - publication KW - pubmed AU - Lin, Jimmy PY - 2008/// UR - http://dx.doi.org/10.1186/1471-2105-9-270 ER -