{"id":"https://openalex.org/W2296060041","doi":"https://doi.org/10.1007/978-3-319-28379-1_7","title":"Extending Naive Bayes Classifier with Hierarchy Feature Level Information for Record Linkage","display_name":"Extending Naive Bayes Classifier with Hierarchy Feature Level Information for Record Linkage","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2296060041","doi":"https://doi.org/10.1007/978-3-319-28379-1_7","mag":"2296060041"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-28379-1_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-28379-1_7","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-319-28379-1_7","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022422213","display_name":"Yun Zhou","orcid":"https://orcid.org/0000-0001-7328-0275"},"institutions":[{"id":"https://openalex.org/I55521800","display_name":"Goldsmiths University of London","ror":"https://ror.org/01khx4a30","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I55521800"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yun Zhou","raw_affiliation_strings":["Tungsten Centre for Intelligent Data Analytics (TCIDA), Goldsmiths, University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tungsten Centre for Intelligent Data Analytics (TCIDA), Goldsmiths, University of London, London, UK","institution_ids":["https://openalex.org/I55521800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049189804","display_name":"John Howroyd","orcid":null},"institutions":[{"id":"https://openalex.org/I55521800","display_name":"Goldsmiths University of London","ror":"https://ror.org/01khx4a30","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I55521800"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Howroyd","raw_affiliation_strings":["Tungsten Centre for Intelligent Data Analytics (TCIDA), Goldsmiths, University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tungsten Centre for Intelligent Data Analytics (TCIDA), Goldsmiths, University of London, London, UK","institution_ids":["https://openalex.org/I55521800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105935151","display_name":"Sebastian Danicic","orcid":null},"institutions":[{"id":"https://openalex.org/I55521800","display_name":"Goldsmiths University of London","ror":"https://ror.org/01khx4a30","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I55521800"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sebastian Danicic","raw_affiliation_strings":["Tungsten Centre for Intelligent Data Analytics (TCIDA), Goldsmiths, University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tungsten Centre for Intelligent Data Analytics (TCIDA), Goldsmiths, University of London, London, UK","institution_ids":["https://openalex.org/I55521800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020811661","display_name":"J. M. Bishop","orcid":"https://orcid.org/0000-0003-0749-7737"},"institutions":[{"id":"https://openalex.org/I55521800","display_name":"Goldsmiths University of London","ror":"https://ror.org/01khx4a30","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I55521800"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"J. Mark Bishop","raw_affiliation_strings":["Tungsten Centre for Intelligent Data Analytics (TCIDA), Goldsmiths, University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tungsten Centre for Intelligent Data Analytics (TCIDA), Goldsmiths, University of London, London, UK","institution_ids":["https://openalex.org/I55521800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022422213"],"corresponding_institution_ids":["https://openalex.org/I55521800"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.9352,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75566949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"104"},"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9922000169754028,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9013000130653381,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.8499290943145752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7602931261062622},{"id":"https://openalex.org/keywords/probabilistic-classification","display_name":"Probabilistic classification","score":0.6551516056060791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6434329748153687},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6398993730545044},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.620159387588501},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5521860122680664},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.5022823810577393},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4875797629356384},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46803808212280273},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4422356188297272},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4346201717853546},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.43301916122436523},{"id":"https://openalex.org/keywords/bayes-classifier","display_name":"Bayes classifier","score":0.4208206236362457},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.40353450179100037},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.11909770965576172}],"concepts":[{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.8499290943145752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602931261062622},{"id":"https://openalex.org/C189119545","wikidata":"https://www.wikidata.org/wiki/Q5128022","display_name":"Probabilistic classification","level":4,"score":0.6551516056060791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6434329748153687},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6398993730545044},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.620159387588501},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5521860122680664},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.5022823810577393},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4875797629356384},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46803808212280273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4422356188297272},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4346201717853546},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.43301916122436523},{"id":"https://openalex.org/C185207860","wikidata":"https://www.wikidata.org/wiki/Q17004744","display_name":"Bayes classifier","level":4,"score":0.4208206236362457},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.40353450179100037},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.11909770965576172},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-319-28379-1_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-28379-1_7","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:eprints.gold.ac.uk:17381","is_oa":false,"landing_page_url":"https://research.gold.ac.uk/view/goldsmiths/Zhou=3AYun=3A=3A.html>;","pdf_url":null,"source":{"id":"https://openalex.org/S4306400496","display_name":"Goldsmiths (University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"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":"Conference or Workshop Item"}],"best_oa_location":{"id":"doi:10.1007/978-3-319-28379-1_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-28379-1_7","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W41404523","https://openalex.org/W46452414","https://openalex.org/W143355615","https://openalex.org/W1517993545","https://openalex.org/W1559390933","https://openalex.org/W1761401273","https://openalex.org/W1817561967","https://openalex.org/W2009325985","https://openalex.org/W2024018837","https://openalex.org/W2034190452","https://openalex.org/W2071218570","https://openalex.org/W2073471108","https://openalex.org/W2087483562","https://openalex.org/W2108991785","https://openalex.org/W2133990480","https://openalex.org/W2157468491","https://openalex.org/W2170112109","https://openalex.org/W3146259567","https://openalex.org/W4234053595"],"related_works":["https://openalex.org/W1972450020","https://openalex.org/W2996897273","https://openalex.org/W1607432302","https://openalex.org/W83434975","https://openalex.org/W1584413767","https://openalex.org/W2537862391","https://openalex.org/W145653800","https://openalex.org/W2342969114","https://openalex.org/W2122175496","https://openalex.org/W2393473353"],"abstract_inverted_index":{"Probabilistic":[0],"record":[1,13,81],"linkage":[2,14,82],"has":[3,61,77],"been":[4,48,62],"well":[5],"investigated":[6,84],"in":[7,67,80],"recent":[8],"years.":[9],"The":[10],"Fellegi-Sunter":[11],"probabilistic":[12],"and":[15,26,44,64,83,117],"its":[16],"enhanced":[17],"version":[18,56],"are":[19],"commonly":[20],"used":[21,50],"methods,":[22],"which":[23],"calculate":[24],"match":[25],"non-match":[27],"weights":[28],"for":[29],"each":[30],"pair":[31],"of":[32,35,57,87],"corresponding":[33],"fields":[34],"record-pairs.":[36],"Bayesian":[37],"network":[38],"classifiers":[39],"\u2013":[40],"naive":[41,102],"Bayes":[42,103],"classifier":[43,104],"TAN":[45,58],"have":[46],"also":[47],"successfully":[49],"here.":[51],"Very":[52],"recently,":[53],"an":[54],"extended":[55],"(called":[59],"ETAN)":[60],"developed":[63],"proved":[65],"superior":[66],"classification":[68],"accuracy":[69],"to":[70,114],"conventional":[71],"TAN.":[72],"However,":[73],"no":[74],"previous":[75],"work":[76],"applied":[78],"ETAN":[79],"the":[85,101,112,119],"benefits":[86],"using":[88],"a":[89],"naturally":[90],"existing":[91],"hierarchy":[92],"feature":[93],"level":[94],"information.":[95,107],"In":[96],"this":[97],"work,":[98],"we":[99,109],"extend":[100],"with":[105],"such":[106],"Finally":[108],"apply":[110],"all":[111],"methods":[113],"four":[115],"datasets":[116],"estimate":[118],"$$F_1$$":[120],"scores.":[121]},"counts_by_year":[{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}