{"id":"https://openalex.org/W2151932833","doi":"https://doi.org/10.1145/1060745.1060805","title":"User-centric Web crawling","display_name":"User-centric Web crawling","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2151932833","doi":"https://doi.org/10.1145/1060745.1060805","mag":"2151932833"},"language":"en","primary_location":{"id":"doi:10.1145/1060745.1060805","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th international conference on World Wide Web - WWW '05","raw_type":"proceedings-article"},"type":"conference-paper","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/A5042339206","display_name":"Sandeep Pandey","orcid":"https://orcid.org/0000-0003-1995-6515"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Pandey","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109881550","display_name":"Christopher Olston","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Olston","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":7.33,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.97895928,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9897000193595886,"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/T12288","display_name":"Optimization and Search Problems","score":0.984499990940094,"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/crawling","display_name":"Crawling","score":0.7675564885139465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7285321950912476},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6436077952384949}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7675564885139465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285321950912476},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6436077952384949},{"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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/1060745.1060805","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th international conference on World Wide Web - WWW '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.3444","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.3444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://asso-aria.org/coria/2007/35.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.9242","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.9242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-db.stanford.edu/%7Eolston/publications/crawling_survey.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.178.344","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.178.344","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/121136/1500000017.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.9676","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.9676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~olston/publications/userCentricCrawling.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.6287","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.6287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2005.org/cdrom/docs/p401.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":33,"referenced_works":["https://openalex.org/W63649906","https://openalex.org/W73128518","https://openalex.org/W116750838","https://openalex.org/W133089299","https://openalex.org/W135168798","https://openalex.org/W162491510","https://openalex.org/W1489992655","https://openalex.org/W1524983059","https://openalex.org/W1566984846","https://openalex.org/W1604437383","https://openalex.org/W1761828760","https://openalex.org/W1854214752","https://openalex.org/W1976641326","https://openalex.org/W1987272746","https://openalex.org/W2006479099","https://openalex.org/W2007842132","https://openalex.org/W2018928332","https://openalex.org/W2030453570","https://openalex.org/W2047221353","https://openalex.org/W2066636486","https://openalex.org/W2075006521","https://openalex.org/W2086453025","https://openalex.org/W2095927587","https://openalex.org/W2112051977","https://openalex.org/W2138621811","https://openalex.org/W2152565070","https://openalex.org/W2154724067","https://openalex.org/W2157748587","https://openalex.org/W2158676623","https://openalex.org/W2166743161","https://openalex.org/W2325227998","https://openalex.org/W2743788926","https://openalex.org/W2892228776"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2358547986","https://openalex.org/W2078475175","https://openalex.org/W2319283426","https://openalex.org/W2558137253","https://openalex.org/W2159872134","https://openalex.org/W2141869928","https://openalex.org/W4299833833","https://openalex.org/W1974064905","https://openalex.org/W2795447506"],"abstract_inverted_index":{"Search":[0],"engines":[1,17],"are":[2],"the":[3,10,14,19,40,68,77,97,123,126,133,143,147,150,153,156,160,164,167,178,216,228,235,287],"primary":[4],"gateways":[5],"of":[6,27,48,54,74,76,125,142,152,159,166,177,180,208,219,222,243],"information":[7],"access":[8],"on":[9,215],"Web":[11,20,28,41,49,78,107,162,196,223,249,255,284],"today.":[12],"Behind":[13],"scenes,":[15],"search":[16,34,88,114,134,182,203,270,288],"crawl":[18],"to":[21,31,51,65,90,105,121,173,190,233,267],"populate":[22],"a":[23,80,87,113,139,174,181,192],"local":[24,184],"indexed":[25],"repository":[26,47,93,154],"pages,":[29],"used":[30],"answer":[32,63],"user":[33,127,168],"queries.":[35],"In":[36,99],"an":[37],"aggregate":[38],"sense,":[39],"is":[42,83,120,200],"very":[43],"dynamic,":[44],"causing":[45],"any":[46],"pages":[50,108,224,285],"become":[52],"out":[53],"date":[55],"over":[56],"time,":[57],"which":[58,146],"in":[59,145,227],"turn":[60],"causes":[61],"query":[62,132],"quality":[64,124,165,179,272],"degrade.":[66],"Given":[67],"considerable":[69],"size,":[70],"dynamicity,":[71],"and":[72,155,206,230],"degree":[73],"autonomy":[75],"as":[79],"whole,":[81],"it":[82],"not":[84],"feasible":[85],"for":[86,109,129,194,274,281],"engine":[89,115,204,271],"maintain":[91,268],"its":[92],"exactly":[94],"synchronized":[95],"with":[96,138],"Web.":[98],"this":[100,188],"paper":[101],"we":[102],"study":[103],"how":[104,232],"schedule":[106],"selective":[110],"(re)downloading":[111,198],"into":[112,286],"repository.":[116,185,289],"The":[117],"scheduling":[118,195,220],"objective":[119],"maximize":[122],"experience":[128],"those":[130],"who":[131],"engine.":[135],"We":[136,186,212,238],"begin":[137],"quantitative":[140],"characterization":[141,171],"way":[144],"discrepancy":[148],"between":[149],"content":[151,158],"current":[157],"live":[161],"impacts":[163],"experience.":[169],"This":[170],"leads":[172],"usercentric":[175],"metric":[176,189],"engine\u2019s":[183],"use":[187],"derive":[191],"policy":[193],"page":[197,250],"that":[199,260],"driven":[201],"by":[202],"usage":[205],"free":[207],"exterior":[209],"tuning":[210],"parameters.":[211],"then":[213],"focus":[214],"important":[217],"subproblem":[218],"refreshing":[221],"already":[225],"present":[226],"repository,":[229],"show":[231],"compute":[234],"priorities":[236],"efficiently.":[237],"provide":[239],"extensive":[240],"empirical":[241],"comparisons":[242],"our":[244,261],"user-centric":[245],"method":[246,262],"against":[247],"prior":[248],"refresh":[251],"strategies,":[252],"using":[253],"real":[254],"data.":[256],"Our":[257],"results":[258],"demonstrate":[259],"requires":[263],"far":[264],"fewer":[265],"resources":[266,279],"same":[269],"level":[273],"users,":[275],"leaving":[276],"substantially":[277],"more":[278],"available":[280],"incorporating":[282],"new":[283]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":9}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
