{"id":"https://openalex.org/W3121133979","doi":"https://doi.org/10.1145/3428757.3429129","title":"Unsupervised Evaluation of Data Integration Processes","display_name":"Unsupervised Evaluation of Data Integration Processes","publication_year":2020,"publication_date":"2020-11-30","ids":{"openalex":"https://openalex.org/W3121133979","doi":"https://doi.org/10.1145/3428757.3429129","mag":"3121133979"},"language":"en","primary_location":{"id":"doi:10.1145/3428757.3429129","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428757.3429129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11380/1237815","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037298798","display_name":"Matteo Paganelli","orcid":"https://orcid.org/0000-0001-8119-895X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Matteo Paganelli","raw_affiliation_strings":["DIEF-UNIMORE"],"affiliations":[{"raw_affiliation_string":"DIEF-UNIMORE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063748915","display_name":"Francesco Del Buono","orcid":"https://orcid.org/0000-0003-0024-2563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesco Del Buono","raw_affiliation_strings":["DIEF-UNIMORE"],"affiliations":[{"raw_affiliation_string":"DIEF-UNIMORE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005665643","display_name":"Francesco Guerra","orcid":"https://orcid.org/0000-0001-6864-568X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesco Guerra","raw_affiliation_strings":["DIEF-UNIMORE"],"affiliations":[{"raw_affiliation_string":"DIEF-UNIMORE","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069843101","display_name":"Nicola Ferro","orcid":"https://orcid.org/0000-0001-9219-6239"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Ferro","raw_affiliation_strings":["University of Padua, Italy"],"affiliations":[{"raw_affiliation_string":"University of Padua, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037298798"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3705,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68372534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.995199978351593,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.8270201683044434},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7640314698219299},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.6800487637519836},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6567855477333069},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5983745455741882},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5899223685264587},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5758570432662964},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4675067365169525},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4269663989543915},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4135035276412964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3603072762489319},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3297058939933777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270201683044434},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7640314698219299},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.6800487637519836},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6567855477333069},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5983745455741882},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5899223685264587},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5758570432662964},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4675067365169525},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4269663989543915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4135035276412964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3603072762489319},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3297058939933777},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3428757.3429129","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428757.3429129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unimore.it:11380/1237815","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1237815","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:www.research.unipd.it:11577/3367842","is_oa":false,"landing_page_url":"http://hdl.handle.net/11577/3367842","pdf_url":null,"source":{"id":"https://openalex.org/S4377196283","display_name":"Research Padua  Archive (University of Padua)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.unimore.it:11380/1237815","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1237815","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1990578345","https://openalex.org/W2039789840","https://openalex.org/W2056748234","https://openalex.org/W2114764731","https://openalex.org/W2119320829","https://openalex.org/W2225677724","https://openalex.org/W2232417456","https://openalex.org/W2592734881","https://openalex.org/W2604399864","https://openalex.org/W2613666425","https://openalex.org/W2785119431","https://openalex.org/W2915915402","https://openalex.org/W2964223984","https://openalex.org/W2986691260","https://openalex.org/W3044624184","https://openalex.org/W3194736015"],"related_works":["https://openalex.org/W2748020237","https://openalex.org/W2020045149","https://openalex.org/W2618163531","https://openalex.org/W2548532473","https://openalex.org/W2897583753","https://openalex.org/W2116862600","https://openalex.org/W2398119633","https://openalex.org/W73205277","https://openalex.org/W2245848650","https://openalex.org/W3203986070"],"abstract_inverted_index":{"Evaluation":[0],"of":[1,4,29,84,90,121],"the":[2,26,34,38,44,52,66,94,119,122],"quality":[3],"data":[5,14,30,127],"integration":[6,95,128],"processes":[7],"is":[8,18,59,82,93,106],"usually":[9],"performed":[10],"via":[11],"manual":[12,104],"onerous":[13],"inspections.":[15],"This":[16],"task":[17],"particularly":[19],"heavy":[20],"in":[21,43,125],"real":[22],"business":[23],"scenarios,":[24],"where":[25],"large":[27],"amount":[28],"makes":[31],"checking":[32],"all":[33],"tuples":[35],"infeasible":[36],"and":[37,55,97,102],"frequent":[39],"updates,":[40],"i.e.":[41],"changes":[42],"sources":[45],"and/or":[46],"new":[47],"sources,":[48],"impose":[49],"to":[50,60],"repeat":[51],"evaluation":[53],"over":[54],"over.":[56],"Our":[57],"idea":[58],"address":[61],"this":[62],"issue":[63],"by":[64],"providing":[65],"experts":[67],"with":[68],"an":[69,88],"unsupervised":[70],"measure,":[71],"based":[72],"on":[73],"word":[74],"frequencies,":[75],"which":[76],"quantifies":[77],"how":[78,91],"much":[79],"a":[80,103],"dataset":[81],"representative":[83],"another":[85],"dataset,":[86],"giving":[87],"indication":[89],"good":[92],"process":[96],"whether":[98],"deviations":[99],"are":[100],"happening":[101],"inspection":[105],"needed.":[107],"We":[108],"also":[109],"conducted":[110],"some":[111],"preliminary":[112],"experiments,":[113],"using":[114],"shared":[115],"datasets,":[116],"that":[117],"show":[118],"effectiveness":[120],"proposed":[123],"measures":[124],"typical":[126],"scenarios.":[129]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-02-01T00:00:00"}