{"id":"https://openalex.org/W1996848289","doi":"https://doi.org/10.1145/2661829.2661885","title":"Estimating the Number and Sizes of Fuzzy-Duplicate Clusters","display_name":"Estimating the Number and Sizes of Fuzzy-Duplicate Clusters","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W1996848289","doi":"https://doi.org/10.1145/2661829.2661885","mag":"1996848289"},"language":"en","primary_location":{"id":"doi:10.1145/2661829.2661885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2661885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","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/A5015327612","display_name":"Arvid Heise","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Arvid Heise","raw_affiliation_strings":["Hasso-Plattner Institute, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso-Plattner Institute, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024434748","display_name":"Gjergji Kasneci","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gjergji Kasneci","raw_affiliation_strings":["Hasso-Plattner Institute, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso-Plattner Institute, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Hasso-Plattner Institute, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso-Plattner Institute, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015327612"],"corresponding_institution_ids":["https://openalex.org/I143288331"],"apc_list":null,"apc_paid":null,"fwci":2.8407,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90464409,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"959","last_page":"968"},"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9847999811172485,"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/computer-science","display_name":"Computer science","score":0.72169029712677},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6348610520362854},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4976973831653595},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.47561269998550415},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4218413829803467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3007012605667114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72169029712677},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6348610520362854},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4976973831653595},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.47561269998550415},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4218413829803467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3007012605667114},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2661829.2661885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2661885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W192724328","https://openalex.org/W1587364696","https://openalex.org/W1965996575","https://openalex.org/W1995541812","https://openalex.org/W2000482994","https://openalex.org/W2014478203","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2067566391","https://openalex.org/W2111116800","https://openalex.org/W2116079723","https://openalex.org/W2143124645","https://openalex.org/W2163794926","https://openalex.org/W2318063279","https://openalex.org/W6607776381","https://openalex.org/W6700160807"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W4376623224","https://openalex.org/W2951359407","https://openalex.org/W2038693912","https://openalex.org/W3136979370","https://openalex.org/W2058170566"],"abstract_inverted_index":{"Duplicates":[0],"in":[1,34],"a":[2,14,38],"dataset":[3],"are":[4],"multiple":[5,49],"representations":[6],"of":[7,24,30,61],"the":[8,22,26,54,59],"same":[9],"real-world":[10],"entity":[11],"and":[12,28,36],"constitute":[13],"major":[15],"data":[16],"quality":[17],"problem.":[18,44],"This":[19],"paper":[20],"investigates":[21],"problem":[23],"estimating":[25],"number":[27,60],"sizes":[29],"duplicate":[31,62],"record":[32],"clusters":[33],"advance":[35],"describes":[37],"sampling-based":[39],"method":[40,56],"for":[41],"solving":[42],"this":[43],"In":[45],"extensive":[46],"experiments,":[47],"on":[48],"datasets,":[50],"we":[51],"show":[52],"that":[53],"proposed":[55],"reliably":[57],"estimates":[58],"clusters,":[63],"while":[64],"being":[65],"highly":[66],"efficient.":[67]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}