{"id":"https://openalex.org/W2727795207","doi":"https://doi.org/10.1007/978-3-319-62386-3_4","title":"Pivot-Based Similarity Wide-Joins Fostering Near-Duplicate Detection","display_name":"Pivot-Based Similarity Wide-Joins Fostering Near-Duplicate Detection","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2727795207","doi":"https://doi.org/10.1007/978-3-319-62386-3_4","mag":"2727795207"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-62386-3_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-62386-3_4","pdf_url":null,"source":{"id":"https://openalex.org/S4210177767","display_name":"Lecture notes in business information processing","issn_l":"1865-1348","issn":["1865-1348","1865-1356"],"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 Business Information Processing","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/A5005872347","display_name":"Luiz Olmes Carvalho","orcid":null},"institutions":[{"id":"https://openalex.org/I140062455","display_name":"Instituto Federal de Educa\u00e7\u00e3o, Ci\u00eancia e Tecnologia de Minas Gerais","ror":"https://ror.org/0553w5c95","country_code":"BR","type":"education","lineage":["https://openalex.org/I1293487690","https://openalex.org/I140062455","https://openalex.org/I2801200668"]},{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Luiz Olmes Carvalho","raw_affiliation_strings":["Federal Institute of Minas Gerais, Belo Horizonte, MG, Brazil","Institute of Mathematics and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal Institute of Minas Gerais, Belo Horizonte, MG, Brazil","institution_ids":["https://openalex.org/I140062455"]},{"raw_affiliation_string":"Institute of Mathematics and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090817031","display_name":"L\u00facio F. D. Santos","orcid":"https://orcid.org/0000-0002-0495-4763"},"institutions":[{"id":"https://openalex.org/I140062455","display_name":"Instituto Federal de Educa\u00e7\u00e3o, Ci\u00eancia e Tecnologia de Minas Gerais","ror":"https://ror.org/0553w5c95","country_code":"BR","type":"education","lineage":["https://openalex.org/I1293487690","https://openalex.org/I140062455","https://openalex.org/I2801200668"]},{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]},{"id":"https://openalex.org/I43526919","display_name":"Universidade Estadual de Montes Claros","ror":"https://ror.org/01hewbk46","country_code":"BR","type":"education","lineage":["https://openalex.org/I43526919"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucio Fernandes Dutra Santos","raw_affiliation_strings":["Federal Institute in the North of Minas Gerais, Montes Claros, MG, Brazil","Institute of Mathematics and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal Institute in the North of Minas Gerais, Montes Claros, MG, Brazil","institution_ids":["https://openalex.org/I43526919","https://openalex.org/I140062455"]},{"raw_affiliation_string":"Institute of Mathematics and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014783020","display_name":"Agma J. M. Traina","orcid":"https://orcid.org/0000-0003-4929-7258"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Agma Juci Machado Traina","raw_affiliation_strings":["Institute of Mathematics and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematics and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020611078","display_name":"Caetano Traina","orcid":"https://orcid.org/0000-0002-6625-6047"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Caetano Traina","raw_affiliation_strings":["Institute of Mathematics and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematics and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005872347"],"corresponding_institution_ids":["https://openalex.org/I140062455","https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":1.0093,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76739417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"81","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":0.9994999766349792,"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":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9943000078201294,"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/joins","display_name":"Joins","score":0.9027256965637207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7530632019042969},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6844757795333862},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.6245949864387512},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6004393696784973},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5238112211227417},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5228683948516846},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5140591859817505},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4984560012817383},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4764419198036194},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34457308053970337},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25660014152526855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20158717036247253}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9027256965637207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530632019042969},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6844757795333862},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.6245949864387512},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6004393696784973},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5238112211227417},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5228683948516846},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5140591859817505},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4984560012817383},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4764419198036194},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34457308053970337},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25660014152526855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20158717036247253},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-62386-3_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-62386-3_4","pdf_url":null,"source":{"id":"https://openalex.org/S4210177767","display_name":"Lecture notes in business information processing","issn_l":"1865-1348","issn":["1865-1348","1865-1356"],"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 Business Information Processing","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W214577476","https://openalex.org/W1909366555","https://openalex.org/W1969294188","https://openalex.org/W1972195523","https://openalex.org/W1977091720","https://openalex.org/W1987325136","https://openalex.org/W2016380647","https://openalex.org/W2055906546","https://openalex.org/W2065259291","https://openalex.org/W2097184821","https://openalex.org/W2119441285","https://openalex.org/W2170872123","https://openalex.org/W2214590652","https://openalex.org/W2310857397","https://openalex.org/W2370551205","https://openalex.org/W3105270602","https://openalex.org/W4248904304"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W2172084996"],"abstract_inverted_index":null,"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
