{"id":"https://openalex.org/W1489992655","doi":"https://doi.org/10.1016/s1389-1286(99)00052-3","title":"Focused crawling: a new approach to topic-specific Web resource discovery","display_name":"Focused crawling: a new approach to topic-specific Web resource discovery","publication_year":1999,"publication_date":"1999-05-01","ids":{"openalex":"https://openalex.org/W1489992655","doi":"https://doi.org/10.1016/s1389-1286(99)00052-3","mag":"1489992655"},"language":"en","primary_location":{"id":"doi:10.1016/s1389-1286(99)00052-3","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s1389-1286(99)00052-3","pdf_url":null,"source":{"id":"https://openalex.org/S63392143","display_name":"Computer Networks","issn_l":"1389-1286","issn":["1389-1286","1872-7069"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101457009","display_name":"Soumen Chakrabarti","orcid":"https://orcid.org/0000-0002-9419-7486"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Soumen Chakrabarti","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology, Bombay, 400076, India"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology, Bombay, 400076, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083828758","display_name":"Martin van den Berg","orcid":"https://orcid.org/0000-0001-6239-6301"},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin van den Berg","raw_affiliation_strings":["FX Palo Alto Laboratory, 3400 Hillview Ave, Bldg 4, Palo Alto, CA 94304, USA"],"affiliations":[{"raw_affiliation_string":"FX Palo Alto Laboratory, 3400 Hillview Ave, Bldg 4, Palo Alto, CA 94304, USA","institution_ids":["https://openalex.org/I26274970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031458509","display_name":"Byron Dom","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byron Dom","raw_affiliation_strings":["IBM Almaden Research Center, 650 Harry Rd, San Jose, CA 95120, USA","IBM Almaden Research Center, 650 Harry Rd., San Jose, CA 95120, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, 650 Harry Rd, San Jose, CA 95120, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center, 650 Harry Rd., San Jose, CA 95120, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101457009"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":{"value":2370,"currency":"USD","value_usd":2370},"apc_paid":null,"fwci":122.3213,"has_fulltext":false,"cited_by_count":1492,"citation_normalized_percentile":{"value":0.99980081,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"31","issue":"11-16","first_page":"1623","last_page":"1640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9627000093460083,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9627000093460083,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.012900000438094139,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.9129917621612549},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.908890426158905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8474411964416504},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.7311708927154541},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7075949311256409},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5840392708778381},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.49039220809936523},{"id":"https://openalex.org/keywords/hypertext","display_name":"Hypertext","score":0.483825147151947},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4760477542877197},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.4653162956237793},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.45281898975372314},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4290597438812256},{"id":"https://openalex.org/keywords/web-resource","display_name":"Web resource","score":0.41151219606399536},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.22703760862350464},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.16530364751815796}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9129917621612549},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.908890426158905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8474411964416504},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.7311708927154541},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7075949311256409},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5840392708778381},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.49039220809936523},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.483825147151947},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4760477542877197},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.4653162956237793},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.45281898975372314},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4290597438812256},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.41151219606399536},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.22703760862350464},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.16530364751815796},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1016/s1389-1286(99)00052-3","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s1389-1286(99)00052-3","pdf_url":null,"source":{"id":"https://openalex.org/S63392143","display_name":"Computer Networks","issn_l":"1389-1286","issn":["1389-1286","1872-7069"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Networks","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.43.1111","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.1111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~soumen/doc/www1999f/pdf/www1999f.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.83.9370","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.83.9370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mainline.brynmawr.edu/Courses/cs380/fall2006/prelim.pdf","raw_type":"text"},{"id":"pmh:oai:dsapce.library.iitb.ac.in:10054/1305","is_oa":false,"landing_page_url":"http://dspace.library.iitb.ac.in/xmlui/handle/10054/1305","pdf_url":null,"source":{"id":"https://openalex.org/S4306400899","display_name":"DSpace (IIT Bombay)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162827531","host_organization_name":"Indian Institute of Technology Bombay","host_organization_lineage":["https://openalex.org/I162827531"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:dspace.library.iitb.ac.in:10054/1305","is_oa":false,"landing_page_url":"http://hdl.handle.net/10054/1305","pdf_url":null,"source":{"id":"https://openalex.org/S4306400899","display_name":"DSpace (IIT Bombay)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162827531","host_organization_name":"Indian Institute of Technology Bombay","host_organization_lineage":["https://openalex.org/I162827531"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W128720162","https://openalex.org/W157562232","https://openalex.org/W950821216","https://openalex.org/W1489992655","https://openalex.org/W1538805611","https://openalex.org/W1549392931","https://openalex.org/W1582583141","https://openalex.org/W1605217017","https://openalex.org/W1968642292","https://openalex.org/W1971788485","https://openalex.org/W1987777228","https://openalex.org/W1998102571","https://openalex.org/W2001832505","https://openalex.org/W2003000928","https://openalex.org/W2006119904","https://openalex.org/W2012516036","https://openalex.org/W2026417691","https://openalex.org/W2029341294","https://openalex.org/W2040041305","https://openalex.org/W2044743392","https://openalex.org/W2049961212","https://openalex.org/W2054119298","https://openalex.org/W2066636486","https://openalex.org/W2076008912","https://openalex.org/W2079333567","https://openalex.org/W2079672501","https://openalex.org/W2082751088","https://openalex.org/W2089192108","https://openalex.org/W2097089247","https://openalex.org/W2126064812","https://openalex.org/W2126631147","https://openalex.org/W2127169217","https://openalex.org/W2138621811","https://openalex.org/W2147164982","https://openalex.org/W2155033358","https://openalex.org/W2161956524","https://openalex.org/W2322524800","https://openalex.org/W2795444554","https://openalex.org/W4210407477","https://openalex.org/W4240407914","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2375180657","https://openalex.org/W2042034567","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2274831913","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W1506122440"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":39},{"year":2017,"cited_by_count":49},{"year":2016,"cited_by_count":55},{"year":2015,"cited_by_count":47},{"year":2014,"cited_by_count":81},{"year":2013,"cited_by_count":89},{"year":2012,"cited_by_count":81}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
