{"id":"https://openalex.org/W2967970042","doi":"https://doi.org/10.18293/seke2019-129","title":"A Mapping Study about Data Lakes: An Improved Definition and Possible Architectures","display_name":"A Mapping Study about Data Lakes: An Improved Definition and Possible Architectures","publication_year":2019,"publication_date":"2019-07-10","ids":{"openalex":"https://openalex.org/W2967970042","doi":"https://doi.org/10.18293/seke2019-129","mag":"2967970042"},"language":"en","primary_location":{"id":"doi:10.18293/seke2019-129","is_oa":false,"landing_page_url":"https://doi.org/10.18293/seke2019-129","pdf_url":null,"source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","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/A5006933192","display_name":"J\u00falia Couto","orcid":"https://orcid.org/0000-0002-4022-0142"},"institutions":[{"id":"https://openalex.org/I45643870","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","ror":"https://ror.org/025vmq686","country_code":"BR","type":"education","lineage":["https://openalex.org/I45643870"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Julia Couto","raw_affiliation_strings":["School of Technology, PUCRS -Pontifical Catholic University of Rio Grande do Sul -Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"School of Technology, PUCRS -Pontifical Catholic University of Rio Grande do Sul -Porto Alegre, Brazil","institution_ids":["https://openalex.org/I45643870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011451059","display_name":"Olimar Teixeira Borges","orcid":"https://orcid.org/0000-0002-2567-2570"},"institutions":[{"id":"https://openalex.org/I45643870","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","ror":"https://ror.org/025vmq686","country_code":"BR","type":"education","lineage":["https://openalex.org/I45643870"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Olimar Borges","raw_affiliation_strings":["School of Technology, PUCRS -Pontifical Catholic University of Rio Grande do Sul -Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"School of Technology, PUCRS -Pontifical Catholic University of Rio Grande do Sul -Porto Alegre, Brazil","institution_ids":["https://openalex.org/I45643870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019215692","display_name":"Duncan D. Ruiz","orcid":"https://orcid.org/0000-0002-4071-3246"},"institutions":[{"id":"https://openalex.org/I45643870","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","ror":"https://ror.org/025vmq686","country_code":"BR","type":"education","lineage":["https://openalex.org/I45643870"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Duncan D. Ruiz","raw_affiliation_strings":["School of Technology, PUCRS -Pontifical Catholic University of Rio Grande do Sul -Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"School of Technology, PUCRS -Pontifical Catholic University of Rio Grande do Sul -Porto Alegre, Brazil","institution_ids":["https://openalex.org/I45643870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014651524","display_name":"Sabrina Marczak","orcid":"https://orcid.org/0000-0001-9631-8969"},"institutions":[{"id":"https://openalex.org/I45643870","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","ror":"https://ror.org/025vmq686","country_code":"BR","type":"education","lineage":["https://openalex.org/I45643870"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Sabrina Marczak","raw_affiliation_strings":["School of Technology, PUCRS -Pontifical Catholic University of Rio Grande do Sul -Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"School of Technology, PUCRS -Pontifical Catholic University of Rio Grande do Sul -Porto Alegre, Brazil","institution_ids":["https://openalex.org/I45643870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024645888","display_name":"Rafael Prikladnicki","orcid":"https://orcid.org/0000-0003-3351-4916"},"institutions":[{"id":"https://openalex.org/I45643870","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","ror":"https://ror.org/025vmq686","country_code":"BR","type":"education","lineage":["https://openalex.org/I45643870"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rafael Prikladnicki","raw_affiliation_strings":["School of Technology, PUCRS -Pontifical Catholic University of Rio Grande do Sul -Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"School of Technology, PUCRS -Pontifical Catholic University of Rio Grande do Sul -Porto Alegre, Brazil","institution_ids":["https://openalex.org/I45643870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006933192"],"corresponding_institution_ids":["https://openalex.org/I45643870"],"apc_list":null,"apc_paid":null,"fwci":4.1594,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94190682,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"2019","issue":null,"first_page":"453","last_page":"458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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":0.9994000196456909,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9839000105857849,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9761999845504761,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6888700127601624},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35961008071899414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6888700127601624},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35961008071899414}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18293/seke2019-129","is_oa":false,"landing_page_url":"https://doi.org/10.18293/seke2019-129","pdf_url":null,"source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1928156542","https://openalex.org/W2035196713","https://openalex.org/W2118328848","https://openalex.org/W2164777277","https://openalex.org/W2292351001","https://openalex.org/W2296136888","https://openalex.org/W2328377221","https://openalex.org/W2473685685","https://openalex.org/W2479639269","https://openalex.org/W2509030362","https://openalex.org/W2515135771","https://openalex.org/W2525655547","https://openalex.org/W2530589556","https://openalex.org/W2562503588","https://openalex.org/W2564380873","https://openalex.org/W2574643375","https://openalex.org/W2575168421","https://openalex.org/W2584740438","https://openalex.org/W2587787907","https://openalex.org/W2588955586","https://openalex.org/W2594526919","https://openalex.org/W2610783334","https://openalex.org/W2612349707","https://openalex.org/W2619121603","https://openalex.org/W2622403554","https://openalex.org/W2636278499","https://openalex.org/W2732131184","https://openalex.org/W2737360161","https://openalex.org/W2741960503","https://openalex.org/W2742637748","https://openalex.org/W2750856415","https://openalex.org/W2751085111","https://openalex.org/W2767448088","https://openalex.org/W2781864800","https://openalex.org/W2784088855","https://openalex.org/W2784237011","https://openalex.org/W2784247783","https://openalex.org/W2785444232","https://openalex.org/W2789473760","https://openalex.org/W2791289172","https://openalex.org/W2791479828","https://openalex.org/W2793562676","https://openalex.org/W2796406438","https://openalex.org/W2796845918","https://openalex.org/W2799290116","https://openalex.org/W2800409976","https://openalex.org/W2803485461","https://openalex.org/W2808616297","https://openalex.org/W2809557400","https://openalex.org/W2809816183","https://openalex.org/W2810397972","https://openalex.org/W2810555946","https://openalex.org/W2811443808","https://openalex.org/W2813939957","https://openalex.org/W2883070524","https://openalex.org/W2883354997","https://openalex.org/W2885838826","https://openalex.org/W2886212520","https://openalex.org/W2889541271","https://openalex.org/W2889809218","https://openalex.org/W2890354115","https://openalex.org/W2906650872","https://openalex.org/W2949076265","https://openalex.org/W4233717669","https://openalex.org/W4255828145","https://openalex.org/W4294214983","https://openalex.org/W4298858166"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"In":[0],"the":[1,80,115,130,139,161,173,185],"past":[2],"few":[3],"years,":[4],"data":[5,14,34,38,48,117,137,154,179,190],"lakes":[6,118,155,191],"emerged":[7],"as":[8,147,192],"a":[9,31,36,58,89,144,148],"trending":[10],"topic":[11],"in":[12,35,82,94,125,187],"big":[13,37],"technologies.Although":[15],"literature":[16,60],"presents":[17],"different":[18,84],"points":[19],"of":[20,33,57,92,193],"view":[21],"related":[22,134],"to":[23,29,44,69,75,87,135,150,157,177],"its":[24,170],"functionalities,":[25],"it":[26],"serves":[27],"mainly":[28],"store":[30],"variety":[32,91],"context.In":[39],"this":[40,183],"paper,":[41],"we":[42,107,142,165],"aim":[43],"identify":[45],"and":[46,51,72,158,169],"analyze":[47],"lake":[49],"definitions":[50],"possible":[52],"architectures.Our":[53],"methodology":[54],"was":[55,119],"composed":[56],"systematic":[59],"mapping":[61],"based":[62],"on":[63],"PRISMA,":[64],"software":[65],"engineering":[66],"best":[67],"practices":[68],"perform":[70],"reviews,":[71],"Kappa":[73],"method":[74],"assess":[76],"results'":[77],"quality.We":[78],"performed":[79],"search":[81,103],"eight":[83],"electronic":[85],"databases":[86],"achieve":[88],"wide":[90],"publishers":[93],"Computer":[95],"Science.We":[96],"first":[97,120],"identified":[98,140],"662":[99],"papers":[100,110],"matching":[101],"our":[102],"criteria;":[104],"after":[105],"filtering,":[106],"selected":[108],"87":[109],"for":[111,189],"review.We":[112],"found":[113,128],"that":[114,129,167,182],"term":[116,131],"defined":[121],"by":[122],"James":[123],"Dixon":[124],"2010.We":[126],"also":[127],"is":[132,184],"often":[133],"raw":[136],"repositories.From":[138],"definitions,":[141],"propose":[143],"new":[145],"one":[146],"means":[149],"better":[151],"state":[152],"what":[153],"refer":[156],"improve":[159],"how":[160],"community":[162],"use":[163],"them.Moreover,":[164],"foind":[166],"Hadoop":[168],"ecosystem":[171],"compose":[172],"most":[174],"used":[175],"toolset":[176],"create":[178],"lakes,":[180],"revealing":[181],"mainstream":[186],"architectures":[188],"today's":[194],"available":[195],"technologies.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}