{"id":"https://openalex.org/W1976732638","doi":"https://doi.org/10.1145/2723372.2747646","title":"BigDansing","display_name":"BigDansing","publication_year":2015,"publication_date":"2015-05-27","ids":{"openalex":"https://openalex.org/W1976732638","doi":"https://doi.org/10.1145/2723372.2747646","mag":"1976732638"},"language":"en","primary_location":{"id":"doi:10.1145/2723372.2747646","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2747646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/112981","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078436323","display_name":"Zuhair Khayyat","orcid":"https://orcid.org/0000-0003-3650-6997"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Zuhair Khayyat","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","King Abdullah University of Science and Technology - KAUST, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"King Abdullah University of Science and Technology - KAUST, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000141065","display_name":"Ihab F. Ilyas","orcid":"https://orcid.org/0000-0001-9052-9714"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ihab F. Ilyas","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079846990","display_name":"Alekh Jindal","orcid":"https://orcid.org/0000-0001-8844-8165"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alekh Jindal","raw_affiliation_strings":["MIT, Cambridge, MA, USA","MIT, Cambridge MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"MIT, Cambridge MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["MIT, Cambridge, MA, USA","MIT, Cambridge MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"MIT, Cambridge MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026923999","display_name":"Mourad Ouzzani","orcid":"https://orcid.org/0000-0002-4035-3025"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mourad Ouzzani","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011336242","display_name":"Paolo Papotti","orcid":"https://orcid.org/0000-0003-0651-4128"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Paolo Papotti","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083942725","display_name":"Jorge-Arnulfo Quian\u00e9-Ruiz","orcid":"https://orcid.org/0000-0002-9001-825X"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Jorge-Arnulfo Quian\u00e9-Ruiz","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089418614","display_name":"Si Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Si Yin","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5078436323"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":27.4928,"has_fulltext":true,"cited_by_count":151,"citation_normalized_percentile":{"value":0.99756536,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1215","last_page":"1230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9886999726295471,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9729999899864197,"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/computer-science","display_name":"Computer science","score":0.9043749570846558},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8066866993904114},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7090415358543396},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7036256790161133},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.6674343347549438},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5470113158226013},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4574616849422455},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4573911428451538},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42868274450302124},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4126741588115692},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.35157084465026855},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3438171148300171},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2638998031616211},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1779913306236267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9043749570846558},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8066866993904114},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7090415358543396},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7036256790161133},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.6674343347549438},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5470113158226013},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4574616849422455},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4573911428451538},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42868274450302124},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4126741588115692},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.35157084465026855},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3438171148300171},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2638998031616211},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1779913306236267},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2723372.2747646","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2747646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/112981","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/112981","pdf_url":"http://hdl.handle.net/1721.1/112981","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Other univ. web domain","raw_type":null},{"id":"pmh:oai:repository.kaust.edu.sa:10754/623134","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/623134","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"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 Paper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/112981","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/112981","pdf_url":"http://hdl.handle.net/1721.1/112981","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Other univ. web domain","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1976732638.pdf","grobid_xml":"https://content.openalex.org/works/W1976732638.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1500547548","https://openalex.org/W1539265392","https://openalex.org/W1573646728","https://openalex.org/W1610496399","https://openalex.org/W1700279323","https://openalex.org/W1964929381","https://openalex.org/W1975184797","https://openalex.org/W1982003698","https://openalex.org/W1986017822","https://openalex.org/W1993685897","https://openalex.org/W1997952460","https://openalex.org/W2002533683","https://openalex.org/W2019891208","https://openalex.org/W2044022210","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2047745978","https://openalex.org/W2061601738","https://openalex.org/W2063103859","https://openalex.org/W2078132546","https://openalex.org/W2081186682","https://openalex.org/W2089206172","https://openalex.org/W2098935637","https://openalex.org/W2099637074","https://openalex.org/W2109220922","https://openalex.org/W2110086534","https://openalex.org/W2112840274","https://openalex.org/W2114887670","https://openalex.org/W2139072600","https://openalex.org/W2147805208","https://openalex.org/W2153889808","https://openalex.org/W2164187405","https://openalex.org/W2167333415","https://openalex.org/W2170616854","https://openalex.org/W2171332293","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W6629856530","https://openalex.org/W6687322159","https://openalex.org/W6693395708"],"related_works":["https://openalex.org/W2016456293","https://openalex.org/W2161128265","https://openalex.org/W1997896902","https://openalex.org/W2138101384","https://openalex.org/W2140894225","https://openalex.org/W4212828571","https://openalex.org/W2125826941","https://openalex.org/W962911587","https://openalex.org/W2270762093","https://openalex.org/W3126834064"],"abstract_inverted_index":{"Data":[0,53],"cleansing":[1,26],"approaches":[2],"have":[3],"usually":[4],"focused":[5],"on":[6,70,138],"detecting":[7],"and":[8,40,60,99,125,132,141],"fixing":[9],"errors":[10],"with":[11,42,101],"little":[12],"attention":[13],"to":[14,16,56,83,92,152],"scaling":[15],"big":[17],"datasets.":[18],"This":[19],"presents":[20],"a":[21,51,117],"serious":[22],"impediment":[23],"since":[24],"data":[25,64,77,94],"often":[27],"involves":[28],"costly":[29],"computations":[30,124],"such":[31,128],"as":[32,129],"enumerating":[33],"pairs":[34],"of":[35,72,104,107,119,157],"tuples,":[36],"handling":[37],"inequality":[38],"joins,":[39],"dealing":[41],"user-defined":[43],"functions.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"present":[49],"BigDansing,":[50],"Big":[52],"Cleansing":[54],"system":[55,67],"tackle":[57],"efficiency,":[58],"scalability,":[59],"ease-of-use":[61],"issues":[62],"in":[63],"cleansing.":[65],"The":[66],"can":[68],"run":[69],"top":[71],"most":[73],"common":[74],"general":[75],"purpose":[76],"processing":[78],"platforms,":[79],"ranging":[80],"from":[81],"DBMSs":[82],"MapReduce-like":[84],"frameworks.":[85],"A":[86],"user-friendly":[87],"programming":[88],"interface":[89],"allows":[90],"users":[91],"express":[93],"quality":[95,162],"rules":[96,115],"both":[97,139],"declaratively":[98],"procedurally,":[100],"no":[102],"requirement":[103],"being":[105],"aware":[106],"the":[108,161,165],"underlying":[109],"distributed":[110,123],"platform.":[111],"BigDansing":[112,146],"takes":[113],"these":[114],"into":[116],"series":[118],"transformations":[120],"that":[121,145],"enable":[122],"several":[126],"optimizations,":[127],"shared":[130],"scans":[131],"specialized":[133],"joins":[134],"operators.":[135],"Experimental":[136],"results":[137],"synthetic":[140],"real":[142],"datasets":[143],"show":[144],"outperforms":[147],"existing":[148],"baseline":[149],"systems":[150],"up":[151],"more":[153],"than":[154],"two":[155],"orders":[156],"magnitude":[158],"without":[159],"sacrificing":[160],"provided":[163],"by":[164],"repair":[166],"algorithms.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":8}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2016-06-24T00:00:00"}
