{"id":"https://openalex.org/W7117932815","doi":"https://doi.org/10.5281/zenodo.17985618","title":"SendGuard900K: Massive Dataset for Metadata-Based Quality Assurance of Email Marketing","display_name":"SendGuard900K: Massive Dataset for Metadata-Based Quality Assurance of Email Marketing","publication_year":2025,"publication_date":"2025-12-19","ids":{"openalex":"https://openalex.org/W7117932815","doi":"https://doi.org/10.5281/zenodo.17985618"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17985618","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17985618","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17985618","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009252880","display_name":"Szymon Bobek","orcid":"https://orcid.org/0000-0002-6350-8405"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Bobek, Szymon","raw_affiliation_strings":["Jagiellonian University"],"raw_orcid":"https://orcid.org/0000-0002-6350-8405","affiliations":[{"raw_affiliation_string":"Jagiellonian University","institution_ids":["https://openalex.org/I126596746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023890658","display_name":"Grzegorz J. Nalepa","orcid":"https://orcid.org/0000-0002-8182-4225"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Nalepa, Grzegorz J.","raw_affiliation_strings":["Jagiellonian University"],"raw_orcid":"https://orcid.org/0000-0002-8182-4225","affiliations":[{"raw_affiliation_string":"Jagiellonian University","institution_ids":["https://openalex.org/I126596746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069697183","display_name":"Sebastian Obara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Obara, Sebastian","raw_affiliation_strings":["Freshmail"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freshmail","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000658149","display_name":"Piotr Suszalski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suszalski, Piotr","raw_affiliation_strings":["Freshmail"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freshmail","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120388144","display_name":"\u0141ukasz Ba\u0142ec","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ba\u0142ec, \u0141ukasz","raw_affiliation_strings":["Freshmail"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freshmail","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7440999746322632},{"id":"https://openalex.org/keywords/quality-assurance","display_name":"Quality assurance","score":0.43799999356269836},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4343000054359436},{"id":"https://openalex.org/keywords/database-marketing","display_name":"Database marketing","score":0.4092999994754791},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.366100013256073},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3596999943256378},{"id":"https://openalex.org/keywords/transactional-leadership","display_name":"Transactional leadership","score":0.3440999984741211},{"id":"https://openalex.org/keywords/direct-marketing","display_name":"Direct marketing","score":0.3357999920845032}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7440999746322632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593999862670898},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4690999984741211},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.43799999356269836},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C2779879191","wikidata":"https://www.wikidata.org/wiki/Q1924293","display_name":"Database marketing","level":4,"score":0.4092999994754791},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.366100013256073},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C68489960","wikidata":"https://www.wikidata.org/wiki/Q2370659","display_name":"Transactional leadership","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C536005652","wikidata":"https://www.wikidata.org/wiki/Q677073","display_name":"Direct marketing","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C98495876","wikidata":"https://www.wikidata.org/wiki/Q1323528","display_name":"Digital marketing","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C127722929","wikidata":"https://www.wikidata.org/wiki/Q7833714","display_name":"Transaction data","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C48891531","wikidata":"https://www.wikidata.org/wiki/Q1141436","display_name":"Marketing research","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2212953","wikidata":"https://www.wikidata.org/wiki/Q948454","display_name":"Transaction log","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C2983355114","wikidata":"https://www.wikidata.org/wiki/Q161380","display_name":"Credit card","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C10511746","wikidata":"https://www.wikidata.org/wiki/Q899388","display_name":"Data security","level":3,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17985618","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17985618","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17985618","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17985618","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2198321825","display_name":null,"funder_award_id":"POIR.01.01.01-00-0202/19-02","funder_id":"https://openalex.org/F4320335039","funder_display_name":"Narodowe Centrum Bada\u0144 i Rozwoju"}],"funders":[{"id":"https://openalex.org/F4320335039","display_name":"Narodowe Centrum Bada\u0144 i Rozwoju","ror":"https://ror.org/05pwfyy15"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"SendGuard900K:":[0],"Massive":[1],"Dataset":[2],"for":[3,107,228],"Metadata-Based":[4],"Quality":[5],"Assurance":[6],"of":[7,22,39,53,80,118,165,218,231,256,277,321],"Email":[8],"Marketing":[9,44],"This":[10,197],"work":[11],"was":[12],"supported":[13],"in":[14,43,124,136,211,252],"part":[15],"by":[16,140,161,271,309],"the":[17,20,37,51,94,119,212,223,229,253,310,318,330],"Project":[18,59],"\u2018\u2018SendGuard\u2014Improving":[19],"Security":[21],"Recipients":[23],"Innovative":[24],"Tool":[25],"Based":[26],"on":[27,73,181],"Machine":[28],"Learning":[29],"Technology":[30],"and":[31,41,45,77,86,111,143,156,171,186,248,317,324,336,376],"Artificial":[32],"Intelligence":[33],"to":[34,70,100,177],"Fight":[35],"with":[36],"Problem":[38],"Spam":[40,375],"Phishing":[42,360],"Transactional":[46],"E-Mail":[47],"Messages\"":[48],"co-financed":[49],"from":[50,93,151,222],"Funds":[52],"European":[54],"Regional":[55],"Development":[56],"Fund":[57],"under":[58],"POIR.01.01.01-00-0202/19-02.":[60],"Overview":[61],"We":[62],"introduce":[63],"SendGuard900K,":[64],"a":[65,102,162,272],"large-scale":[66],"real-world":[67],"dataset":[68,91,174,198],"designed":[69,176],"support":[71],"research":[72,180,306],"quality":[74],"assurance,":[75],"security,":[76],"performance":[78],"analysis":[79],"email":[81,109,182,266],"marketing":[82,110],"campaigns":[83,159,267],"using":[84],"metadata":[85,149],"aggregated":[87],"behavioral":[88],"signals.":[89],"The":[90,114,173,205,238,300],"originates":[92],"SendGuard":[95],"project,":[96],"whose":[97],"goal":[98],"is":[99,175,250],"develop":[101],"significantly":[103],"improved":[104],"AI-driven":[105],"service":[106],"analyzing":[108],"transactional":[112],"messages.":[113],"project":[115],"addresses":[116],"one":[117],"most":[120],"pressing":[121],"global":[122],"challenges":[123],"digital":[125],"communication:":[126],"ensuring":[127],"that":[128],"legitimate,":[129],"personalized":[130],"messages":[131],"reach":[132],"their":[133],"recipients":[134],"effectively":[135],"an":[137],"ecosystem":[138],"dominated":[139],"spam,":[141],"phishing,":[142],"abuse.":[144],"SendGuard900K":[145],"contains":[146],"rich":[147],"campaign-level":[148],"collected":[150],"production":[152],"systems":[153],"between":[154],"2022":[155],"2024,":[157],"spanning":[158],"created":[160],"large":[163,273],"number":[164,274],"independent":[166,278],"companies":[167,279],"across":[168],"multiple":[169],"industries":[170],"geographies.":[172],"enable":[178],"reproducible":[179],"quality,":[183],"deliverability,":[184],"engagement,":[185],"abuse":[187],"detection\u2014without":[188],"exposing":[189],"message":[190,292],"content":[191],"or":[192,341,349,365,381],"personally":[193],"identifiable":[194],"information.":[195],"Files":[196],"includes":[199],"two":[200],"CSV":[201],"files:":[202],"SendGuard900K.csv":[203],"\u2014":[204,215],"main":[206,224],"file":[207],"containing":[208],"all":[209],"records":[210,296],"dataset.":[213],"SendGuard900K-preview.csv":[214],"A":[216],"sample":[217],"100":[219],"rows":[220],"extracted":[221],"file,":[225],"provided":[226],"solely":[227],"purpose":[230],"enabling":[232],"Zenodo\u2019s":[233],"preview":[234],"functionality.":[235],"Data":[236,280],"summary":[237],"detail":[239],"technical":[240],"info":[241],"about":[242],"data":[243],"including":[244],"columns":[245],"names,":[246],"types":[247],"inteprpretation":[249],"given":[251],"Technical":[254],"Notes":[255],"this":[257],"record.":[258],"Time":[259],"period:":[260],"2022\u20132024":[261],"Granularity:":[262],"Campaign-level":[263],"Scale:":[264],"~900,000":[265],"Creators:":[268],"Campaigns":[269],"generated":[270],"(over":[275],"4000)":[276],"types:":[281],"Integer":[282],"metrics,":[283],"categorical":[284],"descriptors,":[285],"timestamps":[286],"Privacy:":[287],"No":[288],"personal":[289],"data,":[290],"no":[291,294],"bodies,":[293],"recipient-level":[295],"Potential":[297],"Research":[298],"Use-cases":[299],"following":[301],"examples":[302],"illustrate":[303],"some":[304],"potential":[305],"directions":[307],"enabled":[308],"dataset;":[311],"however,":[312],"they":[313],"are":[314],"not":[315],"exhaustive,":[316],"actual":[319],"scope":[320],"possible":[322],"analyses":[323],"applications":[325],"can":[326],"easily":[327],"extend":[328],"beyond":[329],"cases":[331],"listed":[332],"below.":[333],"1.":[334],"Deliverability":[335],"Engagement":[337],"Prediction":[338],"Task:":[339,363,379],"Regression":[340],"classificationPotential":[342,383],"targets:":[343,369,384],"campaign_unique_opens_count":[344],"campaign_unique_clicks_count":[345],"derived":[346],"open":[347],"rate":[348,351],"click-through":[350],"time-windowed":[352],"engagement":[353],"metrics":[354],"(e.g.":[355],"_30,":[356],"_60,":[357],"_1440)":[358],"2.":[359],"Risk":[361],"Modeling":[362],"Classification":[364],"risk":[366],"scoring":[367],"(regression)Potential":[368],"campaign_phishing_count":[370,388],"campaign_complaint_count":[371,387],"campaign_moderation":[372,385],"campaign_moderation_rejected_count":[373,386],"3.":[374],"Abuse":[377],"Detection":[378],"Binary":[380],"multiclass":[382]},"counts_by_year":[],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2026-01-01T00:00:00"}
