{"id":"https://openalex.org/W2215544391","doi":"https://doi.org/10.1109/bigdata.2015.7364064","title":"Big data, big data quality problem","display_name":"Big data, big data quality problem","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2215544391","doi":"https://doi.org/10.1109/bigdata.2015.7364064","mag":"2215544391"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7364064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","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/A5033518940","display_name":"David Becker","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Becker","raw_affiliation_strings":["The MITRE Corporation"],"affiliations":[{"raw_affiliation_string":"The MITRE Corporation","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020015160","display_name":"Trish Dunn King","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trish Dunn King","raw_affiliation_strings":["The MITRE Corporation"],"affiliations":[{"raw_affiliation_string":"The MITRE Corporation","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046029900","display_name":"Bill McMullen","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bill McMullen","raw_affiliation_strings":["The MITRE Corporation"],"affiliations":[{"raw_affiliation_string":"The MITRE Corporation","institution_ids":["https://openalex.org/I44896327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033518940"],"corresponding_institution_ids":["https://openalex.org/I44896327"],"apc_list":null,"apc_paid":null,"fwci":10.4398,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.97795785,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2644","last_page":"2653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14280","display_name":"Big Data Technologies and Applications","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T14280","display_name":"Big Data Technologies and Applications","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T14465","display_name":"Leadership, Behavior, and Decision-Making Studies","score":0.998199999332428,"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/T13994","display_name":"The Impact of Diversity and Innovation on Society","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.9460322260856628},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.743090808391571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7306542992591858},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.7258105278015137},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5462505221366882},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4926052689552307},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4676389694213867},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4642968773841858},{"id":"https://openalex.org/keywords/data-integrity","display_name":"Data integrity","score":0.43531209230422974},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.27312660217285156},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22820237278938293},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12388995289802551}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.9460322260856628},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.743090808391571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7306542992591858},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.7258105278015137},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5462505221366882},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4926052689552307},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4676389694213867},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4642968773841858},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.43531209230422974},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27312660217285156},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22820237278938293},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12388995289802551},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7364064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1516922439","https://openalex.org/W2093217276","https://openalex.org/W3033067793"],"related_works":["https://openalex.org/W2891888580","https://openalex.org/W4210350690","https://openalex.org/W2625749796","https://openalex.org/W4226266853","https://openalex.org/W4245701730","https://openalex.org/W2511794504","https://openalex.org/W3092201768","https://openalex.org/W2911648135","https://openalex.org/W3041894995","https://openalex.org/W2146933441"],"abstract_inverted_index":{"A":[0],"USAF":[1],"sponsored":[2],"MITRE":[3],"research":[4],"team":[5],"undertook":[6],"four":[7],"separate,":[8],"domain-specific":[9],"case":[10,17],"studies":[11,18],"about":[12,148],"Big":[13,34,63,89,100,149,160,177,181,189,196],"Data":[14,35,64,90,101,132,161,178,182,190,197],"applications.":[15],"Those":[16],"were":[19],"initial":[20],"investigations":[21],"into":[22],"the":[23,77,85,93,114,117,119,122,130,143,146],"question":[24],"of":[25,80,109,116,188],"whether":[26],"or":[27,43,173],"not":[28,75],"data":[29,47,55,139],"quality":[30,48,133],"issues":[31,49,158,166],"encountered":[32,50],"in":[33,40,51,92,159,176],"collections":[36],"are":[37,108,153],"substantially":[38],"different":[39],"cause,":[41],"manifestation,":[42],"detection":[44],"than":[45,113],"those":[46],"more":[52,172],"traditionally":[53],"sized":[54],"collections.":[56],"The":[57],"study":[58,82],"addresses":[59],"several":[60],"factors":[61,87],"affecting":[62,88],"Quality":[65,183],"at":[66],"multiple":[67],"levels,":[68],"including":[69],"collection,":[70],"processing,":[71,120],"and":[72,95,121,128,170,193],"storage.":[73],"Though":[74],"unexpected,":[76],"key":[78],"findings":[79],"this":[81],"reinforce":[83],"that":[84],"primary":[86],"reside":[91],"limitations":[94],"complexities":[96],"involved":[97],"with":[98],"handling":[99],"while":[102],"maintaining":[103],"its":[104],"integrity.":[105],"These":[106],"concerns":[107],"a":[110],"higher":[111],"magnitude":[112],"provenance":[115],"data,":[118],"tools":[123],"used":[124],"to":[125,191,199],"prepare,":[126],"manipulate,":[127],"store":[129],"data.":[131],"is":[134,151],"extremely":[135],"important":[136],"for":[137],"all":[138],"analytics":[140,162],"problems.":[141],"From":[142],"study's":[144],"findings,":[145],"\"truth":[147],"Data\"":[150],"there":[152],"no":[154],"fundamentally":[155],"new":[156],"DQ":[157,165],"projects.":[163],"Some":[164],"exhibit":[167],"return-s-to-scale":[168],"effects,":[169],"become":[171],"less":[174],"pronounced":[175],"analytics,":[179],"though.":[180],"varies":[184],"from":[185,194],"one":[186,195],"type":[187],"another":[192],"technology":[198],"another.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5}],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-10-10T00:00:00"}