{"id":"https://openalex.org/W4310145190","doi":"https://doi.org/10.23919/fruct56874.2022.9953810","title":"Automated Rule-Based Data Cleaning Using NLP","display_name":"Automated Rule-Based Data Cleaning Using NLP","publication_year":2022,"publication_date":"2022-11-09","ids":{"openalex":"https://openalex.org/W4310145190","doi":"https://doi.org/10.23919/fruct56874.2022.9953810"},"language":"en","primary_location":{"id":"doi:10.23919/fruct56874.2022.9953810","is_oa":false,"landing_page_url":"https://doi.org/10.23919/fruct56874.2022.9953810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 32nd Conference of Open Innovations Association (FRUCT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doaj.org/article/84f2b064bad443b0baf3e7eb78adb8d0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041438914","display_name":"Konstantinos Mavrogiorgos","orcid":null},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Konstantinos Mavrogiorgos","raw_affiliation_strings":["University of Piraeus,Piraeus,Greece","University of Piraeus, Piraeus, Greece"],"affiliations":[{"raw_affiliation_string":"University of Piraeus,Piraeus,Greece","institution_ids":["https://openalex.org/I154757721"]},{"raw_affiliation_string":"University of Piraeus, Piraeus, Greece","institution_ids":["https://openalex.org/I154757721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025387207","display_name":"Argyro Mavrogiorgou","orcid":"https://orcid.org/0000-0002-1543-5627"},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Argyro Mavrogiorgou","raw_affiliation_strings":["University of Piraeus,Piraeus,Greece","University of Piraeus, Piraeus, Greece"],"affiliations":[{"raw_affiliation_string":"University of Piraeus,Piraeus,Greece","institution_ids":["https://openalex.org/I154757721"]},{"raw_affiliation_string":"University of Piraeus, Piraeus, Greece","institution_ids":["https://openalex.org/I154757721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007408273","display_name":"Athanasios Kiourtis","orcid":"https://orcid.org/0000-0002-1681-3626"},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Athanasios Kiourtis","raw_affiliation_strings":["University of Piraeus,Piraeus,Greece","University of Piraeus, Piraeus, Greece"],"affiliations":[{"raw_affiliation_string":"University of Piraeus,Piraeus,Greece","institution_ids":["https://openalex.org/I154757721"]},{"raw_affiliation_string":"University of Piraeus, Piraeus, Greece","institution_ids":["https://openalex.org/I154757721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064789418","display_name":"Nikolaos Zafeiropoulos","orcid":"https://orcid.org/0000-0002-8682-3774"},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikolaos Zafeiropoulos","raw_affiliation_strings":["University of Piraeus,Piraeus,Greece","University of Piraeus, Piraeus, Greece"],"affiliations":[{"raw_affiliation_string":"University of Piraeus,Piraeus,Greece","institution_ids":["https://openalex.org/I154757721"]},{"raw_affiliation_string":"University of Piraeus, Piraeus, Greece","institution_ids":["https://openalex.org/I154757721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034519985","display_name":"Spyridon Kleftakis","orcid":"https://orcid.org/0000-0002-6237-488X"},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Spyridon Kleftakis","raw_affiliation_strings":["University of Piraeus,Piraeus,Greece","University of Piraeus, Piraeus, Greece"],"affiliations":[{"raw_affiliation_string":"University of Piraeus,Piraeus,Greece","institution_ids":["https://openalex.org/I154757721"]},{"raw_affiliation_string":"University of Piraeus, Piraeus, Greece","institution_ids":["https://openalex.org/I154757721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069674161","display_name":"Dimosthenis Kyriazis","orcid":"https://orcid.org/0000-0001-7019-7214"},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimosthenis Kyriazis","raw_affiliation_strings":["University of Piraeus,Piraeus,Greece","University of Piraeus, Piraeus, Greece"],"affiliations":[{"raw_affiliation_string":"University of Piraeus,Piraeus,Greece","institution_ids":["https://openalex.org/I154757721"]},{"raw_affiliation_string":"University of Piraeus, Piraeus, Greece","institution_ids":["https://openalex.org/I154757721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5041438914"],"corresponding_institution_ids":["https://openalex.org/I154757721"],"apc_list":null,"apc_paid":null,"fwci":2.5367,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90070075,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"162","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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":0.9984999895095825,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9779000282287598,"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":0.8109644651412964},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6656241416931152},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6564918160438538},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6315521001815796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6229506731033325},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6072527170181274},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5429262518882751},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.457379549741745},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.44686195254325867},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3991072475910187},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09536170959472656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109644651412964},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6656241416931152},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6564918160438538},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6315521001815796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6229506731033325},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6072527170181274},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5429262518882751},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.457379549741745},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.44686195254325867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3991072475910187},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09536170959472656},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/fruct56874.2022.9953810","is_oa":false,"landing_page_url":"https://doi.org/10.23919/fruct56874.2022.9953810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 32nd Conference of Open Innovations Association (FRUCT)","raw_type":"proceedings-article"},{"id":"pmh:oai:doaj.org/article:84f2b064bad443b0baf3e7eb78adb8d0","is_oa":true,"landing_page_url":"https://doaj.org/article/84f2b064bad443b0baf3e7eb78adb8d0","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"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 XXth Conference of Open Innovations Association FRUCT, Vol 32, Iss 1, Pp 162-168 (2022)","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:doaj.org/article:84f2b064bad443b0baf3e7eb78adb8d0","is_oa":true,"landing_page_url":"https://doaj.org/article/84f2b064bad443b0baf3e7eb78adb8d0","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"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 XXth Conference of Open Innovations Association FRUCT, Vol 32, Iss 1, Pp 162-168 (2022)","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2437617937","https://openalex.org/W2886924127","https://openalex.org/W2940548648","https://openalex.org/W2990188683","https://openalex.org/W2996846626","https://openalex.org/W3001985945","https://openalex.org/W3002709092","https://openalex.org/W3012665221","https://openalex.org/W3019166713","https://openalex.org/W3035119815","https://openalex.org/W3088265803","https://openalex.org/W3094771832","https://openalex.org/W3107199975","https://openalex.org/W3115402873","https://openalex.org/W3115925934","https://openalex.org/W3142970463","https://openalex.org/W3162747839","https://openalex.org/W3164273471","https://openalex.org/W3165206559","https://openalex.org/W3168826388","https://openalex.org/W3173548770","https://openalex.org/W3174036215","https://openalex.org/W3181695441","https://openalex.org/W3196743233","https://openalex.org/W3212733079","https://openalex.org/W3214753659","https://openalex.org/W4221032058","https://openalex.org/W4223934638","https://openalex.org/W4235603165","https://openalex.org/W4296710937","https://openalex.org/W4308918863","https://openalex.org/W6753797868","https://openalex.org/W6770212877","https://openalex.org/W6786578692","https://openalex.org/W6796110051","https://openalex.org/W6798362999","https://openalex.org/W6804221474","https://openalex.org/W6809858327"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W2090827041","https://openalex.org/W2094012830","https://openalex.org/W187246281","https://openalex.org/W2079194830"],"abstract_inverted_index":{"Data":[0,6,87],"Cleaning":[1,88],"is":[2,9,25,41,138,153,178],"a":[3,119,139,144,161,173,204,236],"subfield":[4],"of":[5,18,26,58,63,70,76,133,163,189],"Mining":[7],"that":[8,67,141,155,165,213],"thriving":[10],"in":[11,85,105],"the":[12,16,31,38,74,77,89,109,192,231],"recent":[13],"years.":[14],"Ensuring":[15],"reliability":[17],"data,":[19],"either":[20],"when":[21],"generated":[22,50],"or":[23],"received,":[24],"vital":[27],"importance":[28],"to":[29,35,83,108,117,121,124,127,160,183,196,202,209,230],"provide":[30],"best":[32],"services":[33],"possible":[34],"users.":[36],"Accomplishing":[37],"aforementioned":[39],"task":[40],"easier":[42],"said":[43],"than":[44],"done,":[45],"since":[46],"data":[47,175,185,238],"are":[48,57,68,166],"complex,":[49],"at":[51],"an":[52],"extremely":[53,198],"high":[54],"rate":[55],"and":[56,65,92,113,129],"enormous":[59],"size.":[60],"A":[61],"variety":[62,162],"techniques":[64],"methods":[66],"part":[69],"other":[71,210],"subfields":[72,96],"from":[73],"domain":[75],"Computer":[78],"Science":[79],"have":[80],"been":[81],"invoked":[82],"assist":[84],"making":[86],"most":[90],"efficient":[91,207],"effective":[93,199],"possible.":[94],"Those":[95],"include,":[97],"among":[98,111],"others,":[99],"Natural":[100],"Language":[101],"Processing":[102],"(NLP),":[103],"which":[104,180],"essence":[106],"refers":[107],"interaction":[110],"computers":[112,123],"human":[114,134],"language,":[115],"seeking":[116],"find":[118],"way":[120],"program":[122],"be":[125,158,197,203],"able":[126],"process":[128],"analyze":[130],"huge":[131],"volumes":[132],"language":[135],"data.":[136],"NLP":[137,182,190],"concept":[140],"exists":[142],"for":[143],"long":[145],"time,":[146],"but,":[147],"as":[148],"time":[149],"goes":[150],"by,":[151],"it":[152,156],"proposed":[154],"can":[157],"applied":[159],"concepts":[164],"not":[167,194,215,226],"solely":[168],"NLP-related.":[169],"In":[170],"this":[171],"paper,":[172],"rule-based":[174],"cleaning":[176,239],"mechanism":[177,193,219],"proposed,":[179],"utilizes":[181],"ensure":[184],"reliability.":[186],"Making":[187],"use":[188],"enabled":[191],"only":[195],"but":[200,234],"also":[201],"lot":[205],"more":[206],"compared":[208],"corresponding":[211],"mechanisms":[212],"do":[214],"utilize":[216],"NLP.":[217],"The":[218],"was":[220],"evaluated":[221],"upon":[222],"diverse":[223],"healthcare":[224,232],"datasets,":[225],"however":[227],"being":[228],"limited":[229],"domain,":[233],"supporting":[235],"generalized":[237],"concept.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}