{"id":"https://openalex.org/W2039001182","doi":"https://doi.org/10.1109/icdmw.2006.2","title":"A Comparison of Personal Name Matching: Techniques and Practical Issues","display_name":"A Comparison of Personal Name Matching: Techniques and Practical Issues","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2039001182","doi":"https://doi.org/10.1109/icdmw.2006.2","mag":"2039001182"},"language":"en","primary_location":{"id":"doi:10.1109/icdmw.2006.2","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw.2006.2","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sixth IEEE International Conference on Data Mining - Workshops (ICDMW'06)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://cs.anu.edu.au/techreports/2006/TR-CS-06-02.html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022945960","display_name":"Peter Christen","orcid":"https://orcid.org/0000-0003-3435-2015"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Peter Christen","raw_affiliation_strings":["Department of Computer Science, Australian National University, Canberra, Australia","Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022945960"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":15.1629,"has_fulltext":false,"cited_by_count":333,"citation_normalized_percentile":{"value":0.99209546,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"290","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"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":0.9990000128746033,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9940999746322632,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9879000186920166,"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":0.7806892395019531},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.767973780632019},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.7543956637382507},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5942233800888062},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5084477663040161},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.48301658034324646},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.475632905960083},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44268378615379333},{"id":"https://openalex.org/keywords/personally-identifiable-information","display_name":"Personally identifiable information","score":0.4281066060066223},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.4060696065425873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26014912128448486},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22270986437797546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10958826541900635},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06635016202926636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806892395019531},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.767973780632019},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7543956637382507},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5942233800888062},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5084477663040161},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.48301658034324646},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.475632905960083},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44268378615379333},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.4281066060066223},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.4060696065425873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26014912128448486},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22270986437797546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10958826541900635},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06635016202926636},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icdmw.2006.2","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw.2006.2","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sixth IEEE International Conference on Data Mining - Workshops (ICDMW'06)","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/44521","is_oa":true,"landing_page_url":"http://cs.anu.edu.au/techreports/2006/TR-CS-06-02.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2006 International Conference Conference on Data Mining","raw_type":"Working/Technical Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.3456","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.3456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://datamining.anu.edu.au/publications/2006/tr-cs-06-02.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.8208","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.8208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://datamining.anu.edu.au/publications/2006/mcd2006.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/44521","is_oa":true,"landing_page_url":"http://cs.anu.edu.au/techreports/2006/TR-CS-06-02.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2006 International Conference Conference on Data Mining","raw_type":"Working/Technical Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W19758219","https://openalex.org/W48945287","https://openalex.org/W1484435918","https://openalex.org/W1489107989","https://openalex.org/W1520449809","https://openalex.org/W1597164057","https://openalex.org/W1646278814","https://openalex.org/W1815899388","https://openalex.org/W1983053172","https://openalex.org/W2001496424","https://openalex.org/W2004918398","https://openalex.org/W2010392031","https://openalex.org/W2010595692","https://openalex.org/W2012739991","https://openalex.org/W2034163998","https://openalex.org/W2039001182","https://openalex.org/W2050050080","https://openalex.org/W2052938165","https://openalex.org/W2066792529","https://openalex.org/W2087447526","https://openalex.org/W2093514089","https://openalex.org/W2108263626","https://openalex.org/W2120988656","https://openalex.org/W2128859735","https://openalex.org/W2142023452","https://openalex.org/W2143683307","https://openalex.org/W2150698190","https://openalex.org/W2158919277","https://openalex.org/W2161936973","https://openalex.org/W2164456230","https://openalex.org/W2223011434","https://openalex.org/W2916037451","https://openalex.org/W2999282340","https://openalex.org/W4285719527","https://openalex.org/W6631166905","https://openalex.org/W6636771404","https://openalex.org/W6689036111"],"related_works":["https://openalex.org/W3145288231","https://openalex.org/W2371263218","https://openalex.org/W2092552144","https://openalex.org/W2354196777","https://openalex.org/W2965473297","https://openalex.org/W2108265183","https://openalex.org/W2257399947","https://openalex.org/W2248278495","https://openalex.org/W2386746909","https://openalex.org/W2387316851"],"abstract_inverted_index":{"Finding":[0],"and":[1,17,26,31,40,74,80],"matching":[2,38,42,98,115],"personal":[3,54,72],"names":[4,34,55,73],"is":[5,111],"at":[6],"the":[7,69],"core":[8],"of":[9,13,71,78,88],"an":[10],"increasing":[11],"number":[12,87],"applications:":[14],"from":[15],"text":[16],"Web":[18],"mining,":[19],"search":[20],"engines,":[21],"to":[22,45,50,61],"information":[23],"extraction,":[24],"deduplication":[25],"data":[27,106],"linkage":[28],"systems.":[29],"Variations":[30],"errors":[32],"in":[33],"make":[35],"exact":[36],"string":[37],"problematic,":[39],"approximate":[41],"techniques":[43],"have":[44,56],"be":[46,62],"applied.":[47],"When":[48],"compared":[49],"general":[51],"text,":[52],"however,":[53],"different":[57],"characteristics":[58,70],"that":[59,109],"need":[60],"considered.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"discuss":[68],"present":[75],"potential":[76],"sources":[77],"variations":[79],"errors.":[81],"We":[82],"then":[83],"overview":[84],"a":[85],"comprehensive":[86],"commonly":[89],"used,":[90],"as":[91,93],"well":[92],"some":[94],"recently":[95],"developed":[96],"name":[97,105],"techniques.":[99],"Experimental":[100],"comparisons":[101],"using":[102],"four":[103],"large":[104],"sets":[107],"indicate":[108],"there":[110],"no":[112],"clear":[113],"best":[114],"technique":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":28},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":22},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":22}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}