{"id":"https://openalex.org/W4391567801","doi":"https://doi.org/10.3390/bdcc8020017","title":"A Model for Enhancing Unstructured Big Data Warehouse Execution Time","display_name":"A Model for Enhancing Unstructured Big Data Warehouse Execution Time","publication_year":2024,"publication_date":"2024-02-06","ids":{"openalex":"https://openalex.org/W4391567801","doi":"https://doi.org/10.3390/bdcc8020017"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc8020017","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc8020017","pdf_url":"https://www.mdpi.com/2504-2289/8/2/17/pdf?version=1707182026","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/8/2/17/pdf?version=1707182026","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048031078","display_name":"Marwa Salah Farhan","orcid":"https://orcid.org/0000-0002-6340-2547"},"institutions":[{"id":"https://openalex.org/I84058292","display_name":"Helwan University","ror":"https://ror.org/00h55v928","country_code":"EG","type":"education","lineage":["https://openalex.org/I84058292"]},{"id":"https://openalex.org/I154023281","display_name":"British University in Egypt","ror":"https://ror.org/0066fxv63","country_code":"EG","type":"education","lineage":["https://openalex.org/I154023281"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Marwa Salah Farhan","raw_affiliation_strings":["Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo 11795, Egypt","Faculty of Informatics and Computer Science, British University in Egypt, Cairo 11837, Egypt"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo 11795, Egypt","institution_ids":["https://openalex.org/I84058292"]},{"raw_affiliation_string":"Faculty of Informatics and Computer Science, British University in Egypt, Cairo 11837, Egypt","institution_ids":["https://openalex.org/I154023281"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089278874","display_name":"Amira Youssef","orcid":"https://orcid.org/0000-0002-2344-4785"},"institutions":[{"id":"https://openalex.org/I84058292","display_name":"Helwan University","ror":"https://ror.org/00h55v928","country_code":"EG","type":"education","lineage":["https://openalex.org/I84058292"]},{"id":"https://openalex.org/I4210140988","display_name":"Cairo Higher Institute","ror":"https://ror.org/045rvh172","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210140988"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Amira Youssef","raw_affiliation_strings":["Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo 11795, Egypt","Higher Institute of Computer Science and Information Systems, 5th Settlement, Department of Computer Science, Cairo 11835, Egypt"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo 11795, Egypt","institution_ids":["https://openalex.org/I84058292"]},{"raw_affiliation_string":"Higher Institute of Computer Science and Information Systems, 5th Settlement, Department of Computer Science, Cairo 11835, Egypt","institution_ids":["https://openalex.org/I4210140988"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006325637","display_name":"Laila Abdelhamid","orcid":"https://orcid.org/0000-0002-7928-5680"},"institutions":[{"id":"https://openalex.org/I84058292","display_name":"Helwan University","ror":"https://ror.org/00h55v928","country_code":"EG","type":"education","lineage":["https://openalex.org/I84058292"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Laila Abdelhamid","raw_affiliation_strings":["Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo 11795, Egypt"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo 11795, Egypt","institution_ids":["https://openalex.org/I84058292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089278874"],"corresponding_institution_ids":["https://openalex.org/I4210140988","https://openalex.org/I84058292"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.8263,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84799366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"8","issue":"2","first_page":"17","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998000264167786,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9998000264167786,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9961000084877014,"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":0.9871000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.7237415313720703},{"id":"https://openalex.org/keywords/warehouse","display_name":"Warehouse","score":0.700042188167572},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6253402233123779},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5507479906082153},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.5024158954620361},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.45061105489730835},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3571069538593292},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.24300384521484375},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2387574315071106},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.06913039088249207}],"concepts":[{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.7237415313720703},{"id":"https://openalex.org/C50416739","wikidata":"https://www.wikidata.org/wiki/Q181623","display_name":"Warehouse","level":2,"score":0.700042188167572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6253402233123779},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5507479906082153},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.5024158954620361},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.45061105489730835},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3571069538593292},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.24300384521484375},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2387574315071106},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.06913039088249207}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/bdcc8020017","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc8020017","pdf_url":"https://www.mdpi.com/2504-2289/8/2/17/pdf?version=1707182026","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0aee6b47a2994f6788cdd74ee422b1d4","is_oa":true,"landing_page_url":"https://doaj.org/article/0aee6b47a2994f6788cdd74ee422b1d4","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 8, Iss 2, p 17 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc8020017","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc8020017","pdf_url":"https://www.mdpi.com/2504-2289/8/2/17/pdf?version=1707182026","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391567801.pdf"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1610496399","https://openalex.org/W1989674646","https://openalex.org/W2000876233","https://openalex.org/W2022678827","https://openalex.org/W2043765769","https://openalex.org/W2048493531","https://openalex.org/W2049470338","https://openalex.org/W2062031828","https://openalex.org/W2479227275","https://openalex.org/W2519340860","https://openalex.org/W2561082026","https://openalex.org/W2594063224","https://openalex.org/W2777722041","https://openalex.org/W2784426135","https://openalex.org/W2793386554","https://openalex.org/W2807765779","https://openalex.org/W2888124146","https://openalex.org/W2889062015","https://openalex.org/W2912335482","https://openalex.org/W2925032266","https://openalex.org/W2947006004","https://openalex.org/W2955863533","https://openalex.org/W2963999143","https://openalex.org/W2981583554","https://openalex.org/W2990358206","https://openalex.org/W3001479605","https://openalex.org/W3005236890","https://openalex.org/W3005795666","https://openalex.org/W3010930234","https://openalex.org/W3025750750","https://openalex.org/W3037843194","https://openalex.org/W3082688266","https://openalex.org/W3096600429","https://openalex.org/W3123266248","https://openalex.org/W3126263370","https://openalex.org/W3145723099","https://openalex.org/W3146147323","https://openalex.org/W3157111062","https://openalex.org/W3187028635","https://openalex.org/W3211870954","https://openalex.org/W4200081845","https://openalex.org/W4206552825","https://openalex.org/W4206680474","https://openalex.org/W4283026135","https://openalex.org/W4291366462","https://openalex.org/W4296232960","https://openalex.org/W4308547963","https://openalex.org/W4320480732","https://openalex.org/W4367032606","https://openalex.org/W4382278554","https://openalex.org/W4385078254","https://openalex.org/W4385308071","https://openalex.org/W4387494240","https://openalex.org/W4387614438","https://openalex.org/W6636177537","https://openalex.org/W6726612052","https://openalex.org/W6754002270","https://openalex.org/W6854714418"],"related_works":["https://openalex.org/W3116168327","https://openalex.org/W2389559488","https://openalex.org/W2382329217","https://openalex.org/W3157828377","https://openalex.org/W4377992839","https://openalex.org/W2937168573","https://openalex.org/W2261525379","https://openalex.org/W2162769527","https://openalex.org/W2805468299","https://openalex.org/W4231652189"],"abstract_inverted_index":{"Traditional":[0],"data":[1,22,30,64,80,153,168],"warehouses":[2],"(DWs)":[3],"have":[4],"played":[5],"a":[6,60,87,126,152],"key":[7],"role":[8],"in":[9,129,193],"business":[10],"intelligence":[11],"and":[12,49,70,120,191],"decision":[13],"support":[14],"systems.":[15,32],"However,":[16],"the":[17,21,25,41,72,79,135,158,167,175],"rapid":[18],"growth":[19],"of":[20,54,63,91,138,155,161,195],"generated":[23],"by":[24,143],"current":[26],"applications":[27],"requires":[28],"new":[29,47,88],"warehousing":[31],"In":[33],"big":[34,100],"data,":[35,101],"it":[36],"is":[37,75,118,125,163,178],"important":[38],"to":[39,45,110,171],"adapt":[40],"existing":[42],"warehouse":[43],"systems":[44],"overcome":[46],"issues":[48],"limitations.":[50],"The":[51,107],"main":[52],"drawbacks":[53],"traditional":[55],"Extract\u2013Transform\u2013Load":[56],"(ETL)":[57],"are":[58,81],"that":[59,71,150,184],"huge":[61],"amount":[62],"cannot":[65],"be":[66],"processed":[67],"over":[68],"ETL":[69],"execution":[73,112,136,159,176,196],"time":[74,113,137,160,177],"very":[76],"high":[77],"when":[78],"unstructured.":[82],"This":[83],"paper":[84,133],"focuses":[85],"on":[86,105],"model":[89,108],"consisting":[90],"four":[92],"layers:":[93],"Extract\u2013Clean\u2013Load\u2013Transform":[94],"(ECLT),":[95],"designed":[96],"for":[97,151],"processing":[98],"unstructured":[99],"with":[102,140],"specific":[103],"emphasis":[104],"text.":[106],"aims":[109],"reduce":[111],"through":[114],"experimental":[115],"procedures.":[116],"ECLT":[117,139,162,185],"applied":[119],"tested":[121],"using":[122],"Spark,":[123],"which":[124],"framework":[127],"employed":[128],"Python.":[130],"Finally,":[131],"this":[132],"compares":[134],"different":[141],"models":[142],"applying":[144],"two":[145],"datasets.":[146],"Experimental":[147],"results":[148],"showed":[149],"size":[154,169],"1":[156,172],"TB,":[157],"41.8":[164],"s.":[165,180],"When":[166],"increases":[170],"million":[173],"articles,":[174],"119.6":[179],"These":[181],"findings":[182],"demonstrate":[183],"outperforms":[186],"ETL,":[187],"ELT,":[188],"DELT,":[189],"ELTL,":[190],"ELTA":[192],"terms":[194],"time.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-01-21T23:30:37.877113","created_date":"2025-10-10T00:00:00"}