{"id":"https://openalex.org/W3138113236","doi":"https://doi.org/10.1109/bigdata50022.2020.9378148","title":"Towards Automatic Data Cleansing and Classification of Valid Historical Data An Incremental Approach Based on MDD","display_name":"Towards Automatic Data Cleansing and Classification of Valid Historical Data An Incremental Approach Based on MDD","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3138113236","doi":"https://doi.org/10.1109/bigdata50022.2020.9378148","mag":"3138113236"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9378148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Towards_automatic_data_cleansing_and_classification_of_valid_historical_data_an_incremental_approach_based_on_MDD/23735850","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082516894","display_name":"Enda O\u2019Shea","orcid":"https://orcid.org/0000-0002-2777-5899"},"institutions":[{"id":"https://openalex.org/I230495080","display_name":"University of Limerick","ror":"https://ror.org/00a0n9e72","country_code":"IE","type":"education","lineage":["https://openalex.org/I230495080"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Enda O'Shea","raw_affiliation_strings":["University of Limerick, Limerick, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Limerick, Limerick, Ireland","institution_ids":["https://openalex.org/I230495080"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069185004","display_name":"Rafflesia Khan","orcid":"https://orcid.org/0000-0001-9006-6748"},"institutions":[{"id":"https://openalex.org/I230495080","display_name":"University of Limerick","ror":"https://ror.org/00a0n9e72","country_code":"IE","type":"education","lineage":["https://openalex.org/I230495080"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Rafflesia Khan","raw_affiliation_strings":["University of Limerick, Limerick, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Limerick, Limerick, Ireland","institution_ids":["https://openalex.org/I230495080"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033112212","display_name":"Ciara Breathnach","orcid":"https://orcid.org/0000-0002-4065-0660"},"institutions":[{"id":"https://openalex.org/I230495080","display_name":"University of Limerick","ror":"https://ror.org/00a0n9e72","country_code":"IE","type":"education","lineage":["https://openalex.org/I230495080"]},{"id":"https://openalex.org/I2802024501","display_name":"Irish Research Council","ror":"https://ror.org/051xex213","country_code":"IE","type":"funder","lineage":["https://openalex.org/I2802024501"]},{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["ES","IE"],"is_corresponding":false,"raw_author_name":"Ciara Breathnach","raw_affiliation_strings":["Lero: The Irish Software Research Centre","University of Limerick, Limerick, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lero: The Irish Software Research Centre","institution_ids":["https://openalex.org/I2802024501","https://openalex.org/I97750245"]},{"raw_affiliation_string":"University of Limerick, Limerick, Ireland","institution_ids":["https://openalex.org/I230495080"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013165259","display_name":"Tiziana Margaria","orcid":"https://orcid.org/0000-0002-5547-9739"},"institutions":[{"id":"https://openalex.org/I230495080","display_name":"University of Limerick","ror":"https://ror.org/00a0n9e72","country_code":"IE","type":"education","lineage":["https://openalex.org/I230495080"]},{"id":"https://openalex.org/I2802024501","display_name":"Irish Research Council","ror":"https://ror.org/051xex213","country_code":"IE","type":"funder","lineage":["https://openalex.org/I2802024501"]},{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["ES","IE"],"is_corresponding":false,"raw_author_name":"Tiziana Margaria","raw_affiliation_strings":["Lero: The Irish Software Research Centre","University of Limerick, Limerick, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lero: The Irish Software Research Centre","institution_ids":["https://openalex.org/I2802024501","https://openalex.org/I97750245"]},{"raw_affiliation_string":"University of Limerick, Limerick, Ireland","institution_ids":["https://openalex.org/I230495080"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4684,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.58915938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1914","last_page":"1923"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9944000244140625,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9944000244140625,"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/T11719","display_name":"Data Quality and Management","score":0.9930999875068665,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8126041889190674},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.7278976440429688},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6065987944602966},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5985993146896362},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4809214770793915},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43981385231018066},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4069022536277771},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38245877623558044},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37687012553215027},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27249300479888916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126041889190674},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.7278976440429688},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6065987944602966},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5985993146896362},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4809214770793915},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43981385231018066},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4069022536277771},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38245877623558044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37687012553215027},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27249300479888916},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9378148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/23735850","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Towards_automatic_data_cleansing_and_classification_of_valid_historical_data_an_incremental_approach_based_on_MDD/23735850","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"},{"id":"doi:10.34961/researchrepository-ul.23735850.v1","is_oa":true,"landing_page_url":"https://doi.org/10.34961/researchrepository-ul.23735850.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401530","display_name":"University of Limerick Institutional Repository (University of Limerick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I230495080","host_organization_name":"University of Limerick","host_organization_lineage":["https://openalex.org/I230495080"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/23735850","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Towards_automatic_data_cleansing_and_classification_of_valid_historical_data_an_incremental_approach_based_on_MDD/23735850","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2394637485","display_name":"SFI Centre for Research Training in Artificial Intelligence","funder_award_id":"18/CRT/6223","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G7736775806","display_name":"Lero - the Irish Software Research Centre","funder_award_id":"13/RC/2094","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320321056","display_name":"Irish Research Council","ror":"https://ror.org/051xex213"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W994990881","https://openalex.org/W1499966647","https://openalex.org/W1523375725","https://openalex.org/W1992465941","https://openalex.org/W2014596857","https://openalex.org/W2027993973","https://openalex.org/W2044579012","https://openalex.org/W2097476716","https://openalex.org/W2107465592","https://openalex.org/W2139549655","https://openalex.org/W2152401910","https://openalex.org/W2343715481","https://openalex.org/W2510799396","https://openalex.org/W2523646273","https://openalex.org/W2529802478","https://openalex.org/W2604057676","https://openalex.org/W2605362632","https://openalex.org/W2754385751","https://openalex.org/W2792184728","https://openalex.org/W2898478450","https://openalex.org/W2963686796","https://openalex.org/W2978187656","https://openalex.org/W2979817636","https://openalex.org/W2990689217","https://openalex.org/W2995737494","https://openalex.org/W2997922060","https://openalex.org/W3037654372","https://openalex.org/W3045990532","https://openalex.org/W3098336018","https://openalex.org/W4287980061","https://openalex.org/W6768355468","https://openalex.org/W6771594992","https://openalex.org/W6772402829"],"related_works":["https://openalex.org/W962911587","https://openalex.org/W4200551113","https://openalex.org/W2270762093","https://openalex.org/W2028861106","https://openalex.org/W4255072332","https://openalex.org/W3126834064","https://openalex.org/W3110671107","https://openalex.org/W1754154538","https://openalex.org/W3169246587","https://openalex.org/W4253714063"],"abstract_inverted_index":{"The":[0,250,311],"project":[1,372],"Death":[2],"and":[3,17,50,64,80,144,147,150,165,181,193,201,206,240,245,278,308,323,352,375,393],"Burial":[4],"Data:":[5],"Ireland":[6,27],"1864-1922":[7],"(DBDIrl)":[8],"examines":[9],"the":[10,22,82,98,111,132,136,148,156,160,186,189,194,198,204,224,263,267,303,324,348,371],"relationship":[11],"between":[12],"historical":[13,38],"death":[14],"registration":[15],"data":[16,19,55,113,123,163,238,280,299,384],"burial":[18],"to":[20,30,92,102,179,223,319,357,365,369,380],"explore":[21],"history":[23],"of":[24,43,77,127,135,152,155,188,196,209,342],"power":[25],"in":[26,61,159,183,316,338,378],"from":[28,37,40,266],"1864":[29],"1922.":[31],"Its":[32],"core":[33],"Big":[34],"Data":[35],"arises":[36],"records":[39,60,71],"a":[41,85,104,232,256,272,284,330,339,382],"variety":[42],"heterogeneous":[44],"sources,":[45,124],"some":[46],"aspects":[47],"are":[48,219,354],"pre-digitized":[49],"machine":[51],"readable.":[52],"A":[53],"huge":[54],"set":[56,385],"(over":[57],"4":[58],"million":[59],"each":[62],"source)":[63],"its":[65],"slow":[66],"manual":[67],"enrichment":[68,177],"(ca":[69],"7,000":[70],"processed":[72],"so":[73],"far)":[74],"pose":[75],"issues":[76],"quality,":[78],"scalability,":[79],"creates":[81],"need":[83,304],"for":[84,97,110,142,203,276,305],"quality":[86,107,214],"assurance":[87,108,281],"technology":[88,225,349],"that":[89,114,261,288,335,386],"is":[90,101,115,314,329,387],"accessible":[91],"non-programmers.":[93],"An":[94],"important":[95],"goal":[96],"researcher":[99],"community":[100],"produce":[103,358,381],"reusable,":[105],"high-level":[106],"tool":[109,326],"ingested":[112],"domain":[116],"specific":[117],"(historic":[118],"data),":[119],"highly":[120],"portable":[121],"across":[122],"thus":[125,346],"independent":[126],"storage":[128,143],"technology.This":[129],"paper":[130],"outlines":[131],"step-wise":[133],"design":[134,149,187],"finer":[137],"granular":[138],"digital":[139,145,191],"format,":[140],"aimed":[141],"archiving,":[146],"test":[151],"two":[153,162],"generations":[154],"techniques,":[157],"used":[158],"first":[161,168,229],"ingestion":[164],"cleaning":[166,239,309],"phases.The":[167],"small":[169],"scale":[170,253],"phase":[171,230,254],"was":[172],"exploratory,":[173],"based":[174],"on":[175],"metadata":[176],"transcription":[178],"Excel,":[180],"conducted":[182],"parallel":[184],"with":[185,235,373],"final":[190],"format":[192],"discovery":[195],"all":[197],"domain-specific":[199],"rules":[200],"constraints":[202,296],"syntax":[205],"semantic":[207],"validity":[208],"individual":[210],"entries.":[211],"Excel":[212],"embedded":[213,237],"checks":[215],"or":[216],"database-specific":[217],"techniques":[218],"not":[220],"adequate":[221],"due":[222],"independence":[226,350],"requirement.":[227],"This":[228,292],"produced":[231],"Java":[233,264],"parser":[234],"an":[236,317],"evaluation":[241],"classifier,":[242],"continuously":[243],"improved":[244],"refined":[246],"as":[247,269,271],"insights":[248],"grew.":[249],"next,":[251],"larger":[252],"uses":[255,328],"bespoke":[257],"Historian":[258],"Web":[259],"Application":[260],"embeds":[262],"validator":[265],"parser,":[268],"well":[270],"new":[273,312,359],"Boolean":[274],"classifier":[275,313],"valid":[277],"complete":[279],"built":[282,315],"using":[283],"Model-Driven":[285],"Development":[286],"technique":[287],"we":[289],"also":[290],"describe.":[291],"solution":[293],"enforces":[294],"property":[295],"directly":[297],"at":[298],"capture":[300],"time,":[301],"removing":[302],"additional":[306],"parsing":[307],"stages.":[310],"easy":[318],"use":[320],"graphical":[321],"technology,":[322],"ADD-Lib":[325],"it":[327],"modern":[331],"low-code":[332],"development":[333],"environment":[334],"auto-generates":[336],"code":[337],"large":[340],"number":[341],"programming":[343],"languages.":[344],"It":[345],"meets":[347],"requirement":[351],"historians":[353],"now":[355],"able":[356,364],"classifiers":[360],"themselves":[361],"without":[362],"being":[363],"program.":[366],"We":[367],"aim":[368],"infuse":[370],"computational":[374],"archival":[376],"thinking":[377],"order":[379],"robust":[383],"FAIR":[388],"compliant":[389],"(Free":[390],"Accessible":[391],"Inter-operable":[392],"Re-useable).":[394]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}