{"id":"https://openalex.org/W4391093487","doi":"https://doi.org/10.1109/bigdata59044.2023.10386224","title":"Sorting the Digital Stream: Big Data-driven Insights into Email Classification for Spam and Ham Detection","display_name":"Sorting the Digital Stream: Big Data-driven Insights into Email Classification for Spam and Ham Detection","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391093487","doi":"https://doi.org/10.1109/bigdata59044.2023.10386224"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386224","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","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/A5023820143","display_name":"Syed Attique Shah","orcid":"https://orcid.org/0000-0003-2949-7391"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Syed Attique Shah","raw_affiliation_strings":["Birmingham City University, STEAMhouse,School of Computing and Digital Technology,Birmingham,United Kingdom,B47RQ"],"affiliations":[{"raw_affiliation_string":"Birmingham City University, STEAMhouse,School of Computing and Digital Technology,Birmingham,United Kingdom,B47RQ","institution_ids":["https://openalex.org/I12870472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093759978","display_name":"Emil Anthony Arputham","orcid":null},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emil Anthony Arputham","raw_affiliation_strings":["Birmingham City University, STEAMhouse,School of Computing and Digital Technology,Birmingham,United Kingdom,B47RQ"],"affiliations":[{"raw_affiliation_string":"Birmingham City University, STEAMhouse,School of Computing and Digital Technology,Birmingham,United Kingdom,B47RQ","institution_ids":["https://openalex.org/I12870472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063377741","display_name":"Awais Ahmed","orcid":"https://orcid.org/0000-0003-4410-2028"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Awais Ahmed","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering,Sichuan,China","School of Computer Science and Engineering, University of Electronic Science and Technology of China, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,Sichuan,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061834318","display_name":"Mohamed Amine Ben Farah","orcid":"https://orcid.org/0000-0002-0135-9942"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mohamed Ben Farah","raw_affiliation_strings":["Birmingham City University, STEAMhouse,School of Computing and Digital Technology,Birmingham,United Kingdom,B47RQ"],"affiliations":[{"raw_affiliation_string":"Birmingham City University, STEAMhouse,School of Computing and Digital Technology,Birmingham,United Kingdom,B47RQ","institution_ids":["https://openalex.org/I12870472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114120405","display_name":"Attal Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I143719379","display_name":"Balochistan University of Information Technology, Engineering and Management Sciences","ror":"https://ror.org/01vf56d70","country_code":"PK","type":"education","lineage":["https://openalex.org/I143719379"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Attal Shah","raw_affiliation_strings":["Faculty of ICT BUITEMS,Department of Computer Engineering,Quetta,Pakistan","Department of Computer Engineering, Faculty of ICT BUITEMS, Quetta, Pakistan"],"affiliations":[{"raw_affiliation_string":"Faculty of ICT BUITEMS,Department of Computer Engineering,Quetta,Pakistan","institution_ids":["https://openalex.org/I143719379"]},{"raw_affiliation_string":"Department of Computer Engineering, Faculty of ICT BUITEMS, Quetta, Pakistan","institution_ids":["https://openalex.org/I143719379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107933177","display_name":"Abdul Aziz","orcid":"https://orcid.org/0000-0002-5190-251X"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Abdul Aziz","raw_affiliation_strings":["Universidad de Zaragoza,Aragon Institute of Engineering Research,Zaragoza,Spain,50018"],"affiliations":[{"raw_affiliation_string":"Universidad de Zaragoza,Aragon Institute of Engineering Research,Zaragoza,Spain,50018","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023820143"],"corresponding_institution_ids":["https://openalex.org/I12870472"],"apc_list":null,"apc_paid":null,"fwci":0.4589,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7347416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5598","last_page":"5607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9994000196456909,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.819163978099823},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6627050042152405},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6152792572975159},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6027150750160217},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5886930823326111},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.577448844909668},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5635161399841309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5166166424751282},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5022809505462646},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4910898208618164},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4575954079627991},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4539695382118225},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4288453161716461},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3329792022705078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819163978099823},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6627050042152405},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6152792572975159},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6027150750160217},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5886930823326111},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.577448844909668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5635161399841309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5166166424751282},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5022809505462646},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4910898208618164},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4575954079627991},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4539695382118225},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4288453161716461},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3329792022705078},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386224","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","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":29,"referenced_works":["https://openalex.org/W2063252718","https://openalex.org/W2089352795","https://openalex.org/W2804836751","https://openalex.org/W2806937061","https://openalex.org/W2921150469","https://openalex.org/W2949836779","https://openalex.org/W2981842822","https://openalex.org/W2990198263","https://openalex.org/W2996806689","https://openalex.org/W3006834142","https://openalex.org/W3012363350","https://openalex.org/W3022513095","https://openalex.org/W3027143485","https://openalex.org/W3041162515","https://openalex.org/W3042598118","https://openalex.org/W3057377271","https://openalex.org/W3080622597","https://openalex.org/W3093781078","https://openalex.org/W3112863598","https://openalex.org/W3165340574","https://openalex.org/W3169737192","https://openalex.org/W3184796286","https://openalex.org/W3206830253","https://openalex.org/W3213407977","https://openalex.org/W4213081600","https://openalex.org/W4229053699","https://openalex.org/W4280649903","https://openalex.org/W4281654741","https://openalex.org/W4377691173"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"In":[0],"contemporary":[1],"email":[2,114,157,172,199],"communication,":[3],"the":[4,25,43,51,61,95,98,111,122,130,141,148,154,163,169,178,193,202],"ever-":[5],"expanding":[6],"volume":[7],"of":[8,27,39,48,79,97,100,113,124,143,156,171,195,204],"digital":[9],"correspondence":[10],"has":[11],"ushered":[12],"in":[13,23,109,168],"an":[14],"era":[15],"where":[16],"big":[17,205],"data":[18,64,206],"plays":[19],"a":[20],"pivotal":[21],"role":[22],"addressing":[24],"challenge":[26],"distinguishing":[28],"between":[29,53],"legitimate":[30],"(ham)":[31],"and":[32,46,55,106],"unsolicited":[33],"(spam)":[34],"emails.":[35,57],"The":[36,116],"primary":[37],"objective":[38],"this":[40,92,160],"paper":[41],"is":[42,94],"meticulous":[44],"identification":[45],"establishment":[47],"criteria":[49],"for":[50,86,197],"discrimination":[52],"ham":[54],"spam":[56,88],"To":[58],"achieve":[59],"this,":[60],"study":[62,179],"harnesses":[63],"from":[65],"three":[66],"distinct":[67],"datasets,":[68,149],"aiming":[69],"to":[70,91,119,147,152,192],"identify":[71],"common":[72],"attributes":[73],"shared":[74],"across":[75],"all":[76,150],"emails,":[77],"irrespective":[78],"their":[80],"classification,":[81],"while":[82],"concurrently":[83],"devising":[84],"methodologies":[85],"precise":[87],"detection.":[89],"Central":[90],"endeavor":[93],"evaluation":[96,165,186],"effectiveness":[99],"feature":[101,126],"selection":[102,127],"techniques,":[103],"specifically":[104],"Chi-Square":[105],"Pearson":[107],"Correlation,":[108],"elevating":[110],"accuracy":[112],"classification.":[115,158],"investigation":[117],"extends":[118],"assessing":[120],"how":[121],"combination":[123],"these":[125],"techniques":[128,146,196],"with":[129],"broader":[131],"machine":[132],"learning":[133],"framework":[134],"can":[135],"be":[136],"optimized.":[137],"This":[138,188],"optimization":[139],"entails":[140],"application":[142],"diverse":[144],"preprocessing":[145],"designed":[151],"amplify":[153],"precision":[155],"Furthermore,":[159],"research":[161],"scrutinizes":[162],"performance":[164],"metrics":[166],"employed":[167],"assessment":[170],"classifiers.":[173],"By":[174],"conducting":[175],"comprehensive":[176],"experiments,":[177],"identifies":[180],"optimal":[181],"classifiers":[182],"based":[183],"on":[184],"rigorous":[185],"metrics.":[187],"contributes":[189],"valuable":[190],"insights":[191],"toolkit":[194],"proficient":[198],"classification":[200],"within":[201],"realm":[203],"analysis.":[207]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}