{"id":"https://openalex.org/W108554064","doi":"https://doi.org/10.1007/978-3-642-22913-8_18","title":"Data De-duplication: A Review","display_name":"Data De-duplication: A Review","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W108554064","doi":"https://doi.org/10.1007/978-3-642-22913-8_18","mag":"108554064"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-22913-8_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-22913-8_18","pdf_url":null,"source":{"id":"https://openalex.org/S2764461748","display_name":"Studies in computational intelligence","issn_l":"1860-949X","issn":["1860-949X","1860-9503"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Computational Intelligence","raw_type":"book-chapter"},"type":"book-chapter","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/A5076708603","display_name":"Gianni Costa","orcid":"https://orcid.org/0000-0003-2267-9280"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210137435","display_name":"Interactions, Corpus, Apprentissages, Repr\u00e9sentations","ror":"https://ror.org/04mn0nr69","country_code":"FR","type":"facility","lineage":["https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210137435"]}],"countries":["FR","IT"],"is_corresponding":false,"raw_author_name":"Gianni Costa","raw_affiliation_strings":["ICAR-CNR, Rende, Italy","ICAR, CNR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICAR-CNR, Rende, Italy","institution_ids":["https://openalex.org/I3005160176"]},{"raw_affiliation_string":"ICAR, CNR","institution_ids":["https://openalex.org/I4210137435"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053225136","display_name":"Alfredo Cuzzocrea","orcid":"https://orcid.org/0000-0002-7104-6415"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210137435","display_name":"Interactions, Corpus, Apprentissages, Repr\u00e9sentations","ror":"https://ror.org/04mn0nr69","country_code":"FR","type":"facility","lineage":["https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210137435"]}],"countries":["FR","IT"],"is_corresponding":false,"raw_author_name":"Alfredo Cuzzocrea","raw_affiliation_strings":["ICAR-CNR, Rende, Italy","ICAR, CNR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICAR-CNR, Rende, Italy","institution_ids":["https://openalex.org/I3005160176"]},{"raw_affiliation_string":"ICAR, CNR","institution_ids":["https://openalex.org/I4210137435"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004372595","display_name":"Giuseppe Manco","orcid":"https://orcid.org/0000-0001-9672-3833"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210137435","display_name":"Interactions, Corpus, Apprentissages, Repr\u00e9sentations","ror":"https://ror.org/04mn0nr69","country_code":"FR","type":"facility","lineage":["https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210137435"]}],"countries":["FR","IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Manco","raw_affiliation_strings":["ICAR-CNR, Rende, Italy","ICAR, CNR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICAR-CNR, Rende, Italy","institution_ids":["https://openalex.org/I3005160176"]},{"raw_affiliation_string":"ICAR, CNR","institution_ids":["https://openalex.org/I4210137435"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078466922","display_name":"Riccardo Ortale","orcid":"https://orcid.org/0000-0002-1763-9121"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210137435","display_name":"Interactions, Corpus, Apprentissages, Repr\u00e9sentations","ror":"https://ror.org/04mn0nr69","country_code":"FR","type":"facility","lineage":["https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210137435"]}],"countries":["FR","IT"],"is_corresponding":false,"raw_author_name":"Riccardo Ortale","raw_affiliation_strings":["ICAR-CNR, Rende, Italy","ICAR, CNR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICAR-CNR, Rende, Italy","institution_ids":["https://openalex.org/I3005160176"]},{"raw_affiliation_string":"ICAR, CNR","institution_ids":["https://openalex.org/I4210137435"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1803,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93857494,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9811999797821045,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.977400004863739,"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/computer-science","display_name":"Computer science","score":0.7842932343482971},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6241044998168945},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6073516607284546},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.5667092204093933},{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.5591480731964111},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5121921896934509},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4973004162311554},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.480406790971756},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.46830689907073975},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4377610683441162},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4252238869667053},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4186094105243683},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1863744556903839}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842932343482971},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6241044998168945},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6073516607284546},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.5667092204093933},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.5591480731964111},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5121921896934509},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4973004162311554},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.480406790971756},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.46830689907073975},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4377610683441162},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4252238869667053},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4186094105243683},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1863744556903839},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-22913-8_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-22913-8_18","pdf_url":null,"source":{"id":"https://openalex.org/S2764461748","display_name":"Studies in computational intelligence","issn_l":"1860-949X","issn":["1860-949X","1860-9503"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Computational Intelligence","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":101,"referenced_works":["https://openalex.org/W36024057","https://openalex.org/W41404523","https://openalex.org/W118209581","https://openalex.org/W938539187","https://openalex.org/W1502916507","https://openalex.org/W1526619693","https://openalex.org/W1559390933","https://openalex.org/W1569123402","https://openalex.org/W1591593356","https://openalex.org/W1612155886","https://openalex.org/W1646278814","https://openalex.org/W1660390307","https://openalex.org/W1673310716","https://openalex.org/W1925598861","https://openalex.org/W1934019294","https://openalex.org/W1943251102","https://openalex.org/W1971784203","https://openalex.org/W1981590391","https://openalex.org/W1982806687","https://openalex.org/W1991800036","https://openalex.org/W1992419399","https://openalex.org/W1995541812","https://openalex.org/W1997927541","https://openalex.org/W1999823970","https://openalex.org/W2004539934","https://openalex.org/W2014879296","https://openalex.org/W2024770506","https://openalex.org/W2029873015","https://openalex.org/W2030689309","https://openalex.org/W2033626294","https://openalex.org/W2034190452","https://openalex.org/W2036216970","https://openalex.org/W2038044292","https://openalex.org/W2038276547","https://openalex.org/W2045339614","https://openalex.org/W2049633694","https://openalex.org/W2052390074","https://openalex.org/W2052581258","https://openalex.org/W2057712948","https://openalex.org/W2065199439","https://openalex.org/W2065528935","https://openalex.org/W2065610969","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2082938030","https://openalex.org/W2087064593","https://openalex.org/W2096598900","https://openalex.org/W2097730395","https://openalex.org/W2097776316","https://openalex.org/W2102869387","https://openalex.org/W2104511295","https://openalex.org/W2105423800","https://openalex.org/W2108991785","https://openalex.org/W2109541479","https://openalex.org/W2111625757","https://openalex.org/W2113975509","https://openalex.org/W2120720997","https://openalex.org/W2123561513","https://openalex.org/W2124410446","https://openalex.org/W2125233616","https://openalex.org/W2125530761","https://openalex.org/W2127674618","https://openalex.org/W2127675794","https://openalex.org/W2129571114","https://openalex.org/W2129598390","https://openalex.org/W2130263740","https://openalex.org/W2130416410","https://openalex.org/W2131687179","https://openalex.org/W2139450862","https://openalex.org/W2140212450","https://openalex.org/W2145065594","https://openalex.org/W2146474310","https://openalex.org/W2147717514","https://openalex.org/W2148019918","https://openalex.org/W2148524305","https://openalex.org/W2148781362","https://openalex.org/W2150698190","https://openalex.org/W2151023586","https://openalex.org/W2151179595","https://openalex.org/W2152565070","https://openalex.org/W2154756203","https://openalex.org/W2154785834","https://openalex.org/W2157092487","https://openalex.org/W2159481891","https://openalex.org/W2161936973","https://openalex.org/W2164456230","https://openalex.org/W2170039925","https://openalex.org/W2338189341","https://openalex.org/W2397770138","https://openalex.org/W2501776421","https://openalex.org/W2610179052","https://openalex.org/W2623600023","https://openalex.org/W2914959486","https://openalex.org/W3146259567","https://openalex.org/W3152364157","https://openalex.org/W4230502578","https://openalex.org/W4235019056","https://openalex.org/W4248373945","https://openalex.org/W4254139725","https://openalex.org/W4254788633","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2492590231","https://openalex.org/W2355440778","https://openalex.org/W2064717691","https://openalex.org/W2164160537","https://openalex.org/W2372493300","https://openalex.org/W2391399503","https://openalex.org/W4244644848","https://openalex.org/W2341628596","https://openalex.org/W2110778011","https://openalex.org/W4255070144"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}