{"id":"https://openalex.org/W4410601184","doi":"https://doi.org/10.1186/s40537-025-01176-9","title":"BERT-GraphSAGE: hybrid approach to spam detection","display_name":"BERT-GraphSAGE: hybrid approach to spam detection","publication_year":2025,"publication_date":"2025-05-22","ids":{"openalex":"https://openalex.org/W4410601184","doi":"https://doi.org/10.1186/s40537-025-01176-9"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-025-01176-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01176-9","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01176-9","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01176-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117636864","display_name":"F. Zouak","orcid":null},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"F. Zouak","raw_affiliation_strings":["LISAC Laboratory, Faculty of Sciences Dhar El Mahraz, University Sidi Mohamed Ben Abdellah, 30000, Fez, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISAC Laboratory, Faculty of Sciences Dhar El Mahraz, University Sidi Mohamed Ben Abdellah, 30000, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048317087","display_name":"Omar El Beqqali","orcid":"https://orcid.org/0000-0003-0269-3819"},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"O. El Beqqali","raw_affiliation_strings":["LISAC Laboratory, Faculty of Sciences Dhar El Mahraz, University Sidi Mohamed Ben Abdellah, 30000, Fez, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISAC Laboratory, Faculty of Sciences Dhar El Mahraz, University Sidi Mohamed Ben Abdellah, 30000, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090906662","display_name":"Jamal Riffi","orcid":null},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"J. Riffi","raw_affiliation_strings":["LISAC Laboratory, Faculty of Sciences Dhar El Mahraz, University Sidi Mohamed Ben Abdellah, 30000, Fez, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISAC Laboratory, Faculty of Sciences Dhar El Mahraz, University Sidi Mohamed Ben Abdellah, 30000, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I81605866"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":13.4119,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98465855,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"12","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998000264167786,"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":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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":0.8301310539245605},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.7330793142318726},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.22301921248435974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301310539245605},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.7330793142318726},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.22301921248435974}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-025-01176-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01176-9","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01176-9","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5751dc205f4c460faf2d01c67ac7b418","is_oa":true,"landing_page_url":"https://doaj.org/article/5751dc205f4c460faf2d01c67ac7b418","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,"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":"Journal of Big Data, Vol 12, Iss 1, Pp 1-14 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-025-01176-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01176-9","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01176-9","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410601184.pdf","grobid_xml":"https://content.openalex.org/works/W4410601184.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2099606292","https://openalex.org/W2792555552","https://openalex.org/W2970398671","https://openalex.org/W2979826702","https://openalex.org/W3041998802","https://openalex.org/W3042788417","https://openalex.org/W3076947077","https://openalex.org/W3119513105","https://openalex.org/W3123084617","https://openalex.org/W3161935901","https://openalex.org/W3173753074","https://openalex.org/W4205143667","https://openalex.org/W4206833365","https://openalex.org/W4226327328","https://openalex.org/W4281787892","https://openalex.org/W4294558607","https://openalex.org/W4318719277","https://openalex.org/W4392756413"],"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":{"Even":[0],"after":[1],"the":[2,19,27,119,130,147,172,231],"advent":[3],"of":[4,21,29,46,53,121,132,149,157,174,233],"various":[5],"communication":[6],"networks,":[7],"emails":[8,56,74,167,176],"have":[9,67],"retained":[10],"their":[11,63],"importance":[12],"and":[13,37,48,107,170,192,200,209,214,219,241],"serious,":[14],"professional":[15],"character.":[16],"Moreover,":[17],"as":[18,72],"number":[20,28],"Internet":[22],"users":[23],"increases,":[24],"so":[25],"does":[26],"spam":[30,55,97,240],"emails.":[31,243],"Spam":[32],"refers":[33],"to":[34,42,61,95,117,163,165,177],"any":[35],"unsolicited":[36],"unwanted":[38],"communication,":[39],"which":[40,124,143],"leads":[41],"a":[43,122],"significant":[44],"waste":[45],"resources":[47],"overloads":[49],"networks.":[50],"The":[51,109],"majority":[52],"these":[54],"come":[57],"from":[58,105],"advertisers":[59],"wishing":[60],"promote":[62],"products,":[64],"while":[65],"others":[66],"more":[68],"malicious":[69],"intentions,":[70],"such":[71],"phishing":[73],"aimed":[75],"at":[76],"tricking":[77],"recipients":[78],"into":[79],"providing":[80],"confidential":[81],"information":[82],"like":[83],"website":[84],"credentials":[85],"or":[86],"credit":[87],"card":[88],"details.":[89],"In":[90],"our":[91,234],"research,":[92],"we":[93],"aim":[94],"improve":[96],"detection":[98],"by":[99,113,141,168],"combining":[100],"BERT":[101,114],"(Bidirectional":[102],"Encoder":[103],"Representations":[104],"Transformers)":[106],"GraphSAGE.":[108],"embedding":[110,150,158],"vectors":[111],"generated":[112],"are":[115,125],"used":[116],"represent":[118],"nodes":[120],"graph,":[123],"then":[126],"linked":[127],"based":[128],"on":[129,186,203,212,222],"calculation":[131],"cosine":[133],"similarity.":[134],"This":[135,160],"graph":[136],"structure":[137],"is":[138],"subsequently":[139],"exploited":[140],"GraphSAGE,":[142],"doesn\u2019t":[144],"merely":[145],"record":[146],"results":[148,229],"mapping;":[151],"it":[152],"learns":[153],"an":[154],"inductive":[155],"method":[156],"generation.":[159],"enables":[161],"GraphSAGE":[162],"generalize":[164],"unseen":[166],"sampling":[169],"aggregating":[171],"characteristics":[173],"neighboring":[175],"produce":[178],"robust":[179],"node":[180],"representations.":[181],"Our":[182],"model":[183],"was":[184],"evaluated":[185],"three":[187],"benchmark":[188],"datasets:":[189],"ENRON,":[190,204],"SpamAssassin,":[191,213],"LingSpam.":[193],"It":[194],"achieved":[195],"98.87%":[196],"accuracy,":[197,206,216],"99.81%":[198],"precision,":[199,208,218],"99.98%":[201],"AUC":[202,211,221],"96.44%":[205],"94.43%":[207],"98.86%":[210],"99.20%":[215],"96.98%":[217],"99.55%":[220],"LingSpam,":[223],"outperforming":[224],"several":[225],"state-of-the-art":[226],"baselines.":[227],"These":[228],"confirm":[230],"robustness":[232],"approach":[235],"in":[236],"accurately":[237],"distinguishing":[238],"between":[239],"legitimate":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}