{"id":"https://openalex.org/W4379620286","doi":"https://doi.org/10.1145/3555776.3578724","title":"On evaluating text similarity measures for customer data deduplication","display_name":"On evaluating text similarity measures for customer data deduplication","publication_year":2023,"publication_date":"2023-03-27","ids":{"openalex":"https://openalex.org/W4379620286","doi":"https://doi.org/10.1145/3555776.3578724"},"language":"en","primary_location":{"id":"doi:10.1145/3555776.3578724","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3555776.3578724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","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":true,"raw_author_name":"Pawel Boinski","raw_affiliation_strings":["Poznan University of Technology, Poznan, Poland"],"raw_orcid":"https://orcid.org/0000-0003-4914-9394","affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092105216","display_name":"Mariusz Sienkiewicz","orcid":"https://orcid.org/0000-0002-1665-4928"},"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":"Mariusz Sienkiewicz","raw_affiliation_strings":["Poznan University of Technology, Poznan, Poland"],"raw_orcid":"https://orcid.org/0000-0002-1665-4928","affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","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":false,"raw_author_name":"Robert Wrembel","raw_affiliation_strings":["Poznan University of Technology, Poznan, Poland"],"raw_orcid":"https://orcid.org/0000-0001-6037-5718","affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Poznan, 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 Bebel","raw_affiliation_strings":["Poznan University of Technology, Poznan, Poland"],"raw_orcid":"https://orcid.org/0000-0002-6426-3809","affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"last","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, Poznan, Poland"],"raw_orcid":"https://orcid.org/0000-0001-9486-929X","affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022879000"],"corresponding_institution_ids":["https://openalex.org/I46597724"],"apc_list":null,"apc_paid":null,"fwci":0.4931,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6703306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"18","issue":null,"first_page":"297","last_page":"300"},"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":0.9753999710083008,"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":0.9729999899864197,"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":0.9048327803611755},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.8374637365341187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.669528603553772},{"id":"https://openalex.org/keywords/financial-institution","display_name":"Financial institution","score":0.6167793869972229},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6043845415115356},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4882926940917969},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47642335295677185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2926500141620636},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21867266297340393},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07941922545433044},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.07114419341087341}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9048327803611755},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8374637365341187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.669528603553772},{"id":"https://openalex.org/C2779601481","wikidata":"https://www.wikidata.org/wiki/Q650241","display_name":"Financial institution","level":2,"score":0.6167793869972229},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6043845415115356},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4882926940917969},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47642335295677185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2926500141620636},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21867266297340393},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07941922545433044},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.07114419341087341},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3555776.3578724","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3555776.3578724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6922271065","display_name":null,"funder_award_id":"POIR.01.01.01-00-0287/19","funder_id":"https://openalex.org/F4320327261","funder_display_name":"National Center for Research and Development"}],"funders":[{"id":"https://openalex.org/F4320327261","display_name":"National Center for Research and Development","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2104511295","https://openalex.org/W2123561513","https://openalex.org/W3007475739","https://openalex.org/W3146259567"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4296125805","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W1982579475"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"summarize":[4],"the":[5,54,61],"results":[6],"obtained":[7],"while":[8],"evaluating":[9],"44":[10],"similarity":[11,37,43,72],"measures":[12,38],"for":[13,29],"text":[14],"values,":[15],"which":[16],"represent":[17],"real":[18],"institutional":[19],"customers":[20],"data.":[21],"These":[22],"data":[23],"come":[24],"from":[25],"a":[26,30,67],"project":[27],"conducted":[28],"large":[31,68],"financial":[32],"institution":[33],"in":[34],"Poland.":[35],"The":[36],"were":[39],"assessed":[40],"based":[41,48],"on":[42,49],"values":[44],"they":[45],"returned":[46],"and":[47],"their":[50],"execution":[51],"times.":[52],"To":[53],"best":[55],"of":[56,70],"our":[57],"knowledge,":[58],"it":[59],"is":[60],"first":[62],"report":[63],"that":[64],"evaluates":[65],"such":[66],"selection":[69],"different":[71],"measures.":[73]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
