{"id":"https://openalex.org/W2018928332","doi":"https://doi.org/10.1145/371920.371960","title":"An adaptive model for optimizing performance of an incremental web crawler","display_name":"An adaptive model for optimizing performance of an incremental web crawler","publication_year":2001,"publication_date":"2001-04-01","ids":{"openalex":"https://openalex.org/W2018928332","doi":"https://doi.org/10.1145/371920.371960","mag":"2018928332"},"language":"en","primary_location":{"id":"doi:10.1145/371920.371960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/371920.371960","pdf_url":null,"source":null,"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"},"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/A5090114374","display_name":"Jenny Edwards","orcid":"https://orcid.org/0000-0002-7105-997X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jenny Edwards","raw_affiliation_strings":["Faculty of Information, Technology, University of Technology, Sydney, PO Box 123, Broadway NSW 2007, Australia","Faculty of Information Technology, University of Technology, Sydney, PO Box 123 Broadway, NSW 2007 Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"Faculty of Information, Technology, University of Technology, Sydney, PO Box 123, Broadway NSW 2007, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"Faculty of Information Technology, University of Technology, Sydney, PO Box 123 Broadway, NSW 2007 Australia#TAB#","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033733709","display_name":"Kevin S. McCurley","orcid":"https://orcid.org/0000-0001-7890-5430"},"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":"Kevin McCurley","raw_affiliation_strings":["IBM Research Division, Almaden Research Center, K53/802, 650 Harry Road, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Research Division, Almaden Research Center, K53/802, 650 Harry Road, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111991767","display_name":"John A. Tomlin","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":"John Tomlin","raw_affiliation_strings":["IBM Research Division, Almaden Research Center, K53/802, 650 Harry Road, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Research Division, Almaden Research Center, K53/802, 650 Harry Road, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090114374"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":30.3648,"has_fulltext":false,"cited_by_count":223,"citation_normalized_percentile":{"value":0.99422031,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"106","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T11478","display_name":"Caching and Content Delivery","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/ibm","display_name":"IBM","score":0.9019491672515869},{"id":"https://openalex.org/keywords/research-center","display_name":"Research center","score":0.7936344146728516},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.5476883053779602},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.5065006017684937},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.4857197403907776},{"id":"https://openalex.org/keywords/publishing","display_name":"Publishing","score":0.4842934012413025},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4522552490234375},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43184319138526917},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3697383403778076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.312982439994812},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.10143101215362549}],"concepts":[{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.9019491672515869},{"id":"https://openalex.org/C2777532764","wikidata":"https://www.wikidata.org/wiki/Q31855","display_name":"Research center","level":2,"score":0.7936344146728516},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.5476883053779602},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.5065006017684937},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.4857197403907776},{"id":"https://openalex.org/C151719136","wikidata":"https://www.wikidata.org/wiki/Q3972943","display_name":"Publishing","level":2,"score":0.4842934012413025},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4522552490234375},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43184319138526917},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3697383403778076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.312982439994812},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.10143101215362549},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/371920.371960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/371920.371960","pdf_url":null,"source":null,"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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1018.1506","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1018.1506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://opus.lib.uts.edu.au/bitstream/10453/7045/1/2005001093.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.8164","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.8164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www10.org/cdrom/papers/pdf/p210.pdf","raw_type":"text"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/7045","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/7045","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1546842576","https://openalex.org/W1566984846","https://openalex.org/W1613836731","https://openalex.org/W1987272746","https://openalex.org/W2029341294","https://openalex.org/W2059713800","https://openalex.org/W2066636486","https://openalex.org/W2067338315","https://openalex.org/W2099126271","https://openalex.org/W2152565070","https://openalex.org/W4251434705"],"related_works":["https://openalex.org/W2016917647","https://openalex.org/W2027780767","https://openalex.org/W1979461377","https://openalex.org/W2064146555","https://openalex.org/W2084686108","https://openalex.org/W2062285040","https://openalex.org/W2111444092","https://openalex.org/W2090903439","https://openalex.org/W1986355004","https://openalex.org/W4250301243"],"abstract_inverted_index":{"This":[0,25,146],"paper":[1],"outlines":[2],"the":[3,22,37,63,151,164],"design":[4],"of":[5,40,109],"a":[6,107],"web":[7,41],"crawler":[8,26],"implemented":[9],"for":[10,20,62],"IBM":[11,156],"Almaden&amp;apos;s":[12],"WebFountain":[13],"project":[14],"and":[15,29,112,117,122],"describes":[16],"an":[17,47],"optimization":[18,144],"model":[19,32],"controlling":[21],"crawl":[23],"strategy.":[24],"is":[27,75,161],"scalable":[28],"incremental.":[30],"The":[31],"makes":[33],"no":[34,76],"assumptions":[35],"about":[36],"statistical":[38],"behaviour":[39],"page":[42],"changes,":[43],"but":[44,69,81],"rather":[45],"uses":[46],"adaptive":[48],"approachtomaintain":[49],"data":[50,71],"on":[51,154],"actual":[52],"change":[53],"rates":[54],"which":[55,98],"are":[56,95,104],"in":[57],"turn":[58],"used":[59],"as":[60],"inputs":[61],"optimization.":[64],"Computational":[65],"results":[66],"with":[67],"simulated":[68],"realistic":[70],"show":[72],"that":[73,93,103],"there":[74,94],"`magic":[77],"bullet&amp;apos;":[78],"-":[79],"different,":[80],"equally":[82],"plausible,":[83],"objectives":[84,97],"lead":[85,99],"to":[86,100],"conicting":[87],"`optimal&amp;apos;":[88],"strategies.":[89],"However,":[90],"we":[91],"nd":[92],"compromise":[96],"good":[101],"strategies":[102],"robust":[105],"against":[106],"number":[108],"criteria.":[110],"Categories":[111],"Subject":[113],"Descriptors":[114],"H3.4":[115],"[Systems":[116],"Software]:":[118],"Performance":[119,138],"Evaluation":[120],"(eciency":[121],"eectiveness);":[123],"H4.3":[124],"[Communications":[125],"Applications":[126],"]:":[127],"Information":[128],"Browsers;":[129],"G1.6":[130],"[Optimization]:":[131],"Nonlinear":[132],"Programming":[133],"General":[134],"Terms":[135],"Algorithms,":[136],"Experimentation,":[137],"Keywords":[139],"Crawler,":[140],"incremental":[141],"crawler,":[142],"scalability,":[143],"#":[145],"work":[147],"was":[148,153],"completed":[149],"while":[150],"author":[152],"leaveat":[155],"Almaden":[157],"Research":[158],"Center.":[159],"Copyright":[160],"held":[162],"by":[163],"author/owner.":[165],"WWW10,":[166],"May":[167],"1-5,":[168],"2001,":[169],"Hong":[170],"Kong.":[171],"ACM":[172],"1-58113-348-0/01/0005.":[173],"1.":[174]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":12}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
