{"id":"https://openalex.org/W2103545802","doi":"https://doi.org/10.1145/1571941.1572041","title":"The impact of crawl policy on web search effectiveness","display_name":"The impact of crawl policy on web search effectiveness","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2103545802","doi":"https://doi.org/10.1145/1571941.1572041","mag":"2103545802"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1572041","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","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/A5060832606","display_name":"Dennis Fetterly","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dennis Fetterly","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA","Microsoft Research, Mountain View, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055132321","display_name":"Nick Craswell","orcid":"https://orcid.org/0000-0002-9351-8137"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Nick Craswell","raw_affiliation_strings":["Microsoft Research, Cambridge, United Kingdom","Microsoft Research, Cambridge, United Kingdom ("],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research, Cambridge, United Kingdom (","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022536276","display_name":"Vishwa Vinay","orcid":"https://orcid.org/0000-0002-4043-9953"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Vishwa Vinay","raw_affiliation_strings":["Microsoft Research, Cambridge, United Kingdom","Microsoft Research, Cambridge, United Kingdom ("],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research, Cambridge, United Kingdom (","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060832606"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":6.9867,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.96866874,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"580","last_page":"587"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9864000082015991,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9563999772071838,"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/pagerank","display_name":"PageRank","score":0.8479301929473877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7576422691345215},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7437868118286133},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6915947794914246},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.6612995862960815},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6371443271636963},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.5657104253768921},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5594026446342468},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5445488095283508},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5201224088668823},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4636697769165039},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4311394989490509},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40659433603286743},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3915254473686218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.340711772441864},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.2895095944404602},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1989685297012329},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14939850568771362}],"concepts":[{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.8479301929473877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576422691345215},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7437868118286133},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6915947794914246},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.6612995862960815},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6371443271636963},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5657104253768921},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5594026446342468},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5445488095283508},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5201224088668823},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4636697769165039},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4311394989490509},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40659433603286743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3915254473686218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.340711772441864},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2895095944404602},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1989685297012329},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14939850568771362},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1571941.1572041","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.150.3757","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.150.3757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/81492/fp083-fetterly.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W182781187","https://openalex.org/W1495124840","https://openalex.org/W1566984846","https://openalex.org/W1969301668","https://openalex.org/W2002053721","https://openalex.org/W2026706800","https://openalex.org/W2029341294","https://openalex.org/W2069870183","https://openalex.org/W2097704339","https://openalex.org/W2099768249","https://openalex.org/W2102914327","https://openalex.org/W2113184419","https://openalex.org/W2117850397","https://openalex.org/W2119012894","https://openalex.org/W2128384372","https://openalex.org/W2145990704","https://openalex.org/W2157748587","https://openalex.org/W2158601853","https://openalex.org/W2169557227","https://openalex.org/W2172189174"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2375180657","https://openalex.org/W4248730791","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W2372594123"],"abstract_inverted_index":{"Crawl":[0],"selection":[1,79,104,158],"policy":[2],"has":[3,30],"a":[4,12,63,118],"direct":[5],"influence":[6],"on":[7,36,46,106],"Web":[8],"search":[9,26,52],"effectiveness,":[10],"because":[11],"useful":[13],"page":[14,162],"that":[15,59,102],"is":[16,60,127,145],"not":[17],"selected":[18],"for":[19],"crawling":[20,89],"will":[21],"also":[22],"be":[23],"absent":[24],"from":[25,50],"results.":[27],"Yet":[28],"there":[29],"been":[31],"little":[32],"or":[33],"no":[34],"work":[35],"measuring":[37,54],"this":[38],"effect.":[39],"We":[40,84],"introduce":[41],"an":[42],"evaluation":[43],"framework,":[44],"based":[45,105],"relevance":[47],"judgments":[48],"pooled":[49],"multiple":[51,82,141],"engines,":[53],"the":[55,92,123,128],"maximum":[56],"potential":[57,169],"NDCG":[58,170],"achievable":[61],"using":[62],"particular":[64],"crawl.":[65],"This":[66],"allows":[67],"us":[68],"to":[69],"evaluate":[70],"different":[71],"crawl":[72,103,121,142,157],"policies":[73],"and":[74,96,109,131,148,160],"investigate":[75],"important":[76],"scenarios":[77],"like":[78],"stability":[80],"over":[81,140],"iterations.":[83],"conduct":[85],"two":[86],"sets":[87],"of":[88,94,122,156],"experiments":[90],"at":[91],"scale":[93],"1~billion":[95],"100~million":[97],"pages":[98],"respectively.":[99],"These":[100],"show":[101],"PageRank,":[107,138],"indegree":[108,111,135],"trans-domain":[110],"all":[112],"allow":[113],"better":[114],"retrieval":[115],"effectiveness":[116],"than":[117,171],"simple":[119],"breadth-first":[120],"same":[124],"size.":[125],"PageRank":[126],"most":[129],"reliable":[130],"effective":[132,147],"method.":[133],"Trans-domain":[134],"can":[136],"outperform":[137],"but":[139],"iterations":[143],"it":[144],"less":[146],"more":[149],"unstable.":[150],"Finally":[151],"we":[152],"experiment":[153],"with":[154,167],"combinations":[155],"methods":[159],"per-domain":[161],"limits,":[163],"which":[164],"yield":[165],"crawls":[166],"greater":[168],"PageRank.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}