{"id":"https://openalex.org/W4406460589","doi":"https://doi.org/10.1109/bigdata62323.2024.10825868","title":"Comparing Inexact String Matching Methods for Large Scale Entity Matching","display_name":"Comparing Inexact String Matching Methods for Large Scale Entity Matching","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406460589","doi":"https://doi.org/10.1109/bigdata62323.2024.10825868"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5115940173","display_name":"Davis Spradling","orcid":null},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Davis Spradling","raw_affiliation_strings":["University of North Carolina at Charlotte,Computing and Informatics,Charlotte,NC"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Computing and Informatics,Charlotte,NC","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028427671","display_name":"\u00c9rik Saule","orcid":"https://orcid.org/0000-0003-1634-9234"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Saule","raw_affiliation_strings":["University of North Carolina at Charlotte,Computing and Informatics,Charlotte,NC"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Computing and Informatics,Charlotte,NC","institution_ids":["https://openalex.org/I102149020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5115940173"],"corresponding_institution_ids":["https://openalex.org/I102149020"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32125815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7422","last_page":"7427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9947999715805054,"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":0.9947999715805054,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.7088426351547241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6781944036483765},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5660051703453064},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5645027160644531},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5061437487602234},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3667990267276764},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.322643518447876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2647274136543274},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22077757120132446},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11756053566932678},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09144631028175354}],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7088426351547241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6781944036483765},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5660051703453064},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5645027160644531},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5061437487602234},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3667990267276764},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.322643518447876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2647274136543274},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22077757120132446},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11756053566932678},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09144631028175354},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W1990866149","https://openalex.org/W6636915900"],"related_works":["https://openalex.org/W3145288231","https://openalex.org/W2371263218","https://openalex.org/W4398785990","https://openalex.org/W2092552144","https://openalex.org/W2943461603","https://openalex.org/W2354196777","https://openalex.org/W2257399947","https://openalex.org/W2965473297","https://openalex.org/W2386746909","https://openalex.org/W2108265183"],"abstract_inverted_index":{"the":[0,6,17,79,99],"Advisor":[1,80],"was":[2],"originally":[3],"built":[4],"with":[5,57,108],"purpose":[7],"of":[8],"helping":[9],"users":[10],"build":[11],"a":[12,49,70],"strong":[13],"bibliography":[14],"by":[15],"extending":[16],"document":[18],"set":[19],"obtained":[20],"at":[21],"first-level":[22],"search.":[23],"To":[24],"do":[25],"this":[26,34,67,74],"however,":[27],"diverse":[28],"datasets":[29],"containing":[30],"critical":[31],"metadata":[32,87],"for":[33,48],"project":[35,68,97],"to":[36,81],"work":[37],"must":[38],"be":[39,82],"matched.":[40],"Thus,":[41,66],"inexact":[42,51,109],"string":[43,52,110],"matching":[44,53,111],"is":[45,103],"needed":[46],"but":[47,88],"long-time":[50],"has":[54,77],"had":[55],"issues":[56],"both":[58],"accuracy":[59],"and":[60,117],"runtime":[61],"on":[62],"large":[63],"scale":[64],"data.":[65],"utilizes":[69],"two-phase":[71,75,100],"method.":[72],"Using":[73],"method":[76,101],"allowed":[78],"revived":[83],"through":[84],"gaining":[85],"important":[86],"how":[89],"does":[90],"it":[91],"compare":[92],"against":[93,105],"other":[94],"applications?":[95],"This":[96],"compares":[98],"that":[102],"proposed":[104],"popular":[106],"applications":[107],"capabilities":[112],"such":[113],"as":[114],"PostgreSQL,":[115],"Elasticsearch,":[116],"MongoDB.":[118]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}