{"id":"https://openalex.org/W4241126594","doi":"https://doi.org/10.2139/ssrn.3610772","title":"Data Mining: Dirty Data and Data Cleaning","display_name":"Data Mining: Dirty Data and Data Cleaning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W4241126594","doi":"https://doi.org/10.2139/ssrn.3610772"},"language":"en","primary_location":{"id":"doi:10.2139/ssrn.3610772","doi":"https://doi.org/10.2139/ssrn.3610772","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.3610772","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2139/ssrn.3610772","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015887346","display_name":"Santosh Kumar Singh","orcid":"https://orcid.org/0000-0003-3104-1975","observed_orcids":["https://orcid.org/0000-0003-3104-1975"]},"institutions":[{"id":"https://openalex.org/I71631882","display_name":"Vinoba Bhave University","ror":"https://ror.org/00j98j631","country_code":"IN","type":"education","lineage":["https://openalex.org/I71631882"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Santosh Kumar Singh","raw_affiliation_strings":["University Deptt. of Computer Applications, Vinoba Bhave University, Hazaribag \u2013 825301, Jharkhand, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Deptt. of Computer Applications, Vinoba Bhave University, Hazaribag \u2013 825301, Jharkhand, India","institution_ids":["https://openalex.org/I71631882"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058294459","display_name":"Rajiv Kumar Dwivedi","orcid":"https://orcid.org/0009-0005-2555-7918","observed_orcids":["https://orcid.org/0009-0005-2555-7918","https://orcid.org/0009-0000-5739-2330"]},"institutions":[{"id":"https://openalex.org/I71631882","display_name":"Vinoba Bhave University","ror":"https://ror.org/00j98j631","country_code":"IN","type":"education","lineage":["https://openalex.org/I71631882"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dr. Rajiv Kumar Dwivedi","raw_affiliation_strings":["University Deptt. of Mathematics, Vinoba Bhave University, Hazaribag \u2013 825301, Jharkhand, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Deptt. of Mathematics, Vinoba Bhave University, Hazaribag \u2013 825301, Jharkhand, India","institution_ids":["https://openalex.org/I71631882"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5015887346"],"corresponding_institution_ids":["https://openalex.org/I71631882"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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/T12535","display_name":"Machine Learning and Data Classification","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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.0,"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/data-cleaning","display_name":"data cleaning","score":0.9430000185966492},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.9549999833106995},{"id":"https://openalex.org/keywords/dirty-data","display_name":"dirty data","score":0.8740000128746033},{"id":"https://openalex.org/keywords/data-mining","display_name":"data mining","score":0.7059999704360962},{"id":"https://openalex.org/keywords/data-errors","display_name":"data errors","score":0.5080000162124634},{"id":"https://openalex.org/keywords/missing-data","display_name":"missing data","score":0.6320000290870667},{"id":"https://openalex.org/keywords/data-quality-management","display_name":"data quality management","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3644901216030121},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35058531165122986},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3401612639427185},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32970887422561646}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2139/ssrn.3610772","doi":"https://doi.org/10.2139/ssrn.3610772","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.3610772","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.2139/ssrn.3610772","doi":"https://doi.org/10.2139/ssrn.3610772","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.3610772","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7217073988","https://openalex.org/W2135768893","https://openalex.org/W4249444306","https://openalex.org/W4248342017","https://openalex.org/W2166373579","https://openalex.org/W2923628529","https://openalex.org/W2546578412","https://openalex.org/W4235361915","https://openalex.org/W2055496291","https://openalex.org/W2958573811"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2022-05-12T00:00:00"}
