{"id":"https://openalex.org/W3197656228","doi":"https://doi.org/10.1145/3472163.3472173","title":"Data Management in the Data Lake: A Systematic Mapping","display_name":"Data Management in the Data Lake: A Systematic Mapping","publication_year":2021,"publication_date":"2021-07-14","ids":{"openalex":"https://openalex.org/W3197656228","doi":"https://doi.org/10.1145/3472163.3472173","mag":"3197656228"},"language":"en","primary_location":{"id":"doi:10.1145/3472163.3472173","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472163.3472173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"25th International Database Engineering &amp; Applications Symposium","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/A5085841401","display_name":"Firas Zouari","orcid":"https://orcid.org/0000-0001-6403-2157"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I874609350","display_name":"Universit\u00e9 Jean Moulin Lyon III","ror":"https://ror.org/05b5c0584","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I874609350"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Firas Zouari","raw_affiliation_strings":["Universite Jean Moulin (Lyon III), France","SOC - Service Oriented Computing (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite Jean Moulin (Lyon III), France","institution_ids":["https://openalex.org/I100532134","https://openalex.org/I874609350"]},{"raw_affiliation_string":"SOC - Service Oriented Computing (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047619310","display_name":"Nadia Kabachi","orcid":"https://orcid.org/0000-0001-8071-8490"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nadia Kabachi","raw_affiliation_strings":["Universite Claude Bernard (Lyon I), France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite Claude Bernard (Lyon I), France","institution_ids":["https://openalex.org/I100532134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040130171","display_name":"Khouloud Boukadi","orcid":"https://orcid.org/0000-0002-6744-711X"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]},{"id":"https://openalex.org/I4210119561","display_name":"Digital Research Centre of Sfax","ror":"https://ror.org/02s48dm85","country_code":"TN","type":"facility","lineage":["https://openalex.org/I4210119561"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Khouloud Boukadi","raw_affiliation_strings":["Universite de Sfax, Tunisia","MIRACL - Multimedia, InfoRmation systems and Advanced Computing Laboratory (Route de Tunis, km 10, BP 242, Sakiet Ezziet, 3021 SFAX - Tunisia)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite de Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]},{"raw_affiliation_string":"MIRACL - Multimedia, InfoRmation systems and Advanced Computing Laboratory (Route de Tunis, km 10, BP 242, Sakiet Ezziet, 3021 SFAX - Tunisia)","institution_ids":["https://openalex.org/I4210119561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013633460","display_name":"Chirine Gh\u00e9dira","orcid":"https://orcid.org/0000-0003-0908-2711"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I874609350","display_name":"Universit\u00e9 Jean Moulin Lyon III","ror":"https://ror.org/05b5c0584","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I874609350"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chirine Ghedira Guegan","raw_affiliation_strings":["Universite Jean Moulin (Lyon III), France","SOC - Service Oriented Computing (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite Jean Moulin (Lyon III), France","institution_ids":["https://openalex.org/I100532134","https://openalex.org/I874609350"]},{"raw_affiliation_string":"SOC - Service Oriented Computing (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"280","last_page":"284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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":0.9984999895095825,"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9927999973297119,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9896000027656555,"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/computer-science","display_name":"Computer science","score":0.7741321325302124},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6985805034637451},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6805687546730042},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.6527015566825867},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5872805118560791},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5856573581695557},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5799234509468079},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5657020211219788},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.5493476390838623},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45765459537506104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3878345489501953},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3719097971916199},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10792401432991028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08370804786682129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741321325302124},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6985805034637451},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6805687546730042},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.6527015566825867},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5872805118560791},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5856573581695557},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5799234509468079},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5657020211219788},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.5493476390838623},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45765459537506104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3878345489501953},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3719097971916199},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10792401432991028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08370804786682129},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3472163.3472173","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472163.3472173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"25th International Database Engineering &amp; Applications Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03342938v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03342938","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IDEAS 2021: 25th International Database Engineering & Applications Symposium, Jun 2021, Montreal QC Canada, Canada. pp.280-284, &#x27E8;10.1145/3472163.3472173&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1624245830","https://openalex.org/W1975322779","https://openalex.org/W2612167364","https://openalex.org/W2889473110","https://openalex.org/W2918245750","https://openalex.org/W2958248471","https://openalex.org/W2970992672","https://openalex.org/W2983034192","https://openalex.org/W3093246649","https://openalex.org/W3095333182","https://openalex.org/W3111583617"],"related_works":["https://openalex.org/W2901826185","https://openalex.org/W3119296476","https://openalex.org/W2742521120","https://openalex.org/W2159392828","https://openalex.org/W2353586736","https://openalex.org/W2189235061","https://openalex.org/W2353590449","https://openalex.org/W188368245","https://openalex.org/W2181930696","https://openalex.org/W69955301"],"abstract_inverted_index":{"The":[0,44],"computer":[1,74],"science":[2,75],"community":[3,82],"is":[4,69,83],"paying":[5],"more":[6,8],"and":[7,20,36,99,124,135,142],"attention":[9],"to":[10,13,117,127,140,146],"data":[11,26,32,38,48,59,67,102,105,112],"due":[12],"its":[14,50,77,86],"crucial":[15],"role":[16],"in":[17,40,49,72,85,104,120],"performing":[18,57,97],"analysis":[19,98],"prediction.":[21,136],"Researchers":[22],"have":[23],"proposed":[24],"many":[25],"containers":[27],"such":[28],"as":[29],"files,":[30],"databases,":[31],"warehouses,":[33],"cloud":[34],"systems,":[35],"recently":[37],"lakes":[39],"the":[41,73,80,110,125],"last":[42],"decade.":[43],"latter":[45],"enables":[46],"holding":[47],"native":[51],"format,":[52],"making":[53],"it":[54],"suitable":[55],"for":[56,62,96],"massive":[58],"prediction,":[60],"particularly":[61],"real-time":[63],"application":[64],"development.":[65],"Although":[66],"lake":[68],"well":[70],"adopted":[71],"industry,":[76],"acceptance":[78],"by":[79],"research":[81],"still":[84],"infancy":[87],"stage.":[88],"This":[89,137],"paper":[90],"sheds":[91],"light":[92],"on":[93,101],"existing":[94],"works":[95],"predictions":[100],"placed":[103],"lakes.":[106],"Our":[107],"study":[108,138],"reveals":[109],"necessary":[111],"management":[113],"steps,":[114],"which":[115],"need":[116],"be":[118,128],"followed":[119],"a":[121],"decision":[122],"process,":[123],"requirements":[126],"respected,":[129],"namely":[130],"curation,":[131],"quality":[132],"evaluation,":[133],"privacy-preservation,":[134],"aims":[139],"categorize":[141],"analyze":[143],"proposals":[144],"related":[145],"each":[147],"step":[148],"mentioned":[149],"above.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
