{"id":"https://openalex.org/W2894715570","doi":"https://doi.org/10.1145/3209280.3229109","title":"Document clustering as a record linkage problem","display_name":"Document clustering as a record linkage problem","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2894715570","doi":"https://doi.org/10.1145/3209280.3229109","mag":"2894715570"},"language":"en","primary_location":{"id":"doi:10.1145/3209280.3229109","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209280.3229109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2018","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/A5077385373","display_name":"Nikiforos Pittaras","orcid":"https://orcid.org/0000-0002-9817-7618"},"institutions":[{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":null,"type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]},{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Nikiforos Pittaras","raw_affiliation_strings":["Institute of Informatics and Telecommunications, N.C.S.R. Demokritos, Greece"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, N.C.S.R. Demokritos, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048495248","display_name":"George Giannakopoulos","orcid":"https://orcid.org/0000-0003-2459-589X"},"institutions":[{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":null,"type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]},{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Giannakopoulos","raw_affiliation_strings":["Institute of Informatics and Telecommunications, N.C.S.R. Demokritos, Greece"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, N.C.S.R. Demokritos, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032888405","display_name":"Leonidas Tsekouras","orcid":null},"institutions":[{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":null,"type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]},{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Leonidas Tsekouras","raw_affiliation_strings":["Institute of Informatics and Telecommunications, N.C.S.R. Demokritos, Greece"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, N.C.S.R. Demokritos, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056484904","display_name":"Iraklis Varlamis","orcid":"https://orcid.org/0000-0002-0876-8167"},"institutions":[{"id":"https://openalex.org/I32762134","display_name":"Harokopio University of Athens","ror":"https://ror.org/02k5gp281","country_code":"GR","type":"education","lineage":["https://openalex.org/I32762134"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Iraklis Varlamis","raw_affiliation_strings":["Department of Informatics and Telematics, Harokopio University of Athens, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics and Telematics, Harokopio University of Athens, Greece","institution_ids":["https://openalex.org/I32762134"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077385373"],"corresponding_institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"],"apc_list":null,"apc_paid":null,"fwci":0.847,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77497361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"1","last_page":"4"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9796000123023987,"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/T10028","display_name":"Topic Modeling","score":0.9641000032424927,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8728223443031311},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8109638690948486},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5871568918228149},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5384561419487},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.5256631970405579},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5099211931228638},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5077062845230103},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4787696897983551},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.44981223344802856},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.43583986163139343},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.4355362057685852},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4264412522315979},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4189847707748413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31963860988616943},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18353188037872314},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17099440097808838}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8728223443031311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109638690948486},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5871568918228149},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5384561419487},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.5256631970405579},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5099211931228638},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5077062845230103},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4787696897983551},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.44981223344802856},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.43583986163139343},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4355362057685852},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4264412522315979},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4189847707748413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31963860988616943},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18353188037872314},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17099440097808838},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3209280.3229109","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209280.3229109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W33249699","https://openalex.org/W1549099081","https://openalex.org/W1551709509","https://openalex.org/W1577929347","https://openalex.org/W1602412127","https://openalex.org/W1999315683","https://openalex.org/W2148524305","https://openalex.org/W2399361902","https://openalex.org/W3016724004"],"related_works":["https://openalex.org/W2559422900","https://openalex.org/W2181939267","https://openalex.org/W2491448268","https://openalex.org/W3144143113","https://openalex.org/W2117838073","https://openalex.org/W3174322327","https://openalex.org/W4306940721","https://openalex.org/W2183916789","https://openalex.org/W2892323093","https://openalex.org/W2354012042"],"abstract_inverted_index":{"This":[0],"work":[1],"examines":[2],"document":[3,21,105],"clustering":[4,26,68,76,83,106],"as":[5],"a":[6],"record":[7,42,92],"linkage":[8,43,93],"problem,":[9],"focusing":[10],"on":[11],"named-entities":[12],"and":[13,19,24,52,54,78,95],"frequent":[14],"terms,":[15],"using":[16],"several":[17],"vector":[18],"graph-based":[20],"representation":[22],"methods":[23],"k-means":[25],"with":[27,66],"different":[28],"similarity":[29],"measures.":[30],"The":[31,61,71],"JedAI":[32,97],"Record":[33],"Linkage":[34],"toolkit":[35,98],"is":[36],"employed":[37],"for":[38,58,99,103],"most":[39],"of":[40,89],"the":[41,55,82,87,91,96,101],"pipeline":[44],"tasks":[45],"(i.e.":[46],"preprocessing,":[47],"scalable":[48],"feature":[49],"representation,":[50],"blocking":[51],"clustering)":[53],"OpenCalais":[56],"platform":[57],"entity":[59],"extraction.":[60],"resulting":[62],"clusters":[63],"are":[64],"evaluated":[65],"multiple":[67],"quality":[69],"metrics.":[70],"experiments":[72],"show":[73],"very":[74],"good":[75],"results":[77],"significant":[79],"speedups":[80],"in":[81],"process,":[84],"which":[85],"indicates":[86],"suitability":[88],"both":[90],"formulation":[94],"improving":[100],"scalability":[102],"large-scale":[104],"tasks.":[107]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}