{"id":"https://openalex.org/W1813736802","doi":"https://doi.org/10.14778/2535568.2448944","title":"Counting with the crowd","display_name":"Counting with the crowd","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1813736802","doi":"https://doi.org/10.14778/2535568.2448944","mag":"1813736802"},"language":"en","primary_location":{"id":"doi:10.14778/2535568.2448944","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2535568.2448944","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5112355043","display_name":"Adam Marcus","orcid":"https://orcid.org/0000-0002-1428-2307"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Adam Marcus","raw_affiliation_strings":["MIT, CSAIL","MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT, CSAIL","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028448267","display_name":"David R. Karger","orcid":"https://orcid.org/0000-0002-0024-5847"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Karger","raw_affiliation_strings":["MIT, CSAIL","MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT, CSAIL","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["MIT, CSAIL","MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT, CSAIL","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091023123","display_name":"Robert C. Miller","orcid":"https://orcid.org/0000-0001-8932-2732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert Miller","raw_affiliation_strings":["MIT, CSAIL","MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT, CSAIL","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028243041","display_name":"Sewoong Oh","orcid":"https://orcid.org/0000-0002-8975-8306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sewoong Oh","raw_affiliation_strings":["MIT, CSAIL","MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT, CSAIL","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5112355043"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.4983,"has_fulltext":false,"cited_by_count":97,"citation_normalized_percentile":{"value":0.99227799,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"6","issue":"2","first_page":"109","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/crowdsourcing","display_name":"Crowdsourcing","score":0.843247652053833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7685607671737671},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.7201616764068604},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.6491912603378296},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.490018755197525},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.4324479401111603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4271320700645447},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35536932945251465},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34917140007019043},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34200817346572876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.330959677696228}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.843247652053833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7685607671737671},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.7201616764068604},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.6491912603378296},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.490018755197525},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.4324479401111603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4271320700645447},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35536932945251465},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34917140007019043},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34200817346572876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.330959677696228},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/2535568.2448944","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2535568.2448944","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.5980","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.5980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/vol6/p109-marcus.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.3943","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.3943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://db.disi.unitn.eu/pages/VLDBProgram/pdf/research/p135-marcus.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W1520914943","https://openalex.org/W1551839888","https://openalex.org/W1583345983","https://openalex.org/W1617484126","https://openalex.org/W1904009680","https://openalex.org/W1974554406","https://openalex.org/W1985816302","https://openalex.org/W1995945562","https://openalex.org/W2004921315","https://openalex.org/W2020018978","https://openalex.org/W2028818097","https://openalex.org/W2036625304","https://openalex.org/W2064975723","https://openalex.org/W2098865355","https://openalex.org/W2127008633","https://openalex.org/W2140890285","https://openalex.org/W2145492473","https://openalex.org/W2149033295","https://openalex.org/W2161536413","https://openalex.org/W2168144930","https://openalex.org/W2184059664","https://openalex.org/W3016146927","https://openalex.org/W3106889297","https://openalex.org/W6630973029","https://openalex.org/W6636777244","https://openalex.org/W6681486618"],"related_works":["https://openalex.org/W1987732684","https://openalex.org/W2286465138","https://openalex.org/W3032998312","https://openalex.org/W637393809","https://openalex.org/W4384486036","https://openalex.org/W2808742736","https://openalex.org/W1604338727","https://openalex.org/W2597976432","https://openalex.org/W2294447324","https://openalex.org/W2163482186"],"abstract_inverted_index":{"In":[0],"this":[1,56,135],"paper,":[2],"we":[3,15,119],"address":[4],"the":[5,32,64,154,169,226],"problem":[6],"of":[7,34,42,52,106,156,168,177,207,215,239],"selectivity":[8,131],"estimation":[9,137,191],"in":[10,36,63,69,78],"a":[11,23,37,40,83,88,98,104,193],"crowdsourced":[12],"database.":[13],"Specifically,":[14],"develop":[16,120],"several":[17],"techniques":[18,121],"for":[19,142],"using":[20,134],"workers":[21,103],"on":[22,192],"crowdsourcing":[24],"platform":[25],"like":[26],"Amazon's":[27],"Mechanical":[28],"Turk":[29],"to":[30,73,101,111,122,129,159,174,224,236],"estimate":[31,112,163],"fraction":[33,171],"items":[35,107],"dataset":[38],"(e.g.,":[39,50],"collection":[41,105],"photos)":[43],"that":[44,141,164,186],"satisfy":[45,115],"some":[46,116],"property":[47],"or":[48,90],"predicate":[49,75],"photos":[51],"trees).":[53],"We":[54,93,139,183],"do":[55],"without":[57],"explicitly":[58],"iterating":[59],"through":[60],"every":[61],"item":[62,96],"dataset.":[65],"This":[66],"is":[67,165,222],"important":[68],"crowd-sourced":[70],"query":[71,79],"optimization":[72],"support":[74],"ordering":[76],"and":[77,108,125,228],"evaluation,":[80],"when":[81,133],"performing":[82],"GROUP":[84],"BY":[85],"operation":[86],"with":[87,179],"COUNT":[89],"AVG":[91],"aggregate.":[92],"compare":[94],"sampling":[95],"labels,":[97],"traditional":[99],"approach,":[100],"showing":[102],"asking":[109],"them":[110],"how":[113],"many":[114],"predicate.":[117],"Additionally,":[118],"eliminate":[123],"spammers":[124],"colluding":[126],"attackers":[127],"trying":[128],"skew":[130],"estimates":[132],"count":[136,190],"approach.":[138],"find":[140,185],"images,":[143],"counting":[144],"can":[145,231],"be":[146],"much":[147],"more":[148],"effective":[149],"than":[150,209],"sampled":[151,187],"labeling,":[152],"reducing":[153],"amount":[155],"work":[157],"necessary":[158],"arrive":[160],"at":[161,202,212],"an":[162,175],"within":[166],"1%":[167],"true":[170],"by":[172,234],"up":[173,235],"order":[176],"magnitude,":[178],"lower":[180],"worker":[181],"latency.":[182],"also":[184],"labeling":[188],"outperforms":[189],"text":[194],"processing":[195,204],"task,":[196],"presumably":[197],"because":[198],"people":[199],"are":[200,211],"better":[201],"quickly":[203],"large":[205],"batches":[206],"images":[208],"they":[210],"reading":[213],"strings":[214],"text.":[216],"Our":[217],"spammer":[218],"detection":[219],"technique,":[220],"which":[221],"applicable":[223],"both":[225],"label-":[227],"count-based":[229],"approaches,":[230],"improve":[232],"accuracy":[233],"two":[237],"orders":[238],"magnitude.":[240]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":22},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}