{"id":"https://openalex.org/W2385630000","doi":"https://doi.org/10.5220/0005836701820187","title":"Identification of Organization Name Variants in Large Databases using Rule-based Scoring and Clustering - With a Case Study on the Web of Science Database","display_name":"Identification of Organization Name Variants in Large Databases using Rule-based Scoring and Clustering - With a Case Study on the Web of Science Database","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2385630000","doi":"https://doi.org/10.5220/0005836701820187","mag":"2385630000"},"language":"en","primary_location":{"id":"doi:10.5220/0005836701820187","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005836701820187","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0005836701820187","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076586531","display_name":"Emiel Caron","orcid":null},"institutions":[{"id":"https://openalex.org/I913958620","display_name":"Erasmus University Rotterdam","ror":"https://ror.org/057w15z03","country_code":"NL","type":"education","lineage":["https://openalex.org/I913958620"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Emiel Caron","raw_affiliation_strings":["Erasmus University Rotterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Erasmus University Rotterdam, Netherlands","institution_ids":["https://openalex.org/I913958620"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009397665","display_name":"Hennie Daniels","orcid":null},"institutions":[{"id":"https://openalex.org/I913958620","display_name":"Erasmus University Rotterdam","ror":"https://ror.org/057w15z03","country_code":"NL","type":"education","lineage":["https://openalex.org/I913958620"]},{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hennie Daniels","raw_affiliation_strings":["Tilburg University and Erasmus University Rotterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Tilburg University and Erasmus University Rotterdam, Netherlands","institution_ids":["https://openalex.org/I193700539","https://openalex.org/I913958620"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076586531"],"corresponding_institution_ids":["https://openalex.org/I913958620"],"apc_list":null,"apc_paid":null,"fwci":0.7465,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77246192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9972000122070312,"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":0.9972000122070312,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9933000206947327,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9847000241279602,"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/computer-science","display_name":"Computer science","score":0.7518999576568604},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.716052234172821},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7105341553688049},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5941944122314453},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5342764854431152},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5210999250411987},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5125460624694824},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48828887939453125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1380060911178589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7518999576568604},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.716052234172821},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7105341553688049},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5941944122314453},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5342764854431152},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5210999250411987},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5125460624694824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48828887939453125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1380060911178589},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.5220/0005836701820187","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005836701820187","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.eur.nl:openaire_cris_publications/06a94668-1b45-45c2-9f5c-867b712d6cca","is_oa":false,"landing_page_url":"https://pure.eur.nl/en/publications/06a94668-1b45-45c2-9f5c-867b712d6cca","pdf_url":null,"source":{"id":"https://openalex.org/S4306401266","display_name":"EUR Research Repository (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Caron, E & Daniels, H 2016, Identification of Organization Name Variants in Large Databases using Rule-based Scoring and Clustering - With a Case Study on the Web of Science Database. in 18th International Conference on Enterprise Information Systems (ICEIS 2016). vol. 1, SciTePress, Rome, Italy, pp. 182-187. https://doi.org/10.5220/0005836701820187","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:tilburguniversity.edu:openaire_cris_publications/f8cabd8c-8b93-425f-9afe-1033c701a6e3","is_oa":false,"landing_page_url":"https://research.tilburguniversity.edu/en/publications/f8cabd8c-8b93-425f-9afe-1033c701a6e3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401490","display_name":"Research portal (Tilburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193700539","host_organization_name":"Tilburg University","host_organization_lineage":["https://openalex.org/I193700539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Caron, E A M & Daniels, H 2016, Identification of organization name variants in large databases using rule-based scoring and clustering : With a case study on the Web of Science database. in 18th International Conference on Enterprise Information Systems (ICEIS 2016). vol. 1, SciTePress, Rome, Italy, pp. 182-187, 18th International Conference on Enterprise Information Systems , Rome, Italy, 25/03/15.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:eur:oai:repub.eur.nl:96337","is_oa":true,"landing_page_url":"http://hdl.handle.net/1765/96337","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"pmh:oai:repub.eur.nl:96337","is_oa":true,"landing_page_url":"http://repub.eur.nl/pub/96337","pdf_url":null,"source":{"id":"https://openalex.org/S4377196287","display_name":"RePub (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"doi:10.5220/0005836701820187","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005836701820187","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W1585267848","https://openalex.org/W1980818403","https://openalex.org/W2007172042","https://openalex.org/W2102462631","https://openalex.org/W2131193521","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2158836806","https://openalex.org/W2393816671","https://openalex.org/W2083665254","https://openalex.org/W2942177010"],"abstract_inverted_index":{"This":[0],"research":[1,75],"describes":[2],"a":[3,60,65,107],"general":[4],"method":[5,35,56,69,116],"to":[6],"automatically":[7],"clean":[8],"organizational":[9],"and":[10,52,64,88,103,131],"business":[11,24],"names":[12],"variants
\\nwithin":[13],"large":[14],"databases,":[15,19,21],"such":[16],"as:":[17],"patent":[18],"bibliographic":[20],"databases":[22],"in":[23,77],"information
\\nsystems,":[25],"or":[26],"any":[27],"other":[28],"database":[29,82],"containing":[30],"organisational":[31],"name":[32,37],"variants.":[33],"The":[34,55,68,92,111],"clusters":[36],"variants
\\nof":[38],"organizations":[39],"based":[40],"on":[41,71,106,127],"similarities":[42],"of":[43,74,80,86,94],"their":[44],"associated":[45],"meta-data,":[46],"like,":[47],"for":[48,83,134],"example,":[49],"postal":[50],"code":[51],"email
\\ndomain":[53],"data.":[54],"is":[57,119],"divided":[58],"into":[59],"rule-based":[61],"scoring":[62],"system":[63],"clustering":[66,96],"system.":[67],"is
\\ntested":[70],"the":[72,78,84,95],"cleaning":[73],"organisations":[76],"Web":[79],"Science":[81],"purpose":[85],"bibliometric
\\nanalysis":[87],"scientific":[89],"performance":[90],"evaluation.":[91],"results":[93],"are":[97],"evaluated":[98],"with":[99,126],"metrics":[100],"such
\\nas":[101],"precision":[102,123,130],"recall":[104,133],"analysis":[105],"verified":[108],"data":[109],"set.":[110],"evaluation":[112],"shows":[113],"that":[114],"our":[115],"performs":[117],"well
\\nand":[118],"conservative,":[120],"it":[121],"values":[122],"over":[124],"recall,":[125],"average":[128],"95%":[129],"80%":[132],"clusters.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}