{"id":"https://openalex.org/W4413679724","doi":"https://doi.org/10.1109/csr64739.2025.11130032","title":"Reducing Human-Induced Label Bias in SMS Spam with Context-Enhanced Clustering (CEC)","display_name":"Reducing Human-Induced Label Bias in SMS Spam with Context-Enhanced Clustering (CEC)","publication_year":2025,"publication_date":"2025-08-04","ids":{"openalex":"https://openalex.org/W4413679724","doi":"https://doi.org/10.1109/csr64739.2025.11130032"},"language":"en","primary_location":{"id":"doi:10.1109/csr64739.2025.11130032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csr64739.2025.11130032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cyber Security and Resilience (CSR)","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/A5061123061","display_name":"Gerard Shu Fuhnwi","orcid":null},"institutions":[{"id":"https://openalex.org/I23732399","display_name":"Montana State University","ror":"https://ror.org/02w0trx84","country_code":"US","type":"education","lineage":["https://openalex.org/I23732399","https://openalex.org/I4210126032"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gerard Shu Fuhnwi","raw_affiliation_strings":["Montana State University,Bozeman,MT,USA"],"affiliations":[{"raw_affiliation_string":"Montana State University,Bozeman,MT,USA","institution_ids":["https://openalex.org/I23732399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008975618","display_name":"Ann Marie Reinhold","orcid":"https://orcid.org/0000-0003-0411-3486"},"institutions":[{"id":"https://openalex.org/I23732399","display_name":"Montana State University","ror":"https://ror.org/02w0trx84","country_code":"US","type":"education","lineage":["https://openalex.org/I23732399","https://openalex.org/I4210126032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ann Marie Reinhold","raw_affiliation_strings":["Montana State University,Bozeman,MT,USA"],"affiliations":[{"raw_affiliation_string":"Montana State University,Bozeman,MT,USA","institution_ids":["https://openalex.org/I23732399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041998052","display_name":"Clemente Izurieta","orcid":"https://orcid.org/0000-0002-1002-3906"},"institutions":[{"id":"https://openalex.org/I23732399","display_name":"Montana State University","ror":"https://ror.org/02w0trx84","country_code":"US","type":"education","lineage":["https://openalex.org/I23732399","https://openalex.org/I4210126032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clemente Izurieta","raw_affiliation_strings":["Montana State University,Bozeman,MT,USA"],"affiliations":[{"raw_affiliation_string":"Montana State University,Bozeman,MT,USA","institution_ids":["https://openalex.org/I23732399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061123061"],"corresponding_institution_ids":["https://openalex.org/I23732399"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37944445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9980999827384949,"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":0.9980999827384949,"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/T13155","display_name":"Digital Communication and Language","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9753000140190125,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7705988883972168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.738871157169342},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6574325561523438},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37477216124534607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31212425231933594}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7705988883972168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738871157169342},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6574325561523438},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37477216124534607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31212425231933594},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/csr64739.2025.11130032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csr64739.2025.11130032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cyber Security and Resilience (CSR)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Short":[0],"Message":[1],"Service":[2],"(SMS)":[3],"is":[4],"a":[5,21,86,166,173,193,206],"widely":[6],"used":[7,182],"text":[8],"messaging":[9],"feature":[10],"available":[11],"on":[12,38],"both":[13],"basic":[14],"and":[15,52,101,141,156,172,205],"smartphones,":[16],"making":[17],"SMS":[18,114,130],"spam":[19,115,144],"detection":[20],"critical":[22],"task.":[23],"Supervised":[24],"machine":[25],"learning":[26],"approaches":[27],"often":[28],"face":[29],"challenges":[30,94],"in":[31,49,158],"this":[32],"domain":[33],"due":[34],"to":[35,76,91,132,183,187],"their":[36],"dependence":[37],"manually":[39],"crafted":[40],"features,":[41],"such":[42,135,152],"as":[43,136,153,161],"keyword":[44],"detection,":[45],"which":[46],"can":[47,61],"result":[48],"simplistic":[50],"patterns":[51],"misclassification":[53],"of":[54,79,143,169,178,196,202,211],"more":[55],"complex":[56],"messages.":[57],"Furthermore,":[58],"these":[59,93],"models":[60],"exacerbate":[62],"human-induced":[63,217],"bias":[64,218],"if":[65],"the":[66,112,129,139,190],"training":[67],"data":[68],"include":[69],"inconsistent":[70],"labeling":[71],"or":[72,82],"subjective":[73],"interpretations,":[74],"leading":[75],"unfair":[77],"treatment":[78,174,207],"specific":[80],"keywords":[81],"contexts.":[83],"We":[84,107],"propose":[85],"Context-Enhanced":[87],"Clustering":[88],"(CEC)":[89],"approach":[90,110,147],"address":[92],"by":[95],"leveraging":[96],"contextual":[97],"metadata,":[98],"adaptive":[99],"thresholding,":[100],"modified":[102],"similarity":[103],"measures":[104],"for":[105],"clustering.":[106],"evaluate":[108],"our":[109],"using":[111],"English":[113],"dataset":[116,131],"source":[117],"from":[118,128],"UC":[119],"Irvine\u2019s":[120],"Machine":[121],"Learning":[122],"Repository.":[123],"CEC":[124,191],"identifies":[125],"representative":[126,185],"samples":[127,186],"fine-tune":[133,188],"LLMs":[134],"ChatGPT-4,":[137,189],"improving":[138],"robustness":[140],"fairness":[142],"classification.":[145],"Our":[146],"outperforms":[148],"traditional":[149],"clustering":[150],"techniques":[151],"K":[154],"-means":[155],"DBSCAN":[157],"mitigating":[159],"bias,":[160],"demonstrated":[162],"through":[163],"experiments":[164],"measuring":[165],"balanced":[167,194],"accuracy":[168,195],"$85":[170],"\\%$":[171],"equality":[175,208],"difference":[176,203,209],"(TED)":[177,210],"precisely":[179],"zero.":[180,212],"When":[181],"identify":[184],"achieves":[192],"$98":[197],"\\%$,":[198],"an":[199],"equal":[200],"opportunity":[201],"(EOD),":[204],"These":[213],"results":[214],"significantly":[215],"reduce":[216],"while":[219],"maintaining":[220],"high":[221],"classification":[222],"accuracy.":[223]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}