{"id":"https://openalex.org/W2041771431","doi":"https://doi.org/10.1145/1807167.1807259","title":"Unbiased estimation of size and other aggregates over hidden web databases","display_name":"Unbiased estimation of size and other aggregates over hidden web databases","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2041771431","doi":"https://doi.org/10.1145/1807167.1807259","mag":"2041771431"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807259","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","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/A5057802863","display_name":"Arjun Dasgupta","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arjun Dasgupta","raw_affiliation_strings":["University of Texas at Arlington, Arlington, TX, USA","[University of Texas at Arlington, Arlington, TX, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"[University of Texas at Arlington, Arlington, TX, USA]","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101882004","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-8741-5847"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["George Washington University, Washington, D.C., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, D.C., USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039565475","display_name":"Bradley Jewell","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bradley Jewell","raw_affiliation_strings":["University of Texas at Arlington, Arlington, TX, USA","[University of Texas at Arlington, Arlington, TX, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"[University of Texas at Arlington, Arlington, TX, USA]","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641132","display_name":"Nan Zhang","orcid":"https://orcid.org/0000-0001-9620-5665"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Zhang","raw_affiliation_strings":["George Washington University, Washington, D.C, USA","George Washington University, Washington D.C., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, D.C, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"George Washington University, Washington D.C., USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002203026","display_name":"Gautam Das","orcid":"https://orcid.org/0000-0002-4627-9065"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Das","raw_affiliation_strings":["University of Texas at Arlington, Arlington, TX, USA","[University of Texas at Arlington, Arlington, TX, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"[University of Texas at Arlington, Arlington, TX, USA]","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.2679,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.99056703,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"855","last_page":"866"},"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":0.9976999759674072,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.8445981740951538},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5875428915023804},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5796425342559814},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.5584109425544739},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.502265453338623},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46900224685668945},{"id":"https://openalex.org/keywords/database-query","display_name":"Database query","score":0.4513865113258362},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3718576431274414},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2258807122707367},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20368805527687073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8445981740951538},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5875428915023804},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5796425342559814},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.5584109425544739},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.502265453338623},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46900224685668945},{"id":"https://openalex.org/C2989070954","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database query","level":2,"score":0.4513865113258362},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3718576431274414},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2258807122707367},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20368805527687073},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1807167.1807259","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.4264","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.4264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://home.gwu.edu/~xjin/pub/sigmod2010.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":37,"referenced_works":["https://openalex.org/W34633382","https://openalex.org/W1586176254","https://openalex.org/W1601949013","https://openalex.org/W1605217017","https://openalex.org/W1970173714","https://openalex.org/W1978277861","https://openalex.org/W1986828474","https://openalex.org/W1989856433","https://openalex.org/W1992730709","https://openalex.org/W1998674327","https://openalex.org/W2001947543","https://openalex.org/W2003316857","https://openalex.org/W2010221274","https://openalex.org/W2037701287","https://openalex.org/W2047810995","https://openalex.org/W2047836387","https://openalex.org/W2060088491","https://openalex.org/W2081948558","https://openalex.org/W2083039049","https://openalex.org/W2102815161","https://openalex.org/W2125638313","https://openalex.org/W2129817180","https://openalex.org/W2131006463","https://openalex.org/W2136059419","https://openalex.org/W2151512210","https://openalex.org/W2154707336","https://openalex.org/W2155569834","https://openalex.org/W2164520297","https://openalex.org/W2170188121","https://openalex.org/W2333525369","https://openalex.org/W2615953416","https://openalex.org/W4206551437","https://openalex.org/W4233471163","https://openalex.org/W6601411562","https://openalex.org/W6635193281","https://openalex.org/W6682827647","https://openalex.org/W6685116542"],"related_works":["https://openalex.org/W2037906003","https://openalex.org/W4378699829","https://openalex.org/W2953265498","https://openalex.org/W2533455610","https://openalex.org/W4248236804","https://openalex.org/W2910532728","https://openalex.org/W2963068115","https://openalex.org/W2028002993","https://openalex.org/W2894093432","https://openalex.org/W2041771431"],"abstract_inverted_index":{"Many":[0],"websites":[1],"provide":[2],"restrictive":[3],"form-like":[4],"interfaces":[5],"which":[6,41],"allow":[7],"users":[8],"to":[9,48,75],"execute":[10],"search":[11],"queries":[12,47],"on":[13],"the":[14,23,27,77],"underlying":[15],"hidden":[16,31,66],"databases.":[17,67],"In":[18],"this":[19],"paper,":[20],"we":[21],"consider":[22],"problem":[24],"of":[25,29,46,79],"estimating":[26],"size":[28],"a":[30,43],"database":[32],"through":[33],"its":[34],"web":[35],"interface.":[36],"We":[37,68],"propose":[38],"novel":[39],"techniques":[40,56],"use":[42],"small":[44,53],"number":[45],"produce":[49],"unbiased":[50],"estimates":[51],"with":[52],"variance.":[54],"These":[55],"can":[57],"also":[58],"be":[59],"used":[60],"for":[61],"approximate":[62],"query":[63],"processing":[64],"over":[65],"present":[69],"theoretical":[70],"analysis":[71],"and":[72],"extensive":[73],"experiments":[74],"illustrate":[76],"effectiveness":[78],"our":[80],"approach.":[81]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}