{"id":"https://openalex.org/W509898","doi":null,"title":"A Comparison of String Metrics for Matching Names and Records","display_name":"A Comparison of String Metrics for Matching Names and Records","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W509898","mag":"509898"},"language":"en","primary_location":{"id":"mag:509898","doi":null,"is_oa":false,"landing_page_url":"https://www.cs.cmu.edu/afs/cs/Web/People/wcohen/postscript/kdd-2003-match-ws.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},"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/A5020819503","display_name":"W. W. Cohen and P. Ravikumar and S. Fienberg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"W. W. Cohen and P. Ravikumar and S. Fienberg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5020819503"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.1131,"has_fulltext":false,"cited_by_count":474,"citation_normalized_percentile":{"value":0.99390244,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"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/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/name-matching","display_name":"name matching","score":0.8650000095367432},{"id":"https://openalex.org/keywords/record-matching","display_name":"record matching","score":0.8169999718666077},{"id":"https://openalex.org/keywords/edit-distance","display_name":"edit distance","score":0.9869999885559082},{"id":"https://openalex.org/keywords/java-toolkit","display_name":"Java toolkit","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745922327041626},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6732359528541565},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6696182489395142},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.6245312690734863},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5652415752410889},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5505334734916687},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.5485615730285645},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4637264609336853},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4501941502094269},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.41549327969551086},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4089054465293884},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.35815683007240295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2677980661392212},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15119770169258118},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08506089448928833},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":"mag:509898","doi":null,"is_oa":false,"landing_page_url":"https://www.cs.cmu.edu/afs/cs/Web/People/wcohen/postscript/kdd-2003-match-ws.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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W1540550673","https://openalex.org/W1569123402","https://openalex.org/W1593239840","https://openalex.org/W1646278814","https://openalex.org/W1898496839","https://openalex.org/W1975723136","https://openalex.org/W2009570821","https://openalex.org/W2024770506","https://openalex.org/W2034190452","https://openalex.org/W2036216970","https://openalex.org/W2052581258","https://openalex.org/W2073471108","https://openalex.org/W2102443632","https://openalex.org/W2106895292","https://openalex.org/W2128600649","https://openalex.org/W2150698190","https://openalex.org/W2153977007","https://openalex.org/W2154785834","https://openalex.org/W2159481891","https://openalex.org/W2170902582"],"related_works":["https://openalex.org/W1646278814","https://openalex.org/W2744273759","https://openalex.org/W2249277830","https://openalex.org/W1523728576","https://openalex.org/W7099295012","https://openalex.org/W2120988656","https://openalex.org/W7098740796","https://openalex.org/W2278443863","https://openalex.org/W2012366999","https://openalex.org/W2550962243"],"abstract_inverted_index":{"We":[0,13,54,68],"describe":[1,56],"an":[2,57],"open-source":[3],"Java":[4],"toolkit":[5,61],"of":[6,26],"methods":[7],"for":[8,78,85],"matching":[9,27],"names":[10],"and":[11,51,81],"records.":[12],"summarize":[14],"results":[15,84],"obtained":[16],"from":[17],"using":[18],"various":[19],"string":[20,46,92],"distance":[21,33,49],"metrics":[22,31],"on":[23],"the":[24,60],"task":[25],"entity":[28],"names.":[29],"These":[30],"include":[32],"functions":[34],"proposed":[35],"by":[36],"several":[37],"different":[38],"communities,":[39],"such":[40],"as":[41],"edit-distance":[42],"metrics,":[43,50],"fast":[44],"heuristic":[45],"comparators,":[47],"token-based":[48],"hybrid":[52],"methods.":[53],"then":[55],"extension":[58],"to":[59,65],"which":[62],"allows":[63],"records":[64],"be":[66],"compared.":[67],"discuss":[69],"some":[70,86],"issues":[71],"involved":[72],"in":[73],"performing":[74],"a":[75],"similar":[76],"comparision":[77],"record-matching":[79,88],"techniques,":[80],"finally":[82],"present":[83],"baseline":[87],"algorithms":[89],"that":[90],"aggregate":[91],"comparisons":[93],"between":[94],"fields.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":40},{"year":2018,"cited_by_count":50},{"year":2017,"cited_by_count":56},{"year":2016,"cited_by_count":55},{"year":2015,"cited_by_count":40},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":15}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2016-06-24T00:00:00"}
