{"id":"https://openalex.org/W4387455665","doi":"https://doi.org/10.1007/s12525-023-00677-w","title":"Sanitizing data for analysis: Designing systems for data understanding","display_name":"Sanitizing data for analysis: Designing systems for data understanding","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4387455665","doi":"https://doi.org/10.1007/s12525-023-00677-w"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12525-023-00677-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12525-023-00677-w.pdf","source":{"id":"https://openalex.org/S137519996","display_name":"Electronic Markets","issn_l":"1019-6781","issn":["1019-6781","1422-8890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s12525-023-00677-w.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060423160","display_name":"Joshua Holstein","orcid":"https://orcid.org/0009-0005-3885-8365"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Joshua Holstein","raw_affiliation_strings":["Institute of Information Systems and Marketing, Karlsruhe Institute of Technology Kaiserstra\u00dfe, 89-93, 76133, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Systems and Marketing, Karlsruhe Institute of Technology Kaiserstra\u00dfe, 89-93, 76133, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064032777","display_name":"Max Schemmer","orcid":"https://orcid.org/0000-0001-6341-2051"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Max Schemmer","raw_affiliation_strings":["Institute of Information Systems and Marketing, Karlsruhe Institute of Technology Kaiserstra\u00dfe, 89-93, 76133, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Systems and Marketing, Karlsruhe Institute of Technology Kaiserstra\u00dfe, 89-93, 76133, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014669175","display_name":"Johannes Jakubik","orcid":"https://orcid.org/0000-0002-6235-0300"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Jakubik","raw_affiliation_strings":["Institute of Information Systems and Marketing, Karlsruhe Institute of Technology Kaiserstra\u00dfe, 89-93, 76133, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Systems and Marketing, Karlsruhe Institute of Technology Kaiserstra\u00dfe, 89-93, 76133, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039548036","display_name":"Michael V\u00f6ssing","orcid":"https://orcid.org/0000-0002-7722-6142"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael V\u00f6ssing","raw_affiliation_strings":["Institute of Information Systems and Marketing, Karlsruhe Institute of Technology Kaiserstra\u00dfe, 89-93, 76133, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Systems and Marketing, Karlsruhe Institute of Technology Kaiserstra\u00dfe, 89-93, 76133, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000245557","display_name":"Gerhard Satzger","orcid":"https://orcid.org/0000-0001-8731-654X"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Satzger","raw_affiliation_strings":["Institute of Information Systems and Marketing, Karlsruhe Institute of Technology Kaiserstra\u00dfe, 89-93, 76133, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Systems and Marketing, Karlsruhe Institute of Technology Kaiserstra\u00dfe, 89-93, 76133, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060423160"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":{"value":2590,"currency":"EUR","value_usd":3190,"provenance":"doaj"},"apc_paid":{"value":2590,"currency":"EUR","value_usd":3190,"provenance":"doaj"},"fwci":2.303,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":4,"citation_normalized_percentile":{"value":0.622423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":90},"biblio":{"volume":"33","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9989,"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"}},"topics":[{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9989,"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/T11719","display_name":"Data Quality and Management","score":0.9974,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9952,"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/contextualization","display_name":"Contextualization","score":0.76464725},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.4329208}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8477338},{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.76464725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437453},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6750439},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6304592},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6090819},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5642713},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5191585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4637682},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.4329208},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3964572},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28656393},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19467875},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.15300667},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12525-023-00677-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12525-023-00677-w.pdf","source":{"id":"https://openalex.org/S137519996","display_name":"Electronic Markets","issn_l":"1019-6781","issn":["1019-6781","1422-8890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12525-023-00677-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12525-023-00677-w.pdf","source":{"id":"https://openalex.org/S137519996","display_name":"Electronic Markets","issn_l":"1019-6781","issn":["1019-6781","1422-8890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.47}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":54,"referenced_works":["https://openalex.org/W1535829273","https://openalex.org/W1567491469","https://openalex.org/W159389675","https://openalex.org/W2012594940","https://openalex.org/W2030319141","https://openalex.org/W2042886537","https://openalex.org/W2044102377","https://openalex.org/W2079484041","https://openalex.org/W2080731889","https://openalex.org/W2089174201","https://openalex.org/W2091359547","https://openalex.org/W2114060717","https://openalex.org/W2119111481","https://openalex.org/W2123737882","https://openalex.org/W2146449629","https://openalex.org/W2147753581","https://openalex.org/W2149163211","https://openalex.org/W2151530263","https://openalex.org/W2176760409","https://openalex.org/W2239306219","https://openalex.org/W2464234006","https://openalex.org/W2518579368","https://openalex.org/W2610292725","https://openalex.org/W2791184423","https://openalex.org/W2886130191","https://openalex.org/W2900569230","https://openalex.org/W2904821778","https://openalex.org/W2934302500","https://openalex.org/W2952667803","https://openalex.org/W2958919462","https://openalex.org/W2987169670","https://openalex.org/W3032547911","https://openalex.org/W3042644646","https://openalex.org/W30814344","https://openalex.org/W3099245869","https://openalex.org/W3106700156","https://openalex.org/W3137121183","https://openalex.org/W3151685851","https://openalex.org/W3155739706","https://openalex.org/W3155929575","https://openalex.org/W3164920117","https://openalex.org/W3206271843","https://openalex.org/W3208756203","https://openalex.org/W3210399516","https://openalex.org/W3212368439","https://openalex.org/W416578099","https://openalex.org/W4226227657","https://openalex.org/W4230737036","https://openalex.org/W4243216998","https://openalex.org/W4254111051","https://openalex.org/W4293219882","https://openalex.org/W4296186062","https://openalex.org/W4297520131","https://openalex.org/W760598031"],"related_works":["https://openalex.org/W3122624872","https://openalex.org/W3084772717","https://openalex.org/W2907247951","https://openalex.org/W2796209520","https://openalex.org/W2380261968","https://openalex.org/W2366936177","https://openalex.org/W2136226335","https://openalex.org/W2050262794","https://openalex.org/W2003742646","https://openalex.org/W1773645839"],"abstract_inverted_index":{"Abstract":[0],"As":[1],"organizations":[2,139],"accumulate":[3],"vast":[4],"amounts":[5],"of":[6,31,36,42,53,77,83,99,115],"data":[7,54],"for":[8],"analysis,":[9],"a":[10,65,108],"significant":[11],"challenge":[12],"remains":[13],"in":[14,130],"fully":[15],"understanding":[16,98],"these":[17,60],"datasets":[18,32],"to":[19,48,68,140],"extract":[20],"accurate":[21],"information":[22],"and":[23,33,80,94,121],"generate":[24],"real-world":[25,103],"impact.":[26],"Particularly,":[27],"the":[28,34,40,46,50,74,81,97,113,128],"high":[29],"dimensionality":[30],"lack":[35],"sufficient":[37],"documentation,":[38],"specifically":[39],"provision":[41],"metadata,":[43],"often":[44],"limit":[45],"potential":[47],"exploit":[49],"full":[51],"value":[52],"via":[55],"analytical":[56],"methods.":[57],"To":[58],"address":[59],"issues,":[61],"this":[62,116,133],"study":[63,105],"proposes":[64],"hybrid":[66],"approach":[67,87],"metadata":[69,131],"generation,":[70,132],"that":[71],"leverages":[72],"both":[73],"in-depth":[75],"knowledge":[76,122],"domain":[78],"experts":[79],"scalability":[82],"automated":[84],"processes.":[85],"The":[86],"centers":[88],"on":[89],"two":[90],"key":[91],"design":[92],"principles\u2014semanticization":[93],"contextualization\u2014to":[95],"facilitate":[96],"high-dimensional":[100],"datasets.":[101],"A":[102],"case":[104],"conducted":[106],"at":[107],"leading":[109],"pharmaceutical":[110],"company":[111],"validates":[112],"effectiveness":[114],"approach,":[117],"demonstrating":[118],"improved":[119],"collaboration":[120],"sharing":[123],"among":[124],"users.":[125],"By":[126],"addressing":[127],"challenges":[129],"research":[134],"contributes":[135],"significantly":[136],"toward":[137],"empowering":[138],"make":[141],"more":[142],"effective,":[143],"data-driven":[144],"decisions.":[145]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4387455665","counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2025-01-16T18:51:47.051184","created_date":"2023-10-10"}