{"id":"https://openalex.org/W4382132877","doi":"https://doi.org/10.1007/s13222-023-00448-z","title":"Metadata Extraction from User Queries for Self-Service Data Lake Exploration","display_name":"Metadata Extraction from User Queries for Self-Service Data Lake Exploration","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382132877","doi":"https://doi.org/10.1007/s13222-023-00448-z"},"language":"en","primary_location":{"id":"doi:10.1007/s13222-023-00448-z","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s13222-023-00448-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-023-00448-z.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"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/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s13222-023-00448-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092270883","display_name":"Jonas Gunklach","orcid":"https://orcid.org/0000-0002-2608-2679"},"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":"Jonas Gunklach","raw_affiliation_strings":["Human-Centered Systems Lab, Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Human-Centered Systems Lab, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038934406","display_name":"Sven Michalczyk","orcid":null},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Michalczyk","raw_affiliation_strings":["Robert Bosch GmbH, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH, Stuttgart, Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052837629","display_name":"Mario Nadj","orcid":"https://orcid.org/0000-0002-6901-9450"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mario Nadj","raw_affiliation_strings":["Business & Information Systems Engineering, TU Dortmund University, Dortmund, Germany"],"affiliations":[{"raw_affiliation_string":"Business & Information Systems Engineering, TU Dortmund University, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080792995","display_name":"Alexander Maedche","orcid":"https://orcid.org/0000-0001-6546-4816"},"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":"Alexander Maedche","raw_affiliation_strings":["Human-Centered Systems Lab, Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Human-Centered Systems Lab, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092270883"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":{"value":2380,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2380,"currency":"EUR","value_usd":2890},"fwci":0.7642,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73936186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"23","issue":"2","first_page":"97","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.9781000018119812,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8979829549789429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7869625091552734},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.6528358459472656},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.594851016998291},{"id":"https://openalex.org/keywords/metadata-management","display_name":"Metadata management","score":0.5620903372764587},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5380598306655884},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.46955233812332153},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.46602487564086914},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45947614312171936},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.451852023601532},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4470934271812439},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4096536338329315},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3513684570789337}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8979829549789429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869625091552734},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.6528358459472656},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.594851016998291},{"id":"https://openalex.org/C2779489174","wikidata":"https://www.wikidata.org/wiki/Q6822246","display_name":"Metadata management","level":3,"score":0.5620903372764587},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5380598306655884},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.46955233812332153},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.46602487564086914},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45947614312171936},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.451852023601532},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4470934271812439},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4096536338329315},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3513684570789337},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13222-023-00448-z","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s13222-023-00448-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-023-00448-z.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"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/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s13222-023-00448-z","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s13222-023-00448-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-023-00448-z.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"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/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382132877.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W61163549","https://openalex.org/W1662112478","https://openalex.org/W1980224781","https://openalex.org/W2098118776","https://openalex.org/W2104577574","https://openalex.org/W2144363643","https://openalex.org/W2284173343","https://openalex.org/W2566712162","https://openalex.org/W2784088855","https://openalex.org/W2890552332","https://openalex.org/W2941517172","https://openalex.org/W2968918513","https://openalex.org/W3042644646","https://openalex.org/W3084772717","https://openalex.org/W3200748896","https://openalex.org/W4205175606","https://openalex.org/W4255463977","https://openalex.org/W4256667588"],"related_works":["https://openalex.org/W3084772717","https://openalex.org/W2907247951","https://openalex.org/W2380261968","https://openalex.org/W2376038160","https://openalex.org/W3199469221","https://openalex.org/W4289754504","https://openalex.org/W2807292920","https://openalex.org/W2365178252","https://openalex.org/W4286761135","https://openalex.org/W2950619567"],"abstract_inverted_index":{"Abstract":[0],"Data":[1],"catalogs":[2,27,47],"represent":[3],"a":[4,68,76,128,157],"promising":[5],"solution":[6],"for":[7,59],"semantically":[8],"classifying":[9],"and":[10,14,79,123,146,159],"organizing":[11],"data":[12,17,26,38,43,46,56,77,96,154],"sources":[13],"enriching":[15],"raw":[16],"with":[18,42,112,127],"metadata.":[19],"However,":[20],"recent":[21],"research":[22],"has":[23],"shown":[24],"that":[25,71,134],"are":[28],"difficult":[29],"to":[30,33,49,53,83,115,140],"implement":[31],"due":[32],"the":[34,37,55,85,95,117,121,138,148],"complexity":[35],"of":[36,93,120],"landscape":[39],"or":[40],"issues":[41],"governance.":[44],"Moreover,":[45],"struggle":[48],"enable":[50],"business":[51,81,113],"analysts":[52,82,114],"find":[54],"they":[57],"need":[58],"their":[60],"use":[61],"cases.":[62],"Against":[63],"this":[64],"backdrop,":[65],"we":[66,108],"develop":[67],"self-service":[69],"system":[70,100,122],"automatically":[72],"extracts":[73],"metadata":[74,86,102],"from":[75,103,143],"lake":[78],"enables":[80],"explore":[84],"through":[87],"an":[88],"easy-to-use":[89],"interface.":[90],"Specifically,":[91],"instead":[92],"implementing":[94],"catalog":[97],"top-down,":[98],"our":[99],"derives":[101],"user":[104],"queries":[105,142],"bottom-up.":[106],"Hereby,":[107],"conduct":[109],"15":[110],"interviews":[111],"derive":[116],"underlying":[118],"requirements":[119],"evaluate":[124],"its":[125],"features":[126],"focus":[129],"group.":[130],"Our":[131],"findings":[132],"illustrate":[133],"participants":[135],"especially":[136],"value":[137],"possibility":[139],"reuse":[141],"other":[144],"users":[145],"appreciated":[147],"support":[149],"in":[150],"query":[151],"validation":[152],"as":[153],"preparation":[155],"is":[156],"complex":[158],"time-consuming":[160],"endeavour.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
