{"id":"https://openalex.org/W4308627399","doi":"https://doi.org/10.1145/3549037.3561275","title":"Preliminary findings on the occurrence and causes of data smells in a real-world business travel data processing pipeline","display_name":"Preliminary findings on the occurrence and causes of data smells in a real-world business travel data processing pipeline","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4308627399","doi":"https://doi.org/10.1145/3549037.3561275"},"language":"en","primary_location":{"id":"doi:10.1145/3549037.3561275","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549037.3561275","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549037.3561275","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Software Engineering and AI for Data Quality in Cyber-Physical Systems/Internet of Things","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3549037.3561275","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007432566","display_name":"Valentina Golendukhina","orcid":"https://orcid.org/0000-0002-8274-5924"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Valentina Golendukhina","raw_affiliation_strings":["University of Innsbruck, Austria"],"affiliations":[{"raw_affiliation_string":"University of Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033698477","display_name":"Harald Foidl","orcid":"https://orcid.org/0000-0002-6283-0419"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Harald Foidl","raw_affiliation_strings":["University of Innsbruck, Austria"],"affiliations":[{"raw_affiliation_string":"University of Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055476405","display_name":"Michael Felderer","orcid":"https://orcid.org/0000-0003-3818-4442"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Michael Felderer","raw_affiliation_strings":["University of Innsbruck, Austria"],"affiliations":[{"raw_affiliation_string":"University of Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004548330","display_name":"Rudolf Ramler","orcid":"https://orcid.org/0000-0001-9903-6107"},"institutions":[{"id":"https://openalex.org/I4210126338","display_name":"Software Competence Center Hagenberg (Austria)","ror":"https://ror.org/02ks3nr96","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210126338"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Rudolf Ramler","raw_affiliation_strings":["Software Competence Center Hagenberg, Austria"],"affiliations":[{"raw_affiliation_string":"Software Competence Center Hagenberg, Austria","institution_ids":["https://openalex.org/I4210126338"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007432566"],"corresponding_institution_ids":["https://openalex.org/I190249584"],"apc_list":null,"apc_paid":null,"fwci":0.1637,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53853645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9968000054359436,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9865000247955322,"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/data-quality","display_name":"Data quality","score":0.7372472286224365},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7308584451675415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6799746751785278},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.6764393448829651},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6609838604927063},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.49625593423843384},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4830518364906311},{"id":"https://openalex.org/keywords/code-smell","display_name":"Code smell","score":0.4570060968399048},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.45421138405799866},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.45082566142082214},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.4303413927555084},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4006483554840088},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.3563764691352844},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.225018709897995},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21225512027740479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20344746112823486},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.15810224413871765},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.13127562403678894},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.11140367388725281},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.06806311011314392}],"concepts":[{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.7372472286224365},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7308584451675415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6799746751785278},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6764393448829651},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6609838604927063},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.49625593423843384},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4830518364906311},{"id":"https://openalex.org/C133237599","wikidata":"https://www.wikidata.org/wiki/Q2295111","display_name":"Code smell","level":5,"score":0.4570060968399048},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.45421138405799866},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.45082566142082214},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.4303413927555084},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4006483554840088},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.3563764691352844},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.225018709897995},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21225512027740479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20344746112823486},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.15810224413871765},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.13127562403678894},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.11140367388725281},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.06806311011314392},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3549037.3561275","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549037.3561275","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549037.3561275","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Software Engineering and AI for Data Quality in Cyber-Physical Systems/Internet of Things","raw_type":"proceedings-article"},{"id":"pmh:oai:diglib.uibk.ac.at/:8648067","is_oa":true,"landing_page_url":"https://resolver.obvsg.at/urn:nbn:at:at-ubi:3-33114","pdf_url":null,"source":{"id":"https://openalex.org/S4306401999","display_name":"Digital Library of the University of Innsbruck (University of Innsbruck)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143397708","host_organization_name":"Innsbruck Medical University","host_organization_lineage":["https://openalex.org/I143397708"],"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":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3549037.3561275","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549037.3561275","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549037.3561275","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Software Engineering and AI for Data Quality in Cyber-Physical Systems/Internet of Things","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327593","display_name":"Bundesministerium f\u00fcr Digitalisierung und Wirtschaftsstandort","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308627399.pdf","grobid_xml":"https://content.openalex.org/works/W4308627399.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2212194823","https://openalex.org/W2318871600","https://openalex.org/W2478602411","https://openalex.org/W3107926801","https://openalex.org/W4226428193","https://openalex.org/W4236033732","https://openalex.org/W4312355141","https://openalex.org/W4312432177"],"related_works":["https://openalex.org/W2348093825","https://openalex.org/W2901826185","https://openalex.org/W2390710026","https://openalex.org/W3119296476","https://openalex.org/W2742521120","https://openalex.org/W2353590449","https://openalex.org/W1542560311","https://openalex.org/W2159392828","https://openalex.org/W2353586736","https://openalex.org/W2335291181"],"abstract_inverted_index":{"Detection":[0],"of":[1,17,24,49,77,84,132,142],"poor":[2,46],"quality":[3,27],"data":[4,20,26,36,53,78,89,93,102,107,115,134,144,151],"is":[5,14,29,55],"crucial":[6],"for":[7,147],"enhancing":[8],"data-driven":[9],"systems'":[10],"quality.":[11],"Although":[12,113],"there":[13],"a":[15,82,85],"lot":[16],"research":[18,149],"on":[19,72,81,150],"validation,":[21],"the":[22,45,69,73,92,127,133,140,143],"topic":[23],"potential":[25,157],"issues":[28,34],"still":[30],"underexplored.":[31],"Such":[32],"latent":[33],"or":[35],"smells":[37,54,79,103,116,123],"can":[38],"often":[39],"stay":[40],"undetected":[41],"and":[42,58,75,91,109,129],"lead":[43],"to":[44],"future":[47,148,158],"performance":[48],"data-intensive":[50],"systems.":[51],"Detecting":[52],"not":[56],"trivial":[57],"requires":[59],"knowledge":[60],"about":[61],"their":[62],"causes.":[63],"In":[64],"this":[65,106,154,161],"paper,":[66],"we":[67],"present":[68],"preliminary":[70],"findings":[71,138],"causes":[74],"severity":[76],"based":[80],"study":[83],"real-world":[86],"business":[87],"travel":[88],"set":[90,108],"processing":[94,135],"pipeline":[95,145],"behind":[96],"it.":[97],"The":[98],"results":[99],"show":[100],"that":[101],"exist":[104],"in":[105,119,160],"cause":[110],"severe":[111],"problems.":[112],"many":[114],"already":[117],"occur":[118],"raw":[120],"data,":[121],"some":[122],"are":[124],"created":[125],"during":[126],"transformation":[128],"enrichment":[130],"stages":[131],"pipeline.":[136],"These":[137],"indicate":[139],"importance":[141],"itself":[146],"smells.":[152],"Thus,":[153],"article":[155],"proposes":[156],"work":[159],"area.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}