{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:11:19Z","timestamp":1775283079423,"version":"3.50.1"},"reference-count":31,"publisher":"Elsevier BV","issue":"11-16","license":[{"start":{"date-parts":[[1999,5,1]],"date-time":"1999-05-01T00:00:00Z","timestamp":925516800000},"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":["Computer Networks"],"published-print":{"date-parts":[[1999,5]]},"DOI":"10.1016\/s1389-1286(99)00052-3","type":"journal-article","created":{"date-parts":[[2002,7,26]],"date-time":"2002-07-26T02:32:32Z","timestamp":1027650752000},"page":"1623-1640","source":"Crossref","is-referenced-by-count":810,"title":["Focused crawling: a new approach to topic-specific Web resource discovery"],"prefix":"10.1016","volume":"31","author":[{"given":"Soumen","family":"Chakrabarti","sequence":"first","affiliation":[]},{"given":"Martin","family":"van den Berg","sequence":"additional","affiliation":[]},{"given":"Byron","family":"Dom","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S1389-1286(99)00052-3_BIB1","unstructured":"M. Ackerman, D. Billsus, S. Gaffney, S. Hettich, G. Khoo, D. Kim, R. Klefstad, C. Lowe, A. Ludeman, J. Muramatsu, K. Omori, M. Pazzani, D. Semler, B. Starr and P. Yap, Learning probabilistic user profiles: applications to finding interesting web sites, notifying users of relevant changes to web pages, and locating grant opportunities, AI Magazine 18(2): 47\u201356, 1997, online at http:\/\/www.ics.uci.edu\/~pazzani\/Publications\/AI-MAG.pdf"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB2","doi-asserted-by":"crossref","unstructured":"K. Bharat and A. Broder, A technique for measuring the relative size and overlap of public web search engines, in: Proc. of the 7th World-Wide Web Conference (WWW7), 1998, online at http:\/\/www7.scu.edu.au\/programme\/fullpapers\/1937\/com1937.htm; also see an update at http:\/\/www.research.digital.com\/SRC\/whatsnew\/sem.html","DOI":"10.1016\/S0169-7552(98)00127-5"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB3","doi-asserted-by":"crossref","unstructured":"K. Bharat and M. Henzinger, Improved algorithms for topic distillation in a hyperlinked environment, in: SIGIR Conference on Research and Development in Information Retrieval, vol. 21. ACM, 1998, online at ftp:\/\/ftp.digital.com\/pub\/DEC\/SRC\/publications\/monika\/sigir98.pdf","DOI":"10.1145\/290941.290972"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB4","doi-asserted-by":"crossref","unstructured":"S. Brin and L. Page, The anatomy of a large-scale hypertextual web search engine, in: Proc. of the 7th World-Wide Web WWW Conference, 1998, online at http:\/\/google.stanford.edu\/~backrub\/google.html","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB5","doi-asserted-by":"crossref","unstructured":"S. Chakrabarti, B. Dom, R. Agrawal and P. Raghavan, Scalable feature selection, classification and signature generation for organizing large text databases into hierarchical topic taxonomies, VLDB Journal 7(3): 163\u2013178, 1998.","DOI":"10.1007\/s007780050061"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB6","doi-asserted-by":"crossref","unstructured":"S. Chakrabarti, B. Dom, D. Gibson, J. Kleinberg, P. Raghavan and S. Rajagopalan, Automatic resource compilation by analyzing hyperlink structure and associated text, in: Proc. of the 7th World-Wide Web Conference (WWW7), 1998, online at http:\/\/www7.scu.edu.au\/programme\/fullpapers\/1898\/com1898.html and at http:\/\/www.almaden.ibm.com\/cs\/people\/pragh\/www98\/438.html","DOI":"10.1016\/S0169-7552(98)00087-7"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB7","doi-asserted-by":"crossref","unstructured":"S. Chakrabarti, B. Dom and P. Indyk, Enhanced hypertext categorization using hyperlinks, in: SIGMOD. ACM, 1998, online at http:\/\/www.cs.berkeley.edu\/~soumen\/sigmod98.ps.","DOI":"10.1145\/276304.276332"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB8","doi-asserted-by":"crossref","unstructured":"S. Chakrabarti, D. Gibson and K. McCurley, Surfing the web backwards, in: 8th World Wide Web Conference, Toronto, Canada, May 1999.","DOI":"10.1016\/S1389-1286(99)00042-0"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB9","doi-asserted-by":"crossref","unstructured":"S. Chakrabarti, M. van den Berg and B. Dom, Distributed hypertext resource discovery through examples, Submitted to VLDB, Feb. 1999.","DOI":"10.1016\/S1389-1286(99)00052-3"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB10","doi-asserted-by":"crossref","unstructured":"H. Chen, Y.-M. Chung, M. Ramsey and C.C. Yang, A smart itsy bitsy spider for the web, J. Am. Soc. Inf. Sci. 49(7): 604\u2013618, 1998.","DOI":"10.1002\/(SICI)1097-4571(19980515)49:7<604::AID-ASI3>3.0.CO;2-T"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB11","unstructured":"F.-C. Cheong, Internet Agents: Spiders, Wanderers, Brokers and Bots, New Riders Publishing, Indianapolis, IN, 1996. ISBN: 1-56205-463-5."},{"key":"10.1016\/S1389-1286(99)00052-3_BIB12","doi-asserted-by":"crossref","unstructured":"J. Cho, H. Garcia-Molina and L. Page, Efficient crawling through URL ordering, in: 7th World Wide Web Conference, Brisbane, Australia, Apr. 1998, online at http:\/\/www7.scu.edu.au\/programme\/fullpapers\/1919\/com1919.htm","DOI":"10.1016\/S0169-7552(98)00108-1"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB13","doi-asserted-by":"crossref","unstructured":"J. Dean and M.R. Henzinger, Finding related pages in the world wide web, in: 8th World Wide Web Conference, Toronto, May 1999.","DOI":"10.1016\/S1389-1286(99)00022-5"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB14","doi-asserted-by":"crossref","unstructured":"P. DeBra and R. Post, Information retrieval in the world-wide web: making client-based searching feasible, in: Proc. of the 1st International World Wide Web Conference, Geneva, Switzerland, 1994.","DOI":"10.1016\/0169-7552(94)90132-5"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB15","unstructured":"O. Etzioni, Moving up the information food chain: deploying softbots on the world wide web, in: Proc. of AAAI-96, 1996."},{"key":"10.1016\/S1389-1286(99)00052-3_BIB16","unstructured":"D. Gillmor, Small portals prove that size matters, Tech column in San Jose Mercury News, December 1998, online at http:\/\/www.sjmercury.com\/columnists\/gillmor\/docs\/dg120698.htm and http:\/\/www.cs.berkeley.edu\/~soumen\/focus\/DanGillmor19981206.htm."},{"key":"10.1016\/S1389-1286(99)00052-3_BIB17","doi-asserted-by":"crossref","unstructured":"M. Hersovici, M. Jacovi, Y.S. Maarek, D. Pelleg, M. Shtalheim, S. Ur, The Shark Search algorithm - An application: Tailored web site mappping, 7th World-Wide Web Conference, 1998, Brisbane, Australia, april, online at: http:www.7scu.edu.au\/programme\/fullpapers\/1849\/com1849.htm","DOI":"10.1016\/S0169-7552(98)00038-5"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB18","unstructured":"T. Joachims, D. Freitag and T. Mitchell, WebWatcher: a tour guide for the web, in: IJCAI, August 1997, online at http:\/\/www.cs.cmu.edu\/~webwatcher\/ijcai97.ps"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB19","doi-asserted-by":"crossref","unstructured":"B. Kahle, Preserving the Internet, Scientific American, March 1997, online at http:\/\/www.sciam.com\/0397issue\/0397kahle.html and http:\/\/www.alexa.com\/~brewster\/essays\/sciam_article.html","DOI":"10.1038\/scientificamerican0397-82"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB20","doi-asserted-by":"crossref","unstructured":"L. Katz, A new status index derived from sociometric analysis, Psychometrika 18(1): 39\u201343, March 1953.","DOI":"10.1007\/BF02289026"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB21","unstructured":"J. Kleinberg, Authoritative sources in a hyperlinked environment, in: Proc. ACM-SIAM Symposium on Discrete Algorithms, 1998, also appears as IBM Research Report RJ 10076(91892) and online at http:\/\/www.cs.cornell.edu\/home\/kleinber\/auth.ps"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB22","doi-asserted-by":"crossref","unstructured":"S. Lawrence and C.L. Giles, Searching the world wide web, Science 280: 98\u2013100, April 1998.","DOI":"10.1126\/science.280.5360.98"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB23","unstructured":"S. Macskassy, A. Banerjee, B. Davidson and H. Hirsh, Human performance on clustering web pages: a performance study, in: Knowledge Discovery and Data Mining, vol. 4, pp. 264\u2013268, 1998."},{"key":"10.1016\/S1389-1286(99)00052-3_BIB24","doi-asserted-by":"crossref","unstructured":"M. Marchiori, The quest for correct information on the web: hyper search engines, in: Proc. of the 6th International World Wide Web Conference, Santa Clara, April 1997.","DOI":"10.1016\/S0169-7552(97)00036-6"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB25","doi-asserted-by":"crossref","unstructured":"M.S. Mizruchi, P. Mariolis, M. Schwartz and B. Mintz, Techniques for disaggregating centrality scores in social networks, in: N.B. Tuma (Ed.), Sociological Methodology, pp. 26\u201348, Jossey-Bass, San Francisco, 1986.","DOI":"10.2307\/270918"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB26","doi-asserted-by":"crossref","unstructured":"K. Nigam, A. McCallum, S. Thrun and T. Mitchell, Text classification from labeled and unlabeled documents using EM, Machine Learning, 1999, online at http:\/\/www.cs.cmu.edu\/~knigam\/papers\/emcat-mlj99.ps.gz","DOI":"10.21236\/ADA350490"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB27","doi-asserted-by":"crossref","unstructured":"M. Pazzani, L. Nguyen and S. Mantik, Learning from hotlists and coldlists: towards a WWW information filtering and seeking agent, in: 7th International Conference on Tools with Artificial Intelligence, 1995, online at http:\/\/www.ics.uci.edu\/~pazzani\/Publications\/Coldlist.pdf","DOI":"10.1109\/TAI.1995.479848"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB28","doi-asserted-by":"crossref","unstructured":"J. Shakes, M. Langheinrich and O. Etzioni, Dynamic reference sifting: a case study in the homepage domain, in: Proc. of the 6th World-Wide Web Conference (WWW6), 1997.","DOI":"10.1016\/S0169-7552(97)00048-2"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB29","unstructured":"C. Silverstein, M. Henzinger, H. Marais and M. Moricz, Analysis of a very large AltaVista query log, Technical Report 1998-014, COMPAQ System Research Center, October 1998, online at http:\/\/gatekeeper.dec.com\/pub\/DEC\/SRC\/technical-notes\/abstracts\/src-tn-1998-014.html"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB30","doi-asserted-by":"crossref","unstructured":"L. Terveen and W. Hill, Finding and visualizing inter-site clan graphs, in: Computer Human Interaction (CHI), pp. 448\u2013455, Los Angeles, CA, April 1998, ACM SIGCHI, online at http:\/\/www.research.att.com\/~terveen\/chi98.htm and http:\/\/www.acm.org\/pubs\/articles\/proceedings\/chi\/274644\/p448-terveen\/p4 48-terveen.pdf","DOI":"10.1145\/274644.274705"},{"key":"10.1016\/S1389-1286(99)00052-3_BIB31","doi-asserted-by":"crossref","unstructured":"S. Wasserman and K. Faust, Social Network Analysis, Cambridge University Press, 1994.","DOI":"10.1017\/CBO9780511815478"}],"container-title":["Computer Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1389128699000523?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1389128699000523?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T00:49:25Z","timestamp":1681692565000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1389128699000523"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,5]]},"references-count":31,"journal-issue":{"issue":"11-16","published-print":{"date-parts":[[1999,5]]}},"alternative-id":["S1389128699000523"],"URL":"https:\/\/doi.org\/10.1016\/s1389-1286(99)00052-3","relation":{},"ISSN":["1389-1286"],"issn-type":[{"value":"1389-1286","type":"print"}],"subject":[],"published":{"date-parts":[[1999,5]]}}}