{"id":"https://openalex.org/W4401751787","doi":"https://doi.org/10.1109/icccn61486.2024.10637520","title":"Big Data Quality Scoring for Structured Data Using MapReduce","display_name":"Big Data Quality Scoring for Structured Data Using MapReduce","publication_year":2024,"publication_date":"2024-07-29","ids":{"openalex":"https://openalex.org/W4401751787","doi":"https://doi.org/10.1109/icccn61486.2024.10637520"},"language":"en","primary_location":{"id":"doi:10.1109/icccn61486.2024.10637520","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icccn61486.2024.10637520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 33rd International Conference on Computer Communications and Networks (ICCCN)","raw_type":"proceedings-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/A5062031330","display_name":"Yalong Wu","orcid":"https://orcid.org/0000-0001-9879-431X"},"institutions":[{"id":"https://openalex.org/I52913039","display_name":"University of Houston - Clear Lake","ror":"https://ror.org/01t817z14","country_code":"US","type":"education","lineage":["https://openalex.org/I52913039"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yalong Wu","raw_affiliation_strings":["University of Houston–Clear Lake,Department of Computing Sciences,TX,USA"],"affiliations":[{"raw_affiliation_string":"University of Houston–Clear Lake,Department of Computing Sciences,TX,USA","institution_ids":["https://openalex.org/I52913039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113342769","display_name":"Shalini Dhamodharan","orcid":null},"institutions":[{"id":"https://openalex.org/I52913039","display_name":"University of Houston - Clear Lake","ror":"https://ror.org/01t817z14","country_code":"US","type":"education","lineage":["https://openalex.org/I52913039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shalini Dhamodharan","raw_affiliation_strings":["University of Houston–Clear Lake,Department of Computing Sciences,TX,USA"],"affiliations":[{"raw_affiliation_string":"University of Houston–Clear Lake,Department of Computing Sciences,TX,USA","institution_ids":["https://openalex.org/I52913039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106662325","display_name":"Vinuthna Ghattamaneni","orcid":null},"institutions":[{"id":"https://openalex.org/I52913039","display_name":"University of Houston - Clear Lake","ror":"https://ror.org/01t817z14","country_code":"US","type":"education","lineage":["https://openalex.org/I52913039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinuthna Ghattamaneni","raw_affiliation_strings":["University of Houston–Clear Lake,Department of Computing Sciences,TX,USA"],"affiliations":[{"raw_affiliation_string":"University of Houston–Clear Lake,Department of Computing Sciences,TX,USA","institution_ids":["https://openalex.org/I52913039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033284171","display_name":"N. Kokila","orcid":null},"institutions":[{"id":"https://openalex.org/I52913039","display_name":"University of Houston - Clear Lake","ror":"https://ror.org/01t817z14","country_code":"US","type":"education","lineage":["https://openalex.org/I52913039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Narmada Kokila","raw_affiliation_strings":["University of Houston–Clear Lake,Department of Computing Sciences,TX,USA"],"affiliations":[{"raw_affiliation_string":"University of Houston–Clear Lake,Department of Computing Sciences,TX,USA","institution_ids":["https://openalex.org/I52913039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106662326","display_name":"Chandrika Pathakamuri","orcid":null},"institutions":[{"id":"https://openalex.org/I52913039","display_name":"University of Houston - Clear Lake","ror":"https://ror.org/01t817z14","country_code":"US","type":"education","lineage":["https://openalex.org/I52913039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandrika Pathakamuri","raw_affiliation_strings":["University of Houston–Clear Lake,Department of Computing Sciences,TX,USA"],"affiliations":[{"raw_affiliation_string":"University of Houston–Clear Lake,Department of Computing Sciences,TX,USA","institution_ids":["https://openalex.org/I52913039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059133698","display_name":"Timothy R. Carter","orcid":"https://orcid.org/0000-0002-4026-8859"},"institutions":[{"id":"https://openalex.org/I52913039","display_name":"University of Houston - Clear Lake","ror":"https://ror.org/01t817z14","country_code":"US","type":"education","lineage":["https://openalex.org/I52913039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy Carter","raw_affiliation_strings":["University of Houston–Clear Lake,Department of Computing Sciences,TX,USA"],"affiliations":[{"raw_affiliation_string":"University of Houston–Clear Lake,Department of Computing Sciences,TX,USA","institution_ids":["https://openalex.org/I52913039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103074653","display_name":"Tian Pu","orcid":"https://orcid.org/0000-0002-5150-8053"},"institutions":[{"id":"https://openalex.org/I24010308","display_name":"Stockton University","ror":"https://ror.org/0442n1j98","country_code":"US","type":"education","lineage":["https://openalex.org/I24010308"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pu Tian","raw_affiliation_strings":["Stockton University,School of Business,NJ,USA"],"affiliations":[{"raw_affiliation_string":"Stockton University,School of Business,NJ,USA","institution_ids":["https://openalex.org/I24010308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061053956","display_name":"Kewei Sha","orcid":"https://orcid.org/0000-0002-3750-163X"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kewei Sha","raw_affiliation_strings":["University of North Texas,Department of Information Science,TX,USA"],"affiliations":[{"raw_affiliation_string":"University of North Texas,Department of Information Science,TX,USA","institution_ids":["https://openalex.org/I123534392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5062031330"],"corresponding_institution_ids":["https://openalex.org/I52913039"],"apc_list":null,"apc_paid":null,"fwci":0.8118,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78254365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9883000254631042,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9883000254631042,"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/T11719","display_name":"Data Quality and Management","score":0.9829999804496765,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9498999714851379,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8304641246795654},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7192022800445557},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.49045678973197937},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4880124628543854},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4295836091041565},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38290056586265564},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.171879380941391}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304641246795654},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7192022800445557},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.49045678973197937},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4880124628543854},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4295836091041565},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38290056586265564},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.171879380941391},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccn61486.2024.10637520","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icccn61486.2024.10637520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 33rd International Conference on Computer Communications and Networks (ICCCN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W935072310","https://openalex.org/W2004291985","https://openalex.org/W2070734010","https://openalex.org/W2087309216","https://openalex.org/W2109574129","https://openalex.org/W2303147257","https://openalex.org/W4230298561","https://openalex.org/W4306292106","https://openalex.org/W4312000335","https://openalex.org/W4312070806","https://openalex.org/W4313413556","https://openalex.org/W4319879502","https://openalex.org/W4362611851","https://openalex.org/W4365397912","https://openalex.org/W4387089269"],"related_works":["https://openalex.org/W2891888580","https://openalex.org/W2215544391","https://openalex.org/W4210350690","https://openalex.org/W2135768893","https://openalex.org/W176219849","https://openalex.org/W3021414116","https://openalex.org/W3081133439","https://openalex.org/W4386246791","https://openalex.org/W2945537679","https://openalex.org/W3211701140"],"abstract_inverted_index":{"In":[0],"the":[1,9,19,27,43,68,74,162],"current":[2],"big":[3,56,152],"data":[4,7,33,47,57,97,102,117,133,153],"landscape,":[5],"where":[6],"forms":[8],"cornerstone":[10],"of":[11,23,29,70,116,125,142,166],"myriad":[12],"applications,":[13],"it":[14],"is":[15,63],"crucial":[16],"to":[17,42,127],"establish":[18],"reliability":[20,163],"and":[21,49,111,129,139,156,164],"credibility":[22],"application":[24],"outcomes":[25],"through":[26,136],"prism":[28],"high-quality":[30],"data.":[31],"Nonetheless,":[32],"quality":[34,58,69,98,134,154],"has":[35],"been":[36],"facing":[37],"significant":[38],"evaluation":[39],"challenges":[40],"due":[41],"exponential":[44],"increase":[45],"in":[46,94],"volume":[48],"diversity.":[50],"This":[51,145],"paper":[52],"introduces":[53],"a":[54,123,148],"novel":[55],"scoring":[59],"(BDQS)":[60],"model,":[61],"which":[62],"particularly":[64],"designed":[65],"for":[66,100,151,160],"assessing":[67],"large-scale":[71,167],"datasets":[72,86,168],"within":[73],"Hadoop":[75],"MapReduce":[76],"ecosystem.":[77],"Unlike":[78],"other":[79],"models":[80],"that":[81],"either":[82],"focus":[83],"on":[84,89,122],"smaller":[85],"or":[87],"rely":[88],"sampling":[90],"techniques,":[91],"BDQS":[92,105],"excels":[93],"providing":[95],"comprehensive":[96],"assessment":[99,155],"substantial":[101],"sources.":[103],"Specifically,":[104],"identifies":[106],"accuracy,":[107],"completeness,":[108],"consistency,":[109],"timeliness,":[110],"correlation":[112],"as":[113],"critical":[114],"dimensions":[115],"quality,":[118],"scores":[119],"each":[120],"dimension":[121],"scale":[124],"0":[126],"100,":[128],"derives":[130],"an":[131],"aggregate":[132],"score":[135],"binomial":[137],"testing":[138],"standard":[140],"normalization":[141],"these":[143],"scores.":[144],"research":[146],"advances":[147],"potent":[149],"model":[150],"offers":[157],"valuable":[158],"insights":[159],"enhancing":[161],"applicability":[165],"across":[169],"various":[170],"sectors.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}