{"id":"https://openalex.org/W4385958679","doi":"https://doi.org/10.1007/978-3-031-39847-6_11","title":"On Tuning the Sorted Neighborhood Method for Record Comparisons in a Data Deduplication Pipeline","display_name":"On Tuning the Sorted Neighborhood Method for Record Comparisons in a Data Deduplication Pipeline","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385958679","doi":"https://doi.org/10.1007/978-3-031-39847-6_11"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-39847-6_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-39847-6_11","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":"conference-paper","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/A5022879000","display_name":"Pawe\u0142 Boi\u0144ski","orcid":"https://orcid.org/0000-0003-4914-9394"},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Pawe\u0142 Boi\u0144ski","raw_affiliation_strings":["Poznan University of Technology, Pozna\u0144, Poland"],"raw_orcid":"https://orcid.org/0000-0003-4914-9394","affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Pozna\u0144, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065038855","display_name":"Witold Andrzejewski","orcid":"https://orcid.org/0000-0001-9486-929X"},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Witold Andrzejewski","raw_affiliation_strings":["Poznan University of Technology, Pozna\u0144, Poland"],"raw_orcid":"https://orcid.org/0000-0001-9486-929X","affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Pozna\u0144, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080120294","display_name":"Bartosz B\u0119bel","orcid":"https://orcid.org/0000-0002-6426-3809"},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Bartosz B\u0119bel","raw_affiliation_strings":["Poznan University of Technology, Pozna\u0144, Poland"],"raw_orcid":"https://orcid.org/0000-0002-6426-3809","affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Pozna\u0144, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054888563","display_name":"Robert Wrembel","orcid":"https://orcid.org/0000-0001-6037-5718"},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Robert Wrembel","raw_affiliation_strings":["Artificial Intelligence and Cybersecurity Center, Pozna\u0144, Poland","Poznan University of Technology, Pozna\u0144, Poland"],"raw_orcid":"https://orcid.org/0000-0001-6037-5718","affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Cybersecurity Center, Pozna\u0144, Poland","institution_ids":[]},{"raw_affiliation_string":"Poznan University of Technology, Pozna\u0144, Poland","institution_ids":["https://openalex.org/I46597724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054888563"],"corresponding_institution_ids":["https://openalex.org/I46597724"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.4414,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8246661,"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":"164","last_page":"178"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9886000156402588,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9793000221252441,"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/data-deduplication","display_name":"Data deduplication","score":0.9424437284469604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8687403202056885},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7966113090515137},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5719048380851746},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.528715193271637},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5237962007522583},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.4959312379360199},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4586491584777832},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4465923011302948},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.4454110562801361},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.44170475006103516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14915955066680908},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13817098736763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11819514632225037},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08376622200012207}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9424437284469604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8687403202056885},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7966113090515137},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5719048380851746},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.528715193271637},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5237962007522583},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.4959312379360199},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4586491584777832},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4465923011302948},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.4454110562801361},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.44170475006103516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14915955066680908},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13817098736763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11819514632225037},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08376622200012207},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-39847-6_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-39847-6_11","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":[{"id":"https://metadata.un.org/sdg/9","score":0.5600000023841858,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W131624900","https://openalex.org/W1562135275","https://openalex.org/W1845040079","https://openalex.org/W1985558865","https://openalex.org/W2017167478","https://openalex.org/W2020344074","https://openalex.org/W2031250218","https://openalex.org/W2037801532","https://openalex.org/W2039001182","https://openalex.org/W2104511295","https://openalex.org/W2111116800","https://openalex.org/W2114013702","https://openalex.org/W2166988329","https://openalex.org/W2402667324","https://openalex.org/W3007475739","https://openalex.org/W3014295153","https://openalex.org/W3092962901","https://openalex.org/W3146259567","https://openalex.org/W4242744113","https://openalex.org/W4389295222"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W2943088381","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W4296125805","https://openalex.org/W3216372614","https://openalex.org/W2187819724"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
