{"id":"https://openalex.org/W26430610","doi":null,"title":"A Comparison and Generalization of Blocking and Windowing Algorithms for Duplicate Detection","display_name":"A Comparison and Generalization of Blocking and Windowing Algorithms for Duplicate Detection","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W26430610","mag":"26430610"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.572.2533","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.572.2533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpi.uni-potsdam.de/fileadmin/hpi/FG_Naumann/publications/2009/QDB09_crc.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5076248342","display_name":"Uwe Draisbach","orcid":"https://orcid.org/0000-0001-8160-1374","observed_orcids":["https://orcid.org/0000-0001-8160-1374"]},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"FernUniversit\u00e4t in Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Uwe Draisbach","raw_affiliation_strings":["University of Hagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hagen","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389","observed_orcids":["https://orcid.org/0000-0002-4483-1389"]},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["UNIVERSITY OF POTSDAM"],"raw_orcid":"https://orcid.org/0000-0002-4483-1389","affiliations":[{"raw_affiliation_string":"UNIVERSITY OF POTSDAM","institution_ids":["https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1648,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.90588487,"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":null,"last_page":null},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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/duplicate-detection","display_name":"duplicate detection","score":0.8190000057220459},{"id":"https://openalex.org/keywords/record-deduplication","display_name":"record deduplication","score":0.847000002861023},{"id":"https://openalex.org/keywords/blocking","display_name":"blocking","score":0.628000020980835},{"id":"https://openalex.org/keywords/windowing","display_name":"windowing","score":0.9039999842643738},{"id":"https://openalex.org/keywords/data-linkage","display_name":"data linkage","score":0.7120000123977661},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"data deduplication","score":0.49000000953674316}],"concepts":[{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.7792264223098755},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7322729825973511},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.6884211301803589},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6454892158508301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5737453699111938},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5002865791320801},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.45598840713500977},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34640267491340637},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.16541779041290283},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.572.2533","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.572.2533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpi.uni-potsdam.de/fileadmin/hpi/FG_Naumann/publications/2009/QDB09_crc.pdf","raw_type":"text"},{"id":"mag:26430610","doi":null,"is_oa":false,"landing_page_url":"http://qdb09.irisa.fr/participants/program/Uwe-Draisbach-QDB09.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Sustainable cities and communities","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/11"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3474192450","display_name":null,"funder_award_id":"P20MH-077967","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"}],"funders":[{"id":"https://openalex.org/F4320337346","display_name":"National Institute of Mental Health","ror":"https://ror.org/04xeg9z08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1559390933","https://openalex.org/W1569123402","https://openalex.org/W1612155886","https://openalex.org/W1845040079","https://openalex.org/W1979954747","https://openalex.org/W2024770506","https://openalex.org/W2111116800","https://openalex.org/W2138745909","https://openalex.org/W2166988329","https://openalex.org/W2171574281","https://openalex.org/W3123518987","https://openalex.org/W4214953342","https://openalex.org/W4297820056"],"related_works":["https://openalex.org/W2092336114","https://openalex.org/W2077044633","https://openalex.org/W4236769874","https://openalex.org/W1566649662","https://openalex.org/W3031902962","https://openalex.org/W155407436","https://openalex.org/W2425979479","https://openalex.org/W2592655139","https://openalex.org/W2743425408","https://openalex.org/W4210331307"],"abstract_inverted_index":{"Duplicate":[0],"detection":[1],"is":[2,40],"the":[3,12,44,54,91,95,113,121],"problem":[4],"of":[5,8,32,35,109],"identifying":[6],"pairs":[7,34,59,118],"records":[9,45,51,76],"that":[10],"represent":[11],"same":[13,55],"real":[14],"world":[15],"object,":[16],"and":[17,104,116],"could":[18],"thus":[19],"be":[20,64],"merged":[21],"into":[22,46,77],"a":[23,28,37,107],"single":[24],"record.":[25],"To":[26],"avoid":[27],"prohibitively":[29],"expensive":[30],"comparison":[31],"all":[33,58],"records,":[36],"common":[38],"tech-nique":[39],"to":[41,98],"carefully":[42],"partition":[43,62,75],"smaller":[47],"sub-sets.":[48],"If":[49],"duplicate":[50],"appear":[52],"in":[53,89],"partition,":[56],"only":[57,119],"within":[60,120],"each":[61],"must":[63],"compared.":[65],"Two":[66],"competing":[67],"approaches":[68],"are":[69],"often":[70],"cited:":[71],"Blocking":[72],"methods":[73],"strictly":[74],"disjoint":[78],"subsets,":[79],"for":[80],"instance":[81],"using":[82],"zip-codes":[83],"as":[84,102],"partitioning":[85],"key.":[86],"Windowing":[87],"methods,":[88],"particular":[90],"Sorted-Neighborhood":[92],"method,":[93],"sort":[94],"data":[96,115],"according":[97],"some":[99],"key,":[100],"such":[101],"zip-code,":[103],"then":[105],"slide":[106],"window":[108],"fixed":[110],"size":[111],"across":[112],"sorted":[114],"compare":[117],"window.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":9},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}
