{"id":"https://openalex.org/W3123526537","doi":"https://doi.org/10.1155/2021/6653508","title":"Breast Cancer Identification from Patients\u2019 Tweet Streaming Using Machine Learning Solution on Spark","display_name":"Breast Cancer Identification from Patients\u2019 Tweet Streaming Using Machine Learning Solution on Spark","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3123526537","doi":"https://doi.org/10.1155/2021/6653508","mag":"3123526537"},"language":"en","primary_location":{"id":"doi:10.1155/2021/6653508","doi":"https://doi.org/10.1155/2021/6653508","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6653508","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/6653508.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W3123526537"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://downloads.hindawi.com/journals/complexity/2021/6653508.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040288065","display_name":"Nahla F. Omran","orcid":"https://orcid.org/0000-0002-6826-0429","observed_orcids":["https://orcid.org/0000-0002-6826-0429"]},"institutions":[{"id":"https://openalex.org/I189575948","display_name":"South Valley University","ror":"https://ror.org/00jxshx33","country_code":"EG","type":"education","lineage":["https://openalex.org/I189575948"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Nahla F. Omran","raw_affiliation_strings":["Computer Science Department, Faculty of Science, South Valley University, Qena, Egypt svu.edu.eg","Computer Science Department, Faculty of Science, South Valley University, Qena, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Faculty of Science, South Valley University, Qena, Egypt svu.edu.eg","institution_ids":["https://openalex.org/I189575948"]},{"raw_affiliation_string":"Computer Science Department, Faculty of Science, South Valley University, Qena, Egypt","institution_ids":["https://openalex.org/I189575948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112616313","display_name":"Sara F. Abd-el Ghany","orcid":"https://orcid.org/0000-0001-8362-4350","observed_orcids":["https://orcid.org/0000-0001-8362-4350"]},"institutions":[{"id":"https://openalex.org/I189575948","display_name":"South Valley University","ror":"https://ror.org/00jxshx33","country_code":"EG","type":"education","lineage":["https://openalex.org/I189575948"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Sara F. Abd-el Ghany","raw_affiliation_strings":["Computer Science Department, Faculty of Science, South Valley University, Qena, Egypt svu.edu.eg","Computer Science Department, Faculty of Science, South Valley University, Qena, Egypt"],"raw_orcid":"https://orcid.org/0000-0001-8362-4350","affiliations":[{"raw_affiliation_string":"Computer Science Department, Faculty of Science, South Valley University, Qena, Egypt svu.edu.eg","institution_ids":["https://openalex.org/I189575948"]},{"raw_affiliation_string":"Computer Science Department, Faculty of Science, South Valley University, Qena, Egypt","institution_ids":["https://openalex.org/I189575948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108016584","display_name":"Hager Saleh","orcid":"https://orcid.org/0000-0001-6184-7107","observed_orcids":["https://orcid.org/0000-0001-6184-7107"]},"institutions":[{"id":"https://openalex.org/I189575948","display_name":"South Valley University","ror":"https://ror.org/00jxshx33","country_code":"EG","type":"education","lineage":["https://openalex.org/I189575948"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Hager Saleh","raw_affiliation_strings":["Faculty of Computers and Information, South Valley University, Hurghada, Egypt svu.edu.eg","Faculty of Computers and Information, South Valley University, Hurghada, Egypt"],"raw_orcid":"https://orcid.org/0000-0001-6184-7107","affiliations":[{"raw_affiliation_string":"Faculty of Computers and Information, South Valley University, Hurghada, Egypt svu.edu.eg","institution_ids":["https://openalex.org/I189575948"]},{"raw_affiliation_string":"Faculty of Computers and Information, South Valley University, Hurghada, Egypt","institution_ids":["https://openalex.org/I189575948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000985477","display_name":"Ayman M. Nabil","orcid":"https://orcid.org/0000-0001-9575-6860","observed_orcids":["https://orcid.org/0000-0001-9575-6860"]},"institutions":[{"id":"https://openalex.org/I47853400","display_name":"Misr International University","ror":"https://ror.org/030vg1t69","country_code":"EG","type":"education","lineage":["https://openalex.org/I47853400"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ayman Nabil","raw_affiliation_strings":["Faculty of Computer Science, Misr International University, Cairo, Egypt miuegypt.edu.eg","Faculty of Computer Science, Misr International University, Cairo, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Misr International University, Cairo, Egypt miuegypt.edu.eg","institution_ids":["https://openalex.org/I47853400"]},{"raw_affiliation_string":"Faculty of Computer Science, Misr International University, Cairo, Egypt","institution_ids":["https://openalex.org/I47853400"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112616313"],"corresponding_institution_ids":["https://openalex.org/I189575948"],"apc_list":{"value":2760,"currency":"USD","value_usd":2760},"apc_paid":{"value":2760,"currency":"USD","value_usd":2760},"fwci":1.467,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81727502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"2021","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/breast-cancer-prediction","display_name":"breast cancer prediction","score":0.9800000190734863},{"id":"https://openalex.org/keywords/twitter","display_name":"Twitter","score":0.6069999933242798},{"id":"https://openalex.org/keywords/social-media-health-data","display_name":"social media health data","score":0.8700000047683716},{"id":"https://openalex.org/keywords/real-time-forecasting","display_name":"real-time prediction","score":0.7480000257492065},{"id":"https://openalex.org/keywords/apache-spark","display_name":"Apache Spark","score":0.6420000195503235},{"id":"https://openalex.org/keywords/apache-kafka","display_name":"Apache Kafka","score":0.9729999899864197},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.7710000276565552},{"id":"https://openalex.org/keywords/recursive-feature-elimination","display_name":"recursive feature elimination","score":0.9419999718666077},{"id":"https://openalex.org/keywords/univariate-feature-selection","display_name":"univariate feature selection","score":0.9580000042915344},{"id":"https://openalex.org/keywords/feature-correlation","display_name":"feature correlation","score":0.7839999794960022},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.8130000233650208}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8125407099723816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933196783065796},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6711822748184204},{"id":"https://openalex.org/C530470458","wikidata":"https://www.wikidata.org/wiki/Q128581","display_name":"Breast cancer","level":3,"score":0.4781704545021057},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.4764447808265686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40678074955940247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3632424771785736},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2241242527961731},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.15521231293678284},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09271296858787537},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1155/2021/6653508","doi":"https://doi.org/10.1155/2021/6653508","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6653508","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/6653508.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:hin:complx:6653508","doi":null,"is_oa":false,"landing_page_url":"http://downloads.hindawi.com/journals/complexity/2021/6653508.xml","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:baf5acba125248ec8cd18c9c8ae89e09","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/baf5acba125248ec8cd18c9c8ae89e09","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complexity, Vol 2021 (2021)","raw_type":"article"},{"id":"doi:10.60692/5h0zq-rz160","doi":"https://doi.org/10.60692/5h0zq-rz160","is_oa":true,"landing_page_url":"https://doi.org/10.60692/5h0zq-rz160","pdf_url":null,"source":{"id":"https://openalex.org/S7407051682","display_name":"Greater South Information System","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.60692/8k2pm-m6d75","doi":"https://doi.org/10.60692/8k2pm-m6d75","is_oa":true,"landing_page_url":"https://doi.org/10.60692/8k2pm-m6d75","pdf_url":null,"source":{"id":"https://openalex.org/S7407051682","display_name":"Greater South Information System","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1155/2021/6653508","doi":"https://doi.org/10.1155/2021/6653508","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6653508","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/6653508.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8560000061988831,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3123526537.pdf","grobid_xml":"https://content.openalex.org/works/W3123526537.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1518597757","https://openalex.org/W1692174238","https://openalex.org/W1894664571","https://openalex.org/W1906872188","https://openalex.org/W1983024255","https://openalex.org/W2004320486","https://openalex.org/W2069914810","https://openalex.org/W2089927030","https://openalex.org/W2124794572","https://openalex.org/W2125283600","https://openalex.org/W2125539227","https://openalex.org/W2128306614","https://openalex.org/W2143426320","https://openalex.org/W2144692687","https://openalex.org/W2153092104","https://openalex.org/W2158418996","https://openalex.org/W2324845196","https://openalex.org/W2331956941","https://openalex.org/W2370924594","https://openalex.org/W2436634098","https://openalex.org/W2471518212","https://openalex.org/W2595543006","https://openalex.org/W2768040494","https://openalex.org/W2804226884","https://openalex.org/W2895961568","https://openalex.org/W2901252034","https://openalex.org/W2910232415","https://openalex.org/W2953605441","https://openalex.org/W2978273980","https://openalex.org/W3004813073","https://openalex.org/W3014164107","https://openalex.org/W3019898597","https://openalex.org/W4240616498","https://openalex.org/W4299298161"],"related_works":["https://openalex.org/W4287592186","https://openalex.org/W3138996948","https://openalex.org/W4321494985","https://openalex.org/W3107655866","https://openalex.org/W2912068910","https://openalex.org/W3047321833","https://openalex.org/W2945994271","https://openalex.org/W4407901126","https://openalex.org/W2595543006","https://openalex.org/W3000237489"],"abstract_inverted_index":{"Twitter":[0,150],"integrates":[1],"with":[2,136,163],"streaming":[3,27],"data":[4,30],"technologies":[5],"and":[6,46,68,89,114,125,131,142,149],"machine":[7,137],"learning":[8,138],"to":[9,13,21,62,97,101,139,155],"add":[10],"new":[11],"value":[12],"healthcare.":[14],"This":[15],"paper":[16],"presented":[17],"a":[18,57],"real\u2010time":[19],"system":[20,35],"predict":[22],"breast":[23,173],"cancer":[24,174],"based":[25],"on":[26,121],"patient\u2019s":[28],"health":[29],"from":[31,74,168,178],"Twitter.":[32],"The":[33,160,181],"proposed":[34],"consists":[36],"of":[37,72],"two":[38],"major":[39],"components:":[40],"developing":[41],"an":[42,47],"offline":[43],"building":[44],"model":[45,162,187],"online":[48],"prediction":[49],"pipeline.":[50],"For":[51],"the":[52,60,64,70,75,103,157,164,169,185,189,195],"first":[53,170],"component,":[54],"we":[55],"made":[56],"correlation":[58,65,100,124],"between":[59,66],"features":[61,67,73,98,122],"determine":[63],"reduce":[69],"number":[71],"Breast":[76],"Cancer":[77],"Wisconsin":[78],"Diagnostic":[79],"dataset.":[80],"Two":[81],"feature":[82,87,91,126],"selection":[83,92],"algorithms":[84,93],"are":[85,95,153],"recursive":[86],"elimination":[88],"univariate":[90],"which":[94,193],"applied":[96,135],"after":[99,123],"select":[102],"essential":[104],"features.":[105],"Four":[106],"decision":[107],"trees,":[108],"logistic":[109],"regression,":[110],"support":[111],"vector":[112],"machine,":[113],"random":[115,190],"forest":[116,191],"classifier":[117,192],"have":[118,133],"been":[119,134],"used":[120,154],"selection.":[127],"Also,":[128],"hyperparameter":[129],"tuning":[130],"cross\u2010validation":[132],"optimize":[140],"models":[141],"enhance":[143],"accuracy.":[144,197],"Apache":[145,147],"Spark,":[146],"Kafka,":[148],"Streaming":[151],"API":[152],"develop":[156],"second":[158],"component.":[159],"best":[161,186,196],"highest":[165],"accuracy":[166],"obtained":[167],"component":[171],"predicts":[172],"in":[175],"real":[176],"time":[177],"tweets\u2019":[179],"streaming.":[180],"results":[182],"showed":[183],"that":[184],"is":[188],"achieved":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-02-01T00:00:00"}