{"id":"https://openalex.org/W6962807544","doi":"https://doi.org/10.18420/btw2025-08","title":"DPQL: Applications for Holistic Data Profiling","display_name":"DPQL: Applications for Holistic Data Profiling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W6962807544","doi":"https://doi.org/10.18420/btw2025-08"},"language":"en","primary_location":{"id":"doi:10.18420/btw2025-08","is_oa":true,"landing_page_url":"https://doi.org/10.18420/btw2025-08","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/btw2025-08","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Seeger, Marcian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seeger, Marcian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Papenbrock, Thorsten","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Papenbrock, Thorsten","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57095168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11137","display_name":"Historical Philosophy and Science","score":0.03849999979138374,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11137","display_name":"Historical Philosophy and Science","score":0.03849999979138374,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13897","display_name":"Historical Economic and Legal Thought","score":0.03849999979138374,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12517","display_name":"Seventeenth-Century Political and Philosophical Thought","score":0.030799999833106995,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.8531000018119812},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7531999945640564},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.4909000098705292},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.4401000142097473},{"id":"https://openalex.org/keywords/data-mapping","display_name":"Data mapping","score":0.36899998784065247},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.352400004863739},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.33640000224113464},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8531000018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79339998960495},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7531999945640564},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5389000177383423},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.4909000098705292},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3837999999523163},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.33640000224113464},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3188999891281128},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C2781396290","wikidata":"https://www.wikidata.org/wiki/Q17051824","display_name":"Data publishing","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18420/btw2025-08","is_oa":true,"landing_page_url":"https://doi.org/10.18420/btw2025-08","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/btw2025-08","is_oa":true,"landing_page_url":"https://doi.org/10.18420/btw2025-08","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Data":[0,115],"profiling":[1,42,85,166,217,224],"is":[2,27,81],"the":[3,114,125,170,211],"process":[4],"of":[5,18,57,90,105,132,135,174,180,214],"extracting":[6],"implicit":[7],"metadata,":[8],"such":[9,64],"as":[10,65],"data":[11,19,33,36,41,66,84,141,181,216,223],"types,":[12],"attribute":[13],"statistics,":[14],"and":[15,35,160,172,187,207],"various":[16,133],"types":[17,89,134],"dependencies,":[20,48,50],"from":[21],"raw":[22],"datasets.":[23],"Because":[24],"structural":[25,106],"metadata":[26,60,91,147,190],"often":[28],"not":[29,228],"stored":[30],"explicitly,":[31],"many":[32,97],"management":[34],"engineering":[37,182],"applications":[38,149,183],"rely":[39],"on":[40,203],"to":[43,143,163,210,219],"identify,":[44],"for":[45],"example,":[46],"functional":[47],"inclusion":[49],"or":[51,71],"uniqueness":[52],"column":[53],"combinations.":[54],"The":[55],"utilization":[56],"automatically":[58],"discovered":[59],"within":[61],"use":[62,98],"cases,":[63],"discovery,":[67],"integration,":[68],"normalization,":[69],"cleaning,":[70],"optimization,":[72],"is,":[73],"however,":[74],"a":[75,178],"still":[76],"very":[77],"complicated":[78,154],"process.":[79],"This":[80,151],"because":[82],"existing":[83],"approaches":[86],"consider":[87],"different":[88],"in":[92,95,124,184],"isolation,":[93],"although":[94],"practice,":[96],"cases":[99],"require":[100],"specific":[101],"combinations,":[102],"i.e.,":[103],"patterns":[104,131,139],"metadata.":[107,136],"For":[108],"this":[109,185],"reason,":[110],"we":[111,176],"recently":[112],"proposed":[113],"Profiling":[116],"Query":[117],"Language":[118],"DPQL":[119,137,194,200,226],"that":[120,221],"can":[121],"express":[122,144],"(and":[123],"near":[126],"future":[127],"holistically":[128],"discover)":[129],"arbitrary":[130],"query":[138,195],"allow":[140],"scientists":[142],"exactly":[145],"what":[146],"real-world":[148],"require.":[150],"eliminates":[152],"otherwise":[153],"post-processing":[155],"efforts,":[156],"reduces":[157],"result":[158,201,212,236],"sizes,":[159],"might":[161],"lead":[162],"significantly":[164],"shorter":[165],"times.":[167],"To":[168],"demonstrate":[169,220],"expressiveness":[171],"versatility":[173],"DPQL,":[175],"survey":[177],"variety":[179],"paper":[186],"solve":[188],"their":[189],"requirements":[191],"with":[192,225],"concrete":[193],"patterns.":[196],"We":[197],"also":[198,233],"measure":[199],"sizes":[202,213],"two":[204],"benchmark":[205],"datasets":[206],"compare":[208],"them":[209],"standard":[215],"algorithms":[218],"holistic":[222],"produces":[227],"only":[229],"more":[230],"suitable,":[231],"but":[232],"much":[234],"smaller":[235],"sets.":[237]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
