{"id":"https://openalex.org/W4411984511","doi":"https://doi.org/10.25300/misq/2025/18178","title":"Different but the Same? An Event-Driven Approach to Determine Probabilities of Data Duplication","display_name":"Different but the Same? An Event-Driven Approach to Determine Probabilities of Data Duplication","publication_year":2025,"publication_date":"2025-07-03","ids":{"openalex":"https://openalex.org/W4411984511","doi":"https://doi.org/10.25300/misq/2025/18178"},"language":"en","primary_location":{"id":"doi:10.25300/misq/2025/18178","is_oa":false,"landing_page_url":"https://doi.org/10.25300/misq/2025/18178","pdf_url":null,"source":{"id":"https://openalex.org/S57293258","display_name":"MIS Quarterly","issn_l":"0276-7783","issn":["0276-7783","2162-9730"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4327875293","host_organization_name":"MIS Quarterly","host_organization_lineage":["https://openalex.org/P4327875293"],"host_organization_lineage_names":["MIS Quarterly"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MIS Quarterly","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102761501","display_name":"Bernd Heinrich","orcid":"https://orcid.org/0000-0003-4193-0100"},"institutions":[{"id":"https://openalex.org/I120163777","display_name":"OTH Regensburg","ror":"https://ror.org/04b9vrm74","country_code":"DE","type":"education","lineage":["https://openalex.org/I120163777"]},{"id":"https://openalex.org/I60668342","display_name":"University of Regensburg","ror":"https://ror.org/01eezs655","country_code":"DE","type":"education","lineage":["https://openalex.org/I60668342"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd Heinrich","raw_affiliation_strings":["Faculty of Computer Science and Data Science, University of Regensburg Regensburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Data Science, University of Regensburg Regensburg, Germany","institution_ids":["https://openalex.org/I120163777","https://openalex.org/I60668342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047419169","display_name":"Mathias Klier","orcid":"https://orcid.org/0000-0001-7109-0339"},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]},{"id":"https://openalex.org/I4210163522","display_name":"Technische Hochschule Ulm","ror":"https://ror.org/05e5kd476","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210163522"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mathias Klier","raw_affiliation_strings":["Faculty of Mathematics and Economics, University of Ulm Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Economics, University of Ulm Ulm, Germany","institution_ids":["https://openalex.org/I196349391","https://openalex.org/I4210163522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009343836","display_name":"Andreas Obermeier","orcid":"https://orcid.org/0000-0002-0048-8208"},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]},{"id":"https://openalex.org/I4210163522","display_name":"Technische Hochschule Ulm","ror":"https://ror.org/05e5kd476","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210163522"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Obermeier","raw_affiliation_strings":["Faculty of Mathematics and Economics, University of Ulm Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Economics, University of Ulm Ulm, Germany","institution_ids":["https://openalex.org/I196349391","https://openalex.org/I4210163522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065985284","display_name":"Alexander Schiller","orcid":"https://orcid.org/0000-0002-5545-9017"},"institutions":[{"id":"https://openalex.org/I120163777","display_name":"OTH Regensburg","ror":"https://ror.org/04b9vrm74","country_code":"DE","type":"education","lineage":["https://openalex.org/I120163777"]},{"id":"https://openalex.org/I60668342","display_name":"University of Regensburg","ror":"https://ror.org/01eezs655","country_code":"DE","type":"education","lineage":["https://openalex.org/I60668342"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Schiller","raw_affiliation_strings":["Faculty of Computer Science and Data Science, University of Regensburg Regensburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Data Science, University of Regensburg Regensburg, Germany","institution_ids":["https://openalex.org/I120163777","https://openalex.org/I60668342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6866,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72335949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"49","issue":"4","first_page":"1539","last_page":"1566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9955999851226807,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9848999977111816,"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"}},{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/gene-duplication","display_name":"Gene duplication","score":0.6139121651649475},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6089272499084473},{"id":"https://openalex.org/keywords/event-data","display_name":"Event data","score":0.4552544355392456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4450242519378662},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3787088394165039},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3360012173652649},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2841449975967407},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16188928484916687},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09015050530433655},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08811613917350769}],"concepts":[{"id":"https://openalex.org/C7602840","wikidata":"https://www.wikidata.org/wiki/Q746284","display_name":"Gene duplication","level":3,"score":0.6139121651649475},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6089272499084473},{"id":"https://openalex.org/C2987896495","wikidata":"https://www.wikidata.org/wiki/Q5416716","display_name":"Event data","level":3,"score":0.4552544355392456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4450242519378662},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3787088394165039},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3360012173652649},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2841449975967407},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16188928484916687},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09015050530433655},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08811613917350769},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.25300/misq/2025/18178","is_oa":false,"landing_page_url":"https://doi.org/10.25300/misq/2025/18178","pdf_url":null,"source":{"id":"https://openalex.org/S57293258","display_name":"MIS Quarterly","issn_l":"0276-7783","issn":["0276-7783","2162-9730"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4327875293","host_organization_name":"MIS Quarterly","host_organization_lineage":["https://openalex.org/P4327875293"],"host_organization_lineage_names":["MIS Quarterly"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MIS Quarterly","raw_type":"journal-article"},{"id":"pmh:oai:epub.uni-regensburg.de:76588","is_oa":false,"landing_page_url":"http://orcid.org/0000-0003-4193-0100>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306401229","display_name":"University of Regensburg Publication Server (University of Regensburg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60668342","host_organization_name":"University of Regensburg","host_organization_lineage":["https://openalex.org/I60668342"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:aisel.aisnet.org:misq-4018","is_oa":false,"landing_page_url":"https://aisel.aisnet.org/misq/vol49/iss4/16","pdf_url":null,"source":{"id":"https://openalex.org/S30879505","display_name":"Journal of the Association for Information Systems","issn_l":"1536-9323","issn":["1536-9323"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310321080","host_organization_name":"Association for Information Systems","host_organization_lineage":["https://openalex.org/P4310321080"],"host_organization_lineage_names":["Association for Information Systems"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Management Information Systems Quarterly","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W1213593253","https://openalex.org/W1519238942","https://openalex.org/W1567491469","https://openalex.org/W1970175046","https://openalex.org/W1978628780","https://openalex.org/W1981552604","https://openalex.org/W1985323106","https://openalex.org/W2022475295","https://openalex.org/W2024018837","https://openalex.org/W2031250218","https://openalex.org/W2035615211","https://openalex.org/W2049855118","https://openalex.org/W2050947749","https://openalex.org/W2051677513","https://openalex.org/W2073471108","https://openalex.org/W2089367555","https://openalex.org/W2092336114","https://openalex.org/W2105929850","https://openalex.org/W2108991785","https://openalex.org/W2112947832","https://openalex.org/W2114768858","https://openalex.org/W2127234432","https://openalex.org/W2164830383","https://openalex.org/W2167011595","https://openalex.org/W2168351114","https://openalex.org/W2221741097","https://openalex.org/W2248783999","https://openalex.org/W2287926972","https://openalex.org/W2341832822","https://openalex.org/W2478099072","https://openalex.org/W2498119267","https://openalex.org/W2501271607","https://openalex.org/W2515684830","https://openalex.org/W2588576526","https://openalex.org/W2606460416","https://openalex.org/W2622791136","https://openalex.org/W2767553997","https://openalex.org/W2768202326","https://openalex.org/W2897442092","https://openalex.org/W2917792182","https://openalex.org/W2920239148","https://openalex.org/W2944196176","https://openalex.org/W2947784394","https://openalex.org/W2963313478","https://openalex.org/W2963341956","https://openalex.org/W2970464057","https://openalex.org/W2980449450","https://openalex.org/W2993197938","https://openalex.org/W2999189714","https://openalex.org/W3002045227","https://openalex.org/W3004300812","https://openalex.org/W3008440336","https://openalex.org/W3014295153","https://openalex.org/W3028244158","https://openalex.org/W3034666002","https://openalex.org/W3041133507","https://openalex.org/W3048871918","https://openalex.org/W3084927323","https://openalex.org/W3092962901","https://openalex.org/W3094039038","https://openalex.org/W3103454825","https://openalex.org/W3114455979","https://openalex.org/W3125024313","https://openalex.org/W3128058776","https://openalex.org/W3143821997","https://openalex.org/W3193412448","https://openalex.org/W3194405061","https://openalex.org/W3204702778","https://openalex.org/W4210613880","https://openalex.org/W4213009331","https://openalex.org/W4225850876","https://openalex.org/W4232658882","https://openalex.org/W4236855974","https://openalex.org/W4242286335","https://openalex.org/W4242744113","https://openalex.org/W4244294689","https://openalex.org/W4244746260","https://openalex.org/W4248083651","https://openalex.org/W4299709210","https://openalex.org/W4371785005","https://openalex.org/W4371785011","https://openalex.org/W4382933626"],"related_works":["https://openalex.org/W4388014327","https://openalex.org/W2115382138","https://openalex.org/W2025614457","https://openalex.org/W4385573527","https://openalex.org/W4308672222","https://openalex.org/W4319877673","https://openalex.org/W4309044578","https://openalex.org/W3111366672","https://openalex.org/W2185070550","https://openalex.org/W4206497353"],"abstract_inverted_index":{"The":[0,178],"importance":[1],"of":[2,72,85,117,141,160,168,175,204],"data":[3,35,38,56,127,169],"quality":[4],"assessment,":[5],"in":[6,11,16,28,58,64],"general,":[7],"and":[8,19,37,43,100,119,194],"duplicate":[9,108,153,163],"detection,":[10,41],"particular,":[12],"has":[13],"been":[14],"recognized":[15],"both":[17],"research":[18],"practice.":[20],"Duplicates":[21],"are":[22,47,52],"known":[23],"to":[24,93,164,190],"cause":[25],"critical":[26],"problems":[27],"many":[29],"domains,":[30],"including":[31],"customer":[32,65],"relationship":[33],"management,":[34],"management":[36],"warehousing,":[39],"fraud":[40],"production,":[42],"healthcare.":[44],"Such":[45],"duplicates":[46,63,142],"caused":[48,67],"by":[49,68],"events":[50,99,122,138],"that":[51,185,195],"typically":[53],"associated":[54,126],"with":[55],"patterns":[57,103,128],"the":[59,69,83,86,158,196,205],"records.":[60],"For":[61],"example,":[62],"databases":[66],"event":[70],"\u201crelocation":[71],"a":[73,148,162],"customer\u201d":[74],"characteristically":[75],"exhibit":[76],"dissimilar":[77],"values":[78,84],"for":[79,107,152],"address-related":[80],"features,":[81],"while":[82,170],"other":[87],"features":[88],"(e.g.,":[89],"name-related":[90],"features)":[91],"tend":[92],"be":[94,200],"highly":[95],"similar.":[96],"Analyzing":[97],"duplicate-related":[98],"recognizing":[101],"such":[102],"seems":[104],"particularly":[105],"promising":[106],"detection.":[109,154],"However,":[110],"existing":[111,176,192],"approaches":[112,193],"do":[113],"not":[114],"take":[115],"advantage":[116],"this":[118,134,145],"neither":[120],"consider":[121],"nor":[123],"recognize":[124],"their":[125],"when":[129],"detecting":[130],"potential":[131],"duplicates.":[132],"In":[133],"paper,":[135],"we":[136],"introduce":[137],"as":[139],"causes":[140],"and,":[143],"on":[144,180],"basis,":[146],"propose":[147],"novel":[149],"probability-based":[150],"approach":[151,156,187],"Our":[155],"assigns":[157],"probability":[159],"being":[161],"each":[165],"analyzed":[166],"pair":[167],"avoiding":[171],"limiting":[172],"methodical":[173],"assumptions":[174],"approaches.":[177],"evaluation":[179],"seven":[181],"different":[182],"datasets":[183,203],"shows":[184],"our":[186],"is":[188],"able":[189],"outperform":[191],"models":[197],"learned":[198],"can":[199],"transferred":[201],"between":[202],"same":[206],"domain":[207],"without":[208],"further":[209],"labeling":[210],"or":[211],"repeated":[212],"model":[213],"learning.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}