{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:09:23Z","timestamp":1775282963260,"version":"3.50.1"},"reference-count":28,"publisher":"Elsevier BV","issue":"3","license":[{"start":{"date-parts":[[2004,5,1]],"date-time":"2004-05-01T00:00:00Z","timestamp":1083369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information Processing &amp; Management"],"published-print":{"date-parts":[[2004,5]]},"DOI":"10.1016\/s0306-4573(03)00008-6","type":"journal-article","created":{"date-parts":[[2003,5,12]],"date-time":"2003-05-12T23:55:41Z","timestamp":1052783741000},"page":"527-546","source":"Crossref","is-referenced-by-count":15,"title":["Collection selection for managed distributed document databases"],"prefix":"10.1016","volume":"40","author":[{"given":"Daryl","family":"D'Souza","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James A.","family":"Thom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Zobel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0306-4573(03)00008-6_BIB1","doi-asserted-by":"crossref","unstructured":"Broglio, J., Callan, J., Croft, W. B., & Nachbar, D. (1994). Document retrieval and routing using the INQUERY system. In D. Harman (Ed.), Proceedings of third text retrieval conference (TREC-3) (pp. 29\u201338). National Institute of Standards and Technology Special Publication 500-225, Washington","DOI":"10.6028\/NIST.SP.500-225.umass"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB2","series-title":"Advances in information retrieval: recent research from the center for intelligent information retrieval","first-page":"127","article-title":"Distributed information retrieval","author":"Callan","year":"2000"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB3","doi-asserted-by":"crossref","unstructured":"Callan, J., Connell, M., & Du, A. (1999). Automatic discovery of language models for text databases. In Proceedings of the 1999 ACM international conference on management of data (SIGMOD'99) (pp. 479\u2013490). ACM","DOI":"10.1145\/304182.304224"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB4","doi-asserted-by":"crossref","unstructured":"Callan, J. P., Lu, Z., & Croft, W. B. (1995). Searching distributed collections with inference networks. In E. A. Fox, P. Ingwersen, & R. Fidel (Eds.), Proceedings of the 18th annual international ACM SIGIR conference on research and development in information retrieval (pp. 21\u201328). ACM","DOI":"10.1145\/215206.215328"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB5","unstructured":"Callan, J., Powell, A. L., French, J. C., & Connell, M. (2000). The effects of query based sampling in automatic database selection algorithms. Technical Report CMU-LTI-00-162, Language Technologies Institute, School of Computer Science, Carnegie Mellon University"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB6","doi-asserted-by":"crossref","unstructured":"Crasswell, N., Bailey, P., & Hawking, D. (2000). Server selection on the world wide web. In Proceedings of the fifth ACM conference on digital libraries (pp. 37\u201346)","DOI":"10.1145\/336597.336628"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB7","doi-asserted-by":"crossref","unstructured":"de Kretser, O., Moffat, A., Shimmin, T., & Zobel, J. (1998). Methodologies for distributed information retrieval. In M. P. Papazoglou, M. Takizawa, B. Kramer, & S. Chanson (Eds.), Proceedings of the eighteenth international conference on distributed computing systems (pp. 66\u201373). Amsterdam, the Netherlands","DOI":"10.1109\/ICDCS.1998.679488"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB8","unstructured":"D'Souza, D., & Thom, J. A. (1999). Collection selection using n-term indexing. In Y. Zhang, M. Rusinkiewicz, & Y. Kambayashi (Eds.), Proceedings of the second international symposium on cooperative database systems for advanced applications (CODAS'99) (pp. 52\u201363). Wollongong, NSW, Australia: Springer"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB9","unstructured":"D'Souza, D., Thom, J. A., & Zobel, J. (2000). A comparison of techniques for selecting text collections. In Proceedings of the eleventh Australasian database conference (ADC'2000) (pp. 28\u201332). Canberra, ACT, Australia. To appear in IEEE Computer Society publication"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB10","doi-asserted-by":"crossref","unstructured":"French, J. C., Powell, A. L., Callan, J., Viles, C. L., Emmitt, T., Prey, K. J., & Mou, Y. (1999). Comparing the performance of database selection algorithms. In M. Hearst, F. Gey, & R. Tong (Eds.), Proceedings of the 22nd annual international ACM SIGIR conference on research and development in information retrieval (pp. 238\u2013245). ACM","DOI":"10.1145\/312624.312684"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB11","doi-asserted-by":"crossref","unstructured":"French, J. C., Powell, A. L., Viles, C. L., Emmitt, T., & Prey, K. J. (1998). Evaluating database selection techniques: a testbed and experiment. In W. B. Croft, A. Moffat, C. J. van Rijsbergen, R. Wilkinson, & J. Zobel (Eds.), Proceedings of the 21st annual international ACM SIGIR conference on research and development in information retrieval (pp. 121\u2013129). ACM","DOI":"10.1145\/290941.290976"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB12","unstructured":"Gravano, L., & Garcia-Mol\u0131\u0301na, H. (1995). Generalising GlOSS to vector-space databases and broker hierarchies. In Proceedings of 21st international conference on very large data bases (pp. 78\u201389). September 11\u201315, Zurich, Switzerland"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB13","doi-asserted-by":"crossref","unstructured":"Gravano, L., Garcia-Mol\u0131\u0301na, H., & Tomasic, A. (1994a). The effectiveness of GlOSS for the text database discovery problem. In Proceedings of SIGMOD 94 (pp. 126\u2013137). ACM","DOI":"10.1145\/191839.191869"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB14","doi-asserted-by":"crossref","unstructured":"Gravano, L., Garcia-Mol\u0131\u0301na, H., & Tomasic, A. (1994b). Precision and recall of GlOSS estimators for database discovery. In Proceedings of 3rd international conference on parallel and distributed information systems (pp. 103\u2013106). Austin, TX: IEEE-CS","DOI":"10.1109\/PDIS.1994.331726"},{"issue":"3","key":"10.1016\/S0306-4573(03)00008-6_BIB15","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/0306-4573(94)00047-7","article-title":"Overview of the second text retrieval conference (TREC-2)","volume":"31","author":"Harman","year":"1995","journal-title":"Information Processing and Management"},{"issue":"1","key":"10.1016\/S0306-4573(03)00008-6_BIB16","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1145\/297117.297123","article-title":"Methods for information server selection","volume":"17","author":"Hawking","year":"1999","journal-title":"ACM Transactions on Information Systems"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB17","doi-asserted-by":"crossref","unstructured":"Hawking, D., Voorhees, E., Crasswell, N., & Bailey, P. (2000). Overview of the TREC-8 web track. In E. Voorhees, & D. Harman (Eds.), Proceedings of eighth text retrieval conference (TREC-8) (pp. 131\u2013148). National Institute of Standards and Technology Special Publication 500-246, Washington","DOI":"10.6028\/NIST.SP.500-246"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB18","unstructured":"Larkey, L., Connell, M., & Callan, J. (2000). Collection selection and results merging with topically organized U.S. patents and TREC data. In Proceedings of the ninth ACM international conference on information and knowledge management (CIKM'00) (pp. 282\u2013289)"},{"issue":"1","key":"10.1016\/S0306-4573(03)00008-6_BIB19","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1145\/505282.505284","article-title":"Building efficient and effective metasearch engines","volume":"34","author":"Meng","year":"2002","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB20","doi-asserted-by":"crossref","unstructured":"Powell, A. L., French, J. C., Callan, J., Connell, M., & Viles, C. L. (2000). The impact of database selection on distributed searching. In Proceedings of the 23rd annual international ACM SIGIR conference on research and development in information retrieval (pp. 232\u2013239). ACM","DOI":"10.1145\/345508.345584"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB21","series-title":"Introduction to modern information retrieval","author":"Salton","year":"1983"},{"issue":"1","key":"10.1016\/S0306-4573(03)00008-6_BIB22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/505282.505283","article-title":"Machine learning in automated text categorization","volume":"34","author":"Sebastiani","year":"2002","journal-title":"ACM Computing Surveys"},{"issue":"3","key":"10.1016\/S0306-4573(03)00008-6_BIB23","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1002\/1097-4571(2000)9999:9999<::AID-ASI1591>3.0.CO;2-R","article-title":"Searching the web: the public and their queries","volume":"52","author":"Spink","year":"2001","journal-title":"Journal of the American Society of Information Science and Technology"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB24","doi-asserted-by":"crossref","unstructured":"Voorhees, E. (1996). The TREC-5 database merging track. In E. Voorhees, & D. Harman (Eds.), Proceedings of fifth TREC text retrieval conference (pp. 103\u2013104). National Institute of Standards and Technology Special Publication 500-238, Washington","DOI":"10.6028\/NIST.SP.500-238"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB25","doi-asserted-by":"crossref","unstructured":"Voorhees, E. M., Gupta, N. K., & Johnson-Laird, B. (1995). Learning collection fusion strategies. In E. A. Fox, P. Ingwersen, & R. Fidel (Eds.), Proceedings of the 18th annual international ACM SIGIR conference on research and development in information retrieval (pp. 172\u2013179)","DOI":"10.1145\/215206.215357"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB26","doi-asserted-by":"crossref","unstructured":"Xu, J., & Callan, J. P. (1998). Effective retrieval with distributed collections. In W. B. Croft, A. Moffat, C. J. van Rijsbergen, R. Wilkinson, & J. Zobel (Eds.), Proceedings of the 21st annual international ACM SIGIR conference on research and development in information retrieval (pp. 112\u2013120). ACM","DOI":"10.1145\/290941.290974"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB27","doi-asserted-by":"crossref","unstructured":"Yuwono, B., & Lee, D. L. (1997). Server ranking for distributed text retrieval systems on the internet. In Proceedings of the 5th international conference on database systems for advanced applications (DASFAA'97) (pp. 41\u201349). Melbourne, Vic., Australia","DOI":"10.1142\/9789812819536_0005"},{"key":"10.1016\/S0306-4573(03)00008-6_BIB28","unstructured":"Zobel, J. (1997). Collection selection via lexicon inspection. In Proceedings of the 2nd Australian document computing symposium (ADCS'97) (pp. 74\u201380). Melbourne, Vic., Australia"}],"container-title":["Information Processing &amp; Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457303000086?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457303000086?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T16:29:48Z","timestamp":1734020988000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457303000086"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004,5]]},"references-count":28,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2004,5]]}},"alternative-id":["S0306457303000086"],"URL":"https:\/\/doi.org\/10.1016\/s0306-4573(03)00008-6","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2004,5]]}}}