{"id":"https://openalex.org/W2919119516","doi":"https://doi.org/10.3390/informatics6010010","title":"ETL Best Practices for Data Quality Checks in RIS Databases","display_name":"ETL Best Practices for Data Quality Checks in RIS Databases","publication_year":2019,"publication_date":"2019-03-05","ids":{"openalex":"https://openalex.org/W2919119516","doi":"https://doi.org/10.3390/informatics6010010","mag":"2919119516"},"language":"en","primary_location":{"id":"doi:10.3390/informatics6010010","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics6010010","pdf_url":"https://www.mdpi.com/2227-9709/6/1/10/pdf?version=1551783861","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2227-9709/6/1/10/pdf?version=1551783861","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008817869","display_name":"Otmane Azeroual","orcid":"https://orcid.org/0000-0002-5225-389X"},"institutions":[{"id":"https://openalex.org/I122228004","display_name":"HTW Berlin - University of Applied Sciences","ror":"https://ror.org/01xzwj424","country_code":"DE","type":"education","lineage":["https://openalex.org/I122228004"]},{"id":"https://openalex.org/I4210111137","display_name":"German Centre for Higher Education Research and Science Studies","ror":"https://ror.org/01n8j6z65","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210111137"]},{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Otmane Azeroual","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Applied Sciences\u2014HTW Berlin, Wilhelminenhofstra\u00dfe 75 A, 12459 Berlin, Germany","German Center for Higher Education Research and Science Studies (DZHW), Sch\u00fctzenstra\u00dfe 6a, 10117 Berlin, Germany","Institute for Technical and Business Information Systems\u2014Database Research Group, Otto-von-Guericke-University Magdeburg, Universit\u00e4tsplatz 2, 39106 Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Applied Sciences\u2014HTW Berlin, Wilhelminenhofstra\u00dfe 75 A, 12459 Berlin, Germany","institution_ids":["https://openalex.org/I122228004"]},{"raw_affiliation_string":"German Center for Higher Education Research and Science Studies (DZHW), Sch\u00fctzenstra\u00dfe 6a, 10117 Berlin, Germany","institution_ids":["https://openalex.org/I4210111137"]},{"raw_affiliation_string":"Institute for Technical and Business Information Systems\u2014Database Research Group, Otto-von-Guericke-University Magdeburg, Universit\u00e4tsplatz 2, 39106 Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042946019","display_name":"Gunter Saake","orcid":"https://orcid.org/0000-0001-9576-8474"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gunter Saake","raw_affiliation_strings":["Institute for Technical and Business Information Systems\u2014Database Research Group, Otto-von-Guericke-University Magdeburg, Universit\u00e4tsplatz 2, 39106 Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Technical and Business Information Systems\u2014Database Research Group, Otto-von-Guericke-University Magdeburg, Universit\u00e4tsplatz 2, 39106 Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047752825","display_name":"Mohammad Abuosba","orcid":null},"institutions":[{"id":"https://openalex.org/I122228004","display_name":"HTW Berlin - University of Applied Sciences","ror":"https://ror.org/01xzwj424","country_code":"DE","type":"education","lineage":["https://openalex.org/I122228004"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mohammad Abuosba","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Applied Sciences\u2014HTW Berlin, Wilhelminenhofstra\u00dfe 75 A, 12459 Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Applied Sciences\u2014HTW Berlin, Wilhelminenhofstra\u00dfe 75 A, 12459 Berlin, Germany","institution_ids":["https://openalex.org/I122228004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008817869"],"corresponding_institution_ids":["https://openalex.org/I122228004","https://openalex.org/I4210111137","https://openalex.org/I95793202"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":3.2997,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92028414,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"6","issue":"1","first_page":"10","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9746000170707703,"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/data-quality","display_name":"Data quality","score":0.7302588820457458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6760014891624451},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.6458727717399597},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6128532886505127},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.554224967956543},{"id":"https://openalex.org/keywords/harmonization","display_name":"Harmonization","score":0.5398904085159302},{"id":"https://openalex.org/keywords/data-administration","display_name":"Data administration","score":0.5318586230278015},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.516497790813446},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.49692752957344055},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.47487470507621765},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.4446829855442047},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43261271715164185},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.42444321513175964},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.41137802600860596},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.2238679826259613},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1419954001903534},{"id":"https://openalex.org/keywords/database-model","display_name":"Database model","score":0.13009017705917358},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.09224143624305725}],"concepts":[{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.7302588820457458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6760014891624451},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.6458727717399597},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6128532886505127},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.554224967956543},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.5398904085159302},{"id":"https://openalex.org/C115842085","wikidata":"https://www.wikidata.org/wiki/Q4057846","display_name":"Data administration","level":4,"score":0.5318586230278015},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.516497790813446},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.49692752957344055},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47487470507621765},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.4446829855442047},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43261271715164185},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.42444321513175964},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.41137802600860596},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.2238679826259613},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1419954001903534},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.13009017705917358},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.09224143624305725},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/informatics6010010","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics6010010","pdf_url":"https://www.mdpi.com/2227-9709/6/1/10/pdf?version=1551783861","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:de46525c1d0a45d884483d4113365941","is_oa":true,"landing_page_url":"https://doaj.org/article/de46525c1d0a45d884483d4113365941","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Informatics, Vol 6, Iss 1, p 10 (2019)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2227-9709/6/1/10/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/informatics6010010","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Informatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/informatics6010010","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics6010010","pdf_url":"https://www.mdpi.com/2227-9709/6/1/10/pdf?version=1551783861","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2919119516.pdf","grobid_xml":"https://content.openalex.org/works/W2919119516.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1567491469","https://openalex.org/W1846324747","https://openalex.org/W1975322779","https://openalex.org/W1987094625","https://openalex.org/W2065753378","https://openalex.org/W2068376489","https://openalex.org/W2070257261","https://openalex.org/W2083755493","https://openalex.org/W2099967417","https://openalex.org/W2117366235","https://openalex.org/W2146138848","https://openalex.org/W2397198175","https://openalex.org/W2417883830","https://openalex.org/W2603044889","https://openalex.org/W2794656727","https://openalex.org/W2796210600","https://openalex.org/W2798218576","https://openalex.org/W2800877977","https://openalex.org/W2917577193","https://openalex.org/W2920153029","https://openalex.org/W2973396913","https://openalex.org/W4285719527","https://openalex.org/W4300641138","https://openalex.org/W6606539159","https://openalex.org/W6667163210","https://openalex.org/W6750872235","https://openalex.org/W6750993673"],"related_works":["https://openalex.org/W2384379346","https://openalex.org/W2348093825","https://openalex.org/W2390710026","https://openalex.org/W2364425891","https://openalex.org/W2347601812","https://openalex.org/W2369660510","https://openalex.org/W3015205082","https://openalex.org/W3022239989","https://openalex.org/W1505247071","https://openalex.org/W2364294367"],"abstract_inverted_index":{"The":[0,134],"topic":[1],"of":[2,37,57,60,63,136,144,157,211,217,223,226,246],"data":[3,7,29,83,126,132,137,146,149,158,186,195,199,212,235],"integration":[4,30,88,127,159,200,239,257],"from":[5,170],"external":[6,82,234],"sources":[8,84,187,236],"or":[9,124],"independent":[10],"IT-systems":[11],"has":[12],"received":[13],"increasing":[14],"attention":[15],"recently":[16],"in":[17,26,31,74,214,229,259],"IT":[18],"departments":[19],"as":[20,22,140,192,194],"well":[21,193],"at":[23],"management":[24],"level,":[25],"particular":[27],"concerning":[28],"federated":[32],"database":[33],"systems.":[34],"An":[35,119],"example":[36],"the":[38,53,58,90,100,104,131,145,171,178,209,215,224,244,252,256],"latter":[39],"are":[40,85,154,188,201],"commercial":[41],"research":[42,55,101,105,227],"information":[43,56,93,106,228],"systems":[44],"(RIS),":[45],"which":[46,219],"regularly":[47],"import,":[48],"cleanse,":[49],"transform":[50],"and":[51,81,116,142,150,163,175,190,233,250],"prepare":[52],"analysis":[54],"institutions":[59],"a":[61,75,110],"variety":[62],"databases.":[64],"In":[65,242],"addition,":[66,243],"all":[67],"these":[68],"so-called":[69],"steps":[70],"must":[71,113],"be":[72,114,262],"provided":[73],"secured":[76],"quality.":[77,133],"As":[78],"several":[79],"internal":[80,232],"loaded":[86,176],"for":[87,99,122],"into":[89,177,240],"RIS,":[91,111],"ensuring":[92],"quality":[94,196,225,253],"is":[95,107,128,168],"becoming":[96],"increasingly":[97],"challenging":[98],"institutions.":[102],"Before":[103],"transferred":[108],"to":[109,248],"it":[112],"checked":[115],"cleaned":[117],"up.":[118],"important":[120],"factor":[121],"successful":[123],"competent":[125],"therefore":[129],"always":[130],"removal":[135],"errors":[138],"(such":[139],"duplicates":[141],"harmonization":[143],"structure,":[147],"inconsistent":[148],"outdated":[151],"data,":[152],"etc.)":[153],"essential":[155],"tasks":[156],"using":[160],"extract,":[161],"transform,":[162],"load":[164],"(ETL)":[165],"processes.":[166],"Data":[167],"extracted":[169],"source":[172],"systems,":[173],"transformed":[174],"RIS.":[179,241],"At":[180],"this":[181,204],"point":[182],"conflicts":[183],"between":[184],"different":[185],"controlled":[189],"solved,":[191],"issues":[197,254],"during":[198,237,255],"eliminated.":[202],"Against":[203],"background,":[205],"our":[206],"paper":[207],"presents":[208],"process":[210,258],"transformation":[213],"context":[216],"RIS":[218,260],"gains":[220],"an":[221,230],"overview":[222],"institution\u2019s":[231],"its":[238],"question":[245],"how":[247],"control":[249],"improve":[251],"will":[261],"addressed.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
