{"id":"https://openalex.org/W1965392781","doi":"https://doi.org/10.1109/mis.2004.1274908","title":"Cleaning the spurious links in data","display_name":"Cleaning the spurious links in data","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W1965392781","doi":"https://doi.org/10.1109/mis.2004.1274908","mag":"1965392781"},"language":"en","primary_location":{"id":"doi:10.1109/mis.2004.1274908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mis.2004.1274908","pdf_url":null,"source":{"id":"https://openalex.org/S114241109","display_name":"IEEE Intelligent Systems","issn_l":"1541-1672","issn":["1541-1672","1941-1294"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Intelligent Systems","raw_type":"journal-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/A5019988958","display_name":"Mong Li Lee","orcid":"https://orcid.org/0000-0002-9636-388X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mong Li Lee","raw_affiliation_strings":["National University of Singapore, Singapore","Nat. Univ. of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051209739","display_name":"Wynne Hsu","orcid":"https://orcid.org/0000-0002-4142-8893"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"W. Hsu","raw_affiliation_strings":["National University of Singapore, Singapore","Nat. Univ. of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054166266","display_name":"Vijay Kothari","orcid":"https://orcid.org/0000-0003-1035-7217"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Vijay Kothari","raw_affiliation_strings":["National University of Singapore, Singapore","Nat. Univ. of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":{"value":2995,"currency":"USD","value_usd":2995},"apc_paid":null,"fwci":8.7682,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.9771962,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"19","issue":"2","first_page":"28","last_page":"33"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.991599977016449,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/spurious-relationship","display_name":"Spurious relationship","score":0.9743281602859497},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8166249990463257},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6972333788871765},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.677647590637207},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5573025345802307},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5402014851570129},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.509779155254364},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42502111196517944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13348007202148438},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11373788118362427}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.9743281602859497},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166249990463257},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6972333788871765},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.677647590637207},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5573025345802307},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5402014851570129},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.509779155254364},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42502111196517944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13348007202148438},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11373788118362427},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mis.2004.1274908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mis.2004.1274908","pdf_url":null,"source":{"id":"https://openalex.org/S114241109","display_name":"IEEE Intelligent Systems","issn_l":"1541-1672","issn":["1541-1672","1941-1294"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/39354","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/39354","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1528801041","https://openalex.org/W1569123402","https://openalex.org/W1610496399","https://openalex.org/W1898031563","https://openalex.org/W1999823970","https://openalex.org/W2024770506","https://openalex.org/W2106895292","https://openalex.org/W2129281431","https://openalex.org/W2151763080","https://openalex.org/W2154642793","https://openalex.org/W4250102289","https://openalex.org/W4253461361","https://openalex.org/W6633966005","https://openalex.org/W6636177537","https://openalex.org/W6639540558","https://openalex.org/W6676014748","https://openalex.org/W6682837551"],"related_works":["https://openalex.org/W2027108423","https://openalex.org/W2135768893","https://openalex.org/W1855666948","https://openalex.org/W2758561209","https://openalex.org/W176219849","https://openalex.org/W3021414116","https://openalex.org/W2094985717","https://openalex.org/W2594414941","https://openalex.org/W1548095260","https://openalex.org/W2781711915"],"abstract_inverted_index":{"Data":[0],"quality":[1,169],"problems":[2,19],"can":[3,153,164],"arise":[4],"from":[5,97],"abbreviations,":[6],"data":[7,25,28,42,75,82,96,124,162,168,178],"entry":[8],"mistakes,":[9],"duplicate":[10],"records,":[11],"missing":[12],"fields,":[13],"and":[14,32,71,93,180],"many":[15],"other":[16],"sources.":[17],"These":[18],"proliferate":[20],"when":[21],"you":[22],"integrate":[23],"multiple":[24,51,175],"sources":[26,99],"in":[27,73],"warehousing,":[29],"federated":[30],"databases,":[31],"global":[33],"information":[34,116,160],"systems.":[35],"A":[36],"newly":[37],"discovered":[38],"class":[39],"of":[40,63,136,171],"erroneous":[41],"is":[43,84],"spurious":[44,65,105,119,129,156,172],"links,":[45,106],"where":[46],"a":[47],"real-world":[48,146,181],"entity":[49],"has":[50],"links":[52,66,176],"that":[53,126,138,150],"might":[54],"not":[55],"be":[56],"properly":[57],"associated":[58],"with":[59,144],"it.":[60],"The":[61],"existence":[62],"such":[64],"often":[67],"leads":[68],"to":[69,117],"confusion":[70],"misrepresentation":[72],"the":[74,78,81,95,134,167],"records":[76,125,163],"representing":[77],"entity.":[79],"Although":[80],"set":[83,135],"well":[85],"known":[86],"for":[87],"its":[88],"high-quality":[89],"bibliographic":[90],"information,":[91],"collecting":[92],"maintaining":[94],"diverse":[98],"requires":[100],"enormous":[101],"effort.":[102],"Errors,":[103],"including":[104],"are":[107],"inevitable.":[108],"To":[109],"solve":[110,166],"this":[111],"problem,":[112],"we":[113,122],"use":[114],"context":[115,159],"identify":[118,123,155],"links.":[120,130,157],"First,":[121],"contain":[127],"potential":[128],"We":[131],"then":[132],"determine":[133],"attributes":[137],"constitute":[139],"each":[140],"record's":[141],"context.":[142],"Experiments":[143],"three":[145],"databases":[147],"have":[148],"demonstrated":[149],"our":[151],"approach":[152],"accurately":[154],"Comparing":[158],"between":[161,177],"help":[165],"problem":[170],"links-that":[173],"is,":[174],"entries":[179],"entities.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
