{"id":"https://openalex.org/W2350343990","doi":"https://doi.org/10.5220/0005868700750080","title":"SJClust: Towards a Framework for Integrating Similarity Join Algorithms and Clustering","display_name":"SJClust: Towards a Framework for Integrating Similarity Join Algorithms and Clustering","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2350343990","doi":"https://doi.org/10.5220/0005868700750080","mag":"2350343990"},"language":"en","primary_location":{"id":"doi:10.5220/0005868700750080","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005868700750080","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0005868700750080","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109047760","display_name":"Leonardo Andrade Ribeiro","orcid":"https://orcid.org/0009-0006-4683-7975"},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo Andrade Ribeiro","raw_affiliation_strings":["Universidade Federal de Goi\u00e1s, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Goi\u00e1s, Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053225136","display_name":"Alfredo Cuzzocrea","orcid":"https://orcid.org/0000-0002-7104-6415"},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alfredo Cuzzocrea","raw_affiliation_strings":["University of Trieste and ICAR-CNR, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trieste and ICAR-CNR, Italy","institution_ids":["https://openalex.org/I142444530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051636502","display_name":"Karen Aline Alves Bezerra","orcid":null},"institutions":[{"id":"https://openalex.org/I1315085146","display_name":"Universidade Federal de Lavras","ror":"https://ror.org/0122bmm03","country_code":"BR","type":"education","lineage":["https://openalex.org/I1315085146"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Karen Aline Alves Bezerra","raw_affiliation_strings":["Universidade Federal de Lavras, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Lavras, Brazil","institution_ids":["https://openalex.org/I1315085146"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041039707","display_name":"Ben Hur Bahia do Nascimento","orcid":null},"institutions":[{"id":"https://openalex.org/I1315085146","display_name":"Universidade Federal de Lavras","ror":"https://ror.org/0122bmm03","country_code":"BR","type":"education","lineage":["https://openalex.org/I1315085146"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ben Hur Bahia do Nascimento","raw_affiliation_strings":["Universidade Federal de Lavras, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Lavras, Brazil","institution_ids":["https://openalex.org/I1315085146"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.693,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8132905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9965000152587891,"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/T11106","display_name":"Data Management and Algorithms","score":0.9837999939918518,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7887696027755737},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7809045314788818},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6529467105865479},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.612849235534668},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.586718738079071},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5056254863739014},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.46908727288246155},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4678994417190552},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.42470115423202515},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4127481281757355},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4061756432056427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2845016419887543},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11541715264320374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887696027755737},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7809045314788818},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6529467105865479},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.612849235534668},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.586718738079071},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5056254863739014},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46908727288246155},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4678994417190552},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.42470115423202515},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4127481281757355},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4061756432056427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2845016419887543},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11541715264320374},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0005868700750080","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005868700750080","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arts.units.it:11368/2898316","is_oa":false,"landing_page_url":"http://hdl.handle.net/11368/2898316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400480","display_name":"ArTS Archivio della ricerca di Trieste (University of Trieste https://www.units.it/)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142444530","host_organization_name":"University of Trieste","host_organization_lineage":["https://openalex.org/I142444530"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0005868700750080","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005868700750080","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4205996836","https://openalex.org/W2151692181","https://openalex.org/W4392498349","https://openalex.org/W2093960938","https://openalex.org/W3214148052","https://openalex.org/W4392216655","https://openalex.org/W2807741550","https://openalex.org/W794462722","https://openalex.org/W2029625042","https://openalex.org/W4256664196"],"abstract_inverted_index":{"A":[0,19],"critical":[1],"task":[2],"in":[3],"data":[4],"cleaning":[5],"and":[6,66,89,106],"integration":[7],"is":[8,53],"the":[9,15,46,50,63,71,74],"identification":[10,24],"of":[11,31,73,103],"duplicate":[12,23],"records":[13,33,42],"representing":[14],"same":[16,47],"real-world":[17],"entity.":[18,48],"popular":[20],"approach":[21,96],"to":[22,28,39,45,85,98],"employs":[25],"similarity":[26,87,111],"join":[27,88,112],"find":[29],"pairs":[30],"similar":[32],"followed":[34],"by":[35],"a":[36,57,83,92,101],"clustering":[37,51,90],"algorithm":[38,52],"group":[40],"together":[41],"that":[43],"refer":[44],"However,":[49],"strictly":[54],"used":[55],"as":[56],"post-processing":[58],"step,":[59],"which":[60],"slows":[61],"down":[62],"overall":[64],"performance":[65],"only":[67],"produces":[68],"results":[69],"at":[70],"end":[72],"whole":[75],"process.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"propose":[81],"SjClust,":[82],"framework":[84],"integrate":[86],"into":[91,109],"single":[93],"operation.":[94],"Our":[95],"allows":[97],"smoothly":[99],"accommodating":[100],"variety":[102],"cluster":[104],"representation":[105],"merging":[107],"strategies":[108],"set":[110],"algorithms,":[113],"while":[114],"fully":[115],"leveraging":[116],"state-of-the-art":[117],"optimization":[118],"techniques.":[119]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
