{"id":"https://openalex.org/W1491923463","doi":"https://doi.org/10.1007/978-3-642-15105-7_25","title":"An Efficient Duplicate Record Detection Using q-Grams Array Inverted Index","display_name":"An Efficient Duplicate Record Detection Using q-Grams Array Inverted Index","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1491923463","doi":"https://doi.org/10.1007/978-3-642-15105-7_25","mag":"1491923463"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-15105-7_25","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-15105-7_25","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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 Computer Science","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/A5000272110","display_name":"Alfredo Ferro","orcid":"https://orcid.org/0000-0002-9431-5788"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alfredo Ferro","raw_affiliation_strings":["Dept. of Mathematics and Computer Sciences, University of Catania, Italy"],"affiliations":[{"raw_affiliation_string":"Dept. of Mathematics and Computer Sciences, University of Catania, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002057785","display_name":"Rosalba Giugno","orcid":"https://orcid.org/0000-0001-9843-7638"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rosalba Giugno","raw_affiliation_strings":["Dept. of Mathematics and Computer Sciences, University of Catania, Italy"],"affiliations":[{"raw_affiliation_string":"Dept. of Mathematics and Computer Sciences, University of Catania, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036980875","display_name":"Piera Laura Puglisi","orcid":null},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Piera Laura Puglisi","raw_affiliation_strings":["Dept. of Mathematics and Computer Sciences, University of Catania, Italy"],"affiliations":[{"raw_affiliation_string":"Dept. of Mathematics and Computer Sciences, University of Catania, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057481978","display_name":"Alfredo Pulvirenti","orcid":"https://orcid.org/0000-0002-9764-0295"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alfredo Pulvirenti","raw_affiliation_strings":["Dept. of Mathematics and Computer Sciences, University of Catania, Italy"],"affiliations":[{"raw_affiliation_string":"Dept. of Mathematics and Computer Sciences, University of Catania, Italy","institution_ids":["https://openalex.org/I39063666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000272110"],"corresponding_institution_ids":["https://openalex.org/I39063666"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.6214,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83618818,"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":"309","last_page":"323"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.84843510389328},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.705869197845459},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7030873894691467},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6722289323806763},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6051067113876343},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.5884857177734375},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5477697849273682},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5383428335189819},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4333685040473938},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42643940448760986},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3830680251121521},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3270391821861267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2928863763809204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84843510389328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.705869197845459},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7030873894691467},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6722289323806763},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6051067113876343},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.5884857177734375},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5477697849273682},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5383428335189819},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4333685040473938},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42643940448760986},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3830680251121521},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3270391821861267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2928863763809204},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-15105-7_25","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-15105-7_25","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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 Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1893018","https://openalex.org/W46452414","https://openalex.org/W1540876239","https://openalex.org/W1569123402","https://openalex.org/W1887000090","https://openalex.org/W1920916604","https://openalex.org/W2023358833","https://openalex.org/W2024770506","https://openalex.org/W2034190452","https://openalex.org/W2036216970","https://openalex.org/W2036289425","https://openalex.org/W2043481183","https://openalex.org/W2087064593","https://openalex.org/W2105423800","https://openalex.org/W2108991785","https://openalex.org/W2109464129","https://openalex.org/W2128661986","https://openalex.org/W2154785834","https://openalex.org/W2158874082","https://openalex.org/W2161936973","https://openalex.org/W2171574281","https://openalex.org/W2243410218","https://openalex.org/W2494026964","https://openalex.org/W2996186646","https://openalex.org/W3146259567"],"related_works":["https://openalex.org/W2124379162","https://openalex.org/W2058987221","https://openalex.org/W2145657320","https://openalex.org/W2102493899","https://openalex.org/W2388346754","https://openalex.org/W4282568653","https://openalex.org/W2187610212","https://openalex.org/W2123678380","https://openalex.org/W180545237","https://openalex.org/W1837234277"],"abstract_inverted_index":null,"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
