{"id":"https://openalex.org/W2007687650","doi":"https://doi.org/10.1145/371920.371965","title":"Breadth-first crawling yields high-quality pages","display_name":"Breadth-first crawling yields high-quality pages","publication_year":2001,"publication_date":"2001-04-01","ids":{"openalex":"https://openalex.org/W2007687650","doi":"https://doi.org/10.1145/371920.371965","mag":"2007687650"},"language":"en","primary_location":{"id":"doi:10.1145/371920.371965","doi":"https://doi.org/10.1145/371920.371965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/371920.371965","pdf_url":null,"source":{"id":"https://openalex.org/S7407088480","display_name":"International World Wide Web Conference (WWW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th international conference on World Wide Web","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2007687650"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5037200145","display_name":"Marc Najork","orcid":"https://orcid.org/0000-0003-1423-0854","observed_orcids":["https://orcid.org/0000-0003-1423-0854"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Najork","raw_affiliation_strings":["Compaq Systems Research Center, 130 Lytton Avenue, Palo Alto, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Compaq Systems Research Center, 130 Lytton Avenue, Palo Alto, CA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113681033","display_name":"Janet L. Wiener","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Janet L. Wiener","raw_affiliation_strings":["Compaq Systems Research Center, 130 Lytton Avenue, Palo Alto, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Compaq Systems Research Center, 130 Lytton Avenue, Palo Alto, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.5225,"has_fulltext":false,"cited_by_count":267,"citation_normalized_percentile":{"value":0.98839571,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"114","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9897000193595886,"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":0.9897000193595886,"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":0.009499999694526196,"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/T13976","display_name":"Web visibility and informetrics","score":0.00019999999494757503,"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/web-crawling","display_name":"web crawling","score":0.9079999923706055},{"id":"https://openalex.org/keywords/search-engines","display_name":"search engines","score":0.5180000066757202},{"id":"https://openalex.org/keywords/web-page-ranking","display_name":"web page ranking","score":0.3160000145435333}],"concepts":[{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.6912680268287659},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.6341249942779541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5137234926223755},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43269580602645874},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40795010328292847},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.39279165863990784},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.08986788988113403},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06972256302833557},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/371920.371965","doi":"https://doi.org/10.1145/371920.371965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/371920.371965","pdf_url":null,"source":{"id":"https://openalex.org/S7407088480","display_name":"International World Wide Web Conference (WWW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1613836731","https://openalex.org/W1976232673","https://openalex.org/W1981202432","https://openalex.org/W1983416950","https://openalex.org/W1996709455","https://openalex.org/W2029341294","https://openalex.org/W2066636486","https://openalex.org/W4248184695"],"related_works":["https://openalex.org/W1674850363","https://openalex.org/W7096068129","https://openalex.org/W2110073539","https://openalex.org/W7099805190","https://openalex.org/W14315322","https://openalex.org/W6980827293","https://openalex.org/W7100213608","https://openalex.org/W7095232568","https://openalex.org/W2095543197"],"abstract_inverted_index":{"Article":[0],"Breadth-first":[1],"crawling":[2],"yields":[3],"high-quality":[4],"pages":[5],"Share":[6],"on":[7,69,120],"Authors:":[8],"Marc":[9],"Najork":[10],"Compaq":[11,21,36,46],"Systems":[12,22,37,47],"Research":[13,23,38,48],"Center,":[14,24,39,49],"130":[15,25,40,50],"Lytton":[16,26,41,51],"Avenue,":[17,27,42,52],"Palo":[18,28,43,53],"Alto,":[19,29,44,54],"CA":[20,45],"CAView":[30,55],"Profile":[31,56],",":[32],"Janet":[33],"L.":[34],"Wiener":[35],"Authors":[57],"Info":[58],"&":[59],"Claims":[60],"WWW":[61],"'01:":[62],"Proceedings":[63],"of":[64],"the":[65,121],"10th":[66],"international":[67],"conference":[68],"World":[70],"Wide":[71],"WebMay":[72],"2001":[73],"Pages":[74],"114\u2013118https://doi.org/10.1145/371920.371965Online:01":[75],"April":[76],"2001Publication":[77],"History":[78],"187citation1,650DownloadsMetricsTotal":[79],"Citations187Total":[80],"Downloads1,650Last":[81],"12":[82],"Months60Last":[83],"6":[84],"weeks4":[85],"Get":[86],"Citation":[87,89,126],"AlertsNew":[88,125],"Alert":[90],"added!This":[91],"alert":[92,117],"has":[93,112],"been":[94,113],"successfully":[95],"added":[96],"and":[97],"will":[98,102],"be":[99,103],"sent":[100],"to:You":[101],"notified":[104],"whenever":[105],"a":[106,138],"record":[107],"that":[108],"you":[109],"have":[110],"chosen":[111],"cited.To":[114],"manage":[115],"your":[116,131],"preferences,":[118],"click":[119],"button":[122],"below.Manage":[123],"my":[124],"Alert!Please":[127],"log":[128],"in":[129],"to":[130,134,136],"account":[132],"Save":[133],"BinderSave":[135],"BinderCreate":[137],"New":[139],"BinderNameCancelCreateExport":[140],"CitationPublisher":[141],"SiteGet":[142],"Access":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":9}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}
