{"id":"https://openalex.org/W2910309215","doi":"https://doi.org/10.1109/innovations.2018.8605945","title":"Big Data Quality Assessment Model for Unstructured Data","display_name":"Big Data Quality Assessment Model for Unstructured Data","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2910309215","doi":"https://doi.org/10.1109/innovations.2018.8605945","mag":"2910309215"},"language":"en","primary_location":{"id":"doi:10.1109/innovations.2018.8605945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/innovations.2018.8605945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Innovations in Information Technology (IIT)","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/A5064726931","display_name":"Ikbal Taleb","orcid":"https://orcid.org/0000-0003-1738-2642"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ikbal Taleb","raw_affiliation_strings":["CIISE Concordia University, Montreal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIISE Concordia University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022074764","display_name":"Mohamed Adel Serhani","orcid":"https://orcid.org/0000-0001-7001-3710"},"institutions":[{"id":"https://openalex.org/I201726411","display_name":"United Arab Emirates University","ror":"https://ror.org/01km6p862","country_code":"AE","type":"education","lineage":["https://openalex.org/I201726411"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mohamed Adel Serhani","raw_affiliation_strings":["College of Information Technology UAE University, Al Ain, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Technology UAE University, Al Ain, UAE","institution_ids":["https://openalex.org/I201726411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057013558","display_name":"Rachida Dssouli","orcid":"https://orcid.org/0000-0002-7859-9098"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rachida Dssouli","raw_affiliation_strings":["CIISE Concordia University, Montreal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIISE Concordia University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5226,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.93073528,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9954000115394592,"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"}},{"id":"https://openalex.org/T14280","display_name":"Big Data Technologies and Applications","score":0.9768999814987183,"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":0.7432678937911987},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7233123183250427},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6681208610534668},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.6406958103179932},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5857800245285034},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.506194531917572},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.474031001329422},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42805057764053345},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.30028092861175537},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1313885748386383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432678937911987},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7233123183250427},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6681208610534668},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.6406958103179932},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5857800245285034},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.506194531917572},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.474031001329422},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42805057764053345},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30028092861175537},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1313885748386383},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/innovations.2018.8605945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/innovations.2018.8605945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Innovations in Information Technology (IIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W80463681","https://openalex.org/W114869232","https://openalex.org/W144896739","https://openalex.org/W331312376","https://openalex.org/W935072310","https://openalex.org/W1494137514","https://openalex.org/W1912802097","https://openalex.org/W1989776363","https://openalex.org/W1994410669","https://openalex.org/W2004291985","https://openalex.org/W2007907699","https://openalex.org/W2030910246","https://openalex.org/W2049334895","https://openalex.org/W2066176974","https://openalex.org/W2069140227","https://openalex.org/W2108454922","https://openalex.org/W2109574129","https://openalex.org/W2134684245","https://openalex.org/W2149140091","https://openalex.org/W2157954477","https://openalex.org/W2159128662","https://openalex.org/W2165394871","https://openalex.org/W2169004485","https://openalex.org/W2184308596","https://openalex.org/W2313965969","https://openalex.org/W2315329697","https://openalex.org/W2316007180","https://openalex.org/W2367037334","https://openalex.org/W2465157137","https://openalex.org/W2572690852","https://openalex.org/W2575989903","https://openalex.org/W2579621665","https://openalex.org/W2619066857","https://openalex.org/W2735570159","https://openalex.org/W2738417325","https://openalex.org/W2785683605","https://openalex.org/W2884466623","https://openalex.org/W4239717161","https://openalex.org/W6603158870","https://openalex.org/W6604605561","https://openalex.org/W6611340311","https://openalex.org/W6629518394","https://openalex.org/W6686046723","https://openalex.org/W6698363757","https://openalex.org/W6708021194","https://openalex.org/W6732632601","https://openalex.org/W6738137677","https://openalex.org/W6748426950"],"related_works":["https://openalex.org/W3157828377","https://openalex.org/W4377992839","https://openalex.org/W2891888580","https://openalex.org/W2215544391","https://openalex.org/W4210350690","https://openalex.org/W2937168573","https://openalex.org/W2261525379","https://openalex.org/W2162769527","https://openalex.org/W2805468299","https://openalex.org/W4231652189"],"abstract_inverted_index":{"Big":[0,42,86,210],"Data":[1,20,87,127,133],"has":[2,44],"gained":[3],"an":[4,180,202,228],"enormous":[5],"momentum":[6],"the":[7,13,33,39,111,151,169,188,191,196],"past":[8],"few":[9],"years":[10],"because":[11],"of":[12,16,31,41,84,97,150,157,208,217,233],"tremendous":[14],"volume":[15],"generated":[17,34],"and":[18,59,92,101,114,117,145,220],"processed":[19],"from":[21,119,190],"diverse":[22],"application":[23],"domains.":[24,147],"Nowadays,":[25],"it":[26],"is":[27,36,161],"estimated":[28],"that":[29,167,185,222],"80%":[30],"all":[32,187],"data":[35,43,52,65,100,121,143,146,155,230],"unstructured.":[37],"Evaluating":[38],"quality":[40,53,66,78,83,134,136,165,170,176,182,206,218,231],"been":[45],"identified":[46],"to":[47,50,81,108,163,195,226],"be":[48,224],"essential":[49],"guarantee":[51],"dimensions":[54],"including":[55],"for":[56,63,175,205],"example":[57],"completeness,":[58],"accuracy.":[60],"Current":[61],"initiatives":[62],"unstructured":[64,98,209],"evaluation":[67,79],"are":[68],"still":[69],"under":[70],"investigations.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"propose":[76],"a":[77,154,164,215],"model":[80,184,200],"handle":[82],"Unstructured":[85],"(UBD).":[88],"The":[89,199],"later":[90],"captures":[91],"discover":[93],"first":[94],"key":[95],"properties":[96],"big":[99],"its":[102],"characteristics,":[103],"provides":[104,153,201],"some":[105],"comprehensive":[106],"mechanisms":[107],"sample,":[109],"profile":[110,156,160,166],"UBD":[112,181,192],"dataset":[113],"extract":[115],"features":[116,138,174],"characteristics":[118,219],"heterogeneous":[120],"types":[122,144],"in":[123],"different":[124],"formats.":[125],"A":[126],"Quality":[128,197],"repository":[129],"manage":[130],"relationships":[131],"between":[132],"dimensions,":[135],"Metrics,":[137],"extraction":[139],"methods,":[140],"mining":[141],"methodologies,":[142],"An":[148],"analysis":[149],"samples":[152],"UBD.":[158,234],"This":[159],"extended":[162],"contains":[168],"mapping":[171],"with":[172],"selected":[173],"assessment.":[177],"We":[178],"developed":[179],"assessment":[183],"handles":[186],"processes":[189],"profiling":[193],"exploration":[194],"report.":[198],"initial":[203,229],"blueprint":[204],"estimation":[207],"data.":[211],"It":[212],"also,":[213],"states":[214],"set":[216],"indicators":[221],"can":[223],"used":[225],"outline":[227],"schema":[232]},"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":15},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
