{"id":"https://openalex.org/W1598541138","doi":"https://doi.org/10.1007/978-3-319-11257-2_22","title":"Hierarchical Linkage Clustering with Distributions of Distances for Large-Scale Record Linkage","display_name":"Hierarchical Linkage Clustering with Distributions of Distances for Large-Scale Record Linkage","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W1598541138","doi":"https://doi.org/10.1007/978-3-319-11257-2_22","mag":"1598541138"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-11257-2_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-11257-2_22","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","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/A5033891696","display_name":"Samuel Ventura","orcid":"https://orcid.org/0000-0002-4178-2921"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samuel L. Ventura","raw_affiliation_strings":["Department of Statistics, Carnegie Mellon University, U.S.A","Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Carnegie Mellon University, U.S.A","institution_ids":[]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082779252","display_name":"Rebecca Nugent","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rebecca Nugent","raw_affiliation_strings":["Department of Statistics, Carnegie Mellon University, U.S.A","Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Carnegie Mellon University, U.S.A","institution_ids":[]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033891696"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.0066,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79241405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"283","last_page":"298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9258000254631042,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7716128826141357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7681260108947754},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.6430780291557312},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.6320661306381226},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6224673986434937},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6100140810012817},{"id":"https://openalex.org/keywords/complete-linkage","display_name":"Complete linkage","score":0.5818106532096863},{"id":"https://openalex.org/keywords/complete-linkage-clustering","display_name":"Complete-linkage clustering","score":0.530422031879425},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4693528115749359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4518659710884094},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4511205852031708},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.4141022264957428},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3281744122505188},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.29543596506118774},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.2424272894859314},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10957852005958557},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06080421805381775}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7716128826141357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681260108947754},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.6430780291557312},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6320661306381226},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6224673986434937},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6100140810012817},{"id":"https://openalex.org/C38734473","wikidata":"https://www.wikidata.org/wiki/Q5156506","display_name":"Complete linkage","level":5,"score":0.5818106532096863},{"id":"https://openalex.org/C23822008","wikidata":"https://www.wikidata.org/wiki/Q5156437","display_name":"Complete-linkage clustering","level":5,"score":0.530422031879425},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4693528115749359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4518659710884094},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4511205852031708},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.4141022264957428},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3281744122505188},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.29543596506118774},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.2424272894859314},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10957852005958557},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06080421805381775},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-11257-2_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-11257-2_22","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","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":25,"referenced_works":["https://openalex.org/W41404523","https://openalex.org/W1554944419","https://openalex.org/W1606722289","https://openalex.org/W1854015338","https://openalex.org/W1964879903","https://openalex.org/W2006153666","https://openalex.org/W2039001182","https://openalex.org/W2044063104","https://openalex.org/W2068535610","https://openalex.org/W2073471108","https://openalex.org/W2080099271","https://openalex.org/W2106808680","https://openalex.org/W2117173715","https://openalex.org/W2135223301","https://openalex.org/W2162337786","https://openalex.org/W2164456230","https://openalex.org/W2325888753","https://openalex.org/W2521671426","https://openalex.org/W2787894218","https://openalex.org/W2911964244","https://openalex.org/W2913066018","https://openalex.org/W2913519381","https://openalex.org/W2952919675","https://openalex.org/W4230502578","https://openalex.org/W4230521134"],"related_works":["https://openalex.org/W1985101567","https://openalex.org/W1493637077","https://openalex.org/W583850877","https://openalex.org/W2959239999","https://openalex.org/W2072104876","https://openalex.org/W2979935139","https://openalex.org/W4205753921","https://openalex.org/W3099216502","https://openalex.org/W4237773738","https://openalex.org/W328064821"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
