{"id":"https://openalex.org/W4393560753","doi":"https://doi.org/10.5281/zenodo.6509751","title":"A Dataset of over 500.000 commercial email newsletters, as collected by PrivacyMail.info","display_name":"A Dataset of over 500.000 commercial email newsletters, as collected by PrivacyMail.info","publication_year":2022,"publication_date":"2022-06-12","ids":{"openalex":"https://openalex.org/W4393560753","doi":"https://doi.org/10.5281/zenodo.6509751"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.6509751","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.6509751","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":null,"license_id":null,"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.6509751","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018539996","display_name":"Max Maa\u00df","orcid":"https://orcid.org/0000-0001-9346-8486"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Maass, Max","raw_affiliation_strings":["Secure Mobile Networking Lab, TU Darmstadt"],"affiliations":[{"raw_affiliation_string":"Secure Mobile Networking Lab, TU Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073377080","display_name":"Stephan Schw\u00e4r","orcid":"https://orcid.org/0000-0002-9728-3937"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Schw\u00e4r, Stephan","raw_affiliation_strings":["Secure Mobile Networking Lab, TU Darmstadt"],"affiliations":[{"raw_affiliation_string":"Secure Mobile Networking Lab, TU Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042405070","display_name":"Matthias Hollick","orcid":"https://orcid.org/0000-0002-9163-5989"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hollick, Matthias","raw_affiliation_strings":["Secure Mobile Networking Lab, TU Darmstadt"],"affiliations":[{"raw_affiliation_string":"Secure Mobile Networking Lab, TU Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018539996"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"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":{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9929999709129333,"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"}},"topics":[{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9929999709129333,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9799000024795532,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9616000056266785,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4925266206264496},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.46055710315704346},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4559415578842163},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.374243825674057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4925266206264496},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.46055710315704346},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4559415578842163},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.374243825674057}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.6509751","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.6509751","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.6509751","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.6509751","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"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/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"This":[0,164],"dataset":[1,74,112,165,275],"contains":[2,20,93],"the":[3,35,89,118,124,126,157,177,208,214,227,261,270],"data":[4,209,263],"from":[5,281],"roughly":[6],"two":[7],"years":[8],"of":[9,30,78,146,152,176],"operating":[10],"PrivacyMail.info,":[11],"an":[12],"Open":[13],"Source":[14],"Email":[15],"privacy":[16],"measurement":[17],"platform.":[18],"It":[19],"slightly":[21],"over":[22],"500.000":[23],"commercial":[24],"newsletters,":[25],"as":[26,115],"crowdsourced":[27,71],"by":[28,183],"users":[29],"PrivacyMail.info.":[31,222],"You":[32],"can":[33,60],"find":[34],"methodology":[36],"discussed":[37],"in":[38,50,185,276],"our":[39],"paper:":[40],"Max":[41],"Maass,":[42],"Stephan":[43],"Schw\u00e4r,":[44],"and":[45,91,162,204,240,273],"Matthias":[46],"Hollick.":[47],"\"Towards":[48],"transparency":[49],"email":[51,159,178],"tracking.\"":[52],"Annual":[53],"Privacy":[54],"Forum,":[55],"2019.":[56],"The":[57,111,174],"source":[58],"code":[59],"be":[61,106],"found":[62],"on":[63,88,96,210,254],"github.com/privacymail/privacymail":[64],"Please":[65,257],"note":[66],"that,":[67],"due":[68,170],"to":[69,168,171,206,226,236],"its":[70],"nature,":[72],"this":[73,255,274],"is":[75,82,113,166,202],"a":[76,150,211],"sample":[77],"opportunity":[79],"-":[80,197],"it":[81,98,201],"not":[83,249,259],"representative":[84],"for":[85,135,141,193],"all":[86],"newsletters":[87,103],"Internet,":[90],"likely":[92,105],"biases":[94],"based":[95],"how":[97],"was":[99,139],"collected.":[100],"Notably,":[101],"German-language":[102],"will":[104,242],"heavily":[107],"over-represented.":[108],"<strong>Dataset":[109],"Structure</strong><br>":[110],"structured":[114],"follows:":[116],"On":[117],"top":[119],"level":[120],"are":[121,133,149,180],"folders":[122,148],"describing":[123],"website":[125],"newsletter":[127],"belongs":[128],"to.":[129],"Inside":[130,144],"that":[131,138,142,155,267,279],"folder":[132],"subfolders":[134],"each":[136,145],"identity":[137],"registered":[140],"website.":[143],"these":[147],"series":[151],".eml":[153],"files":[154],"represent":[156],"received":[158],"messages.":[160],"<strong>Copyright":[161],"Licensing</strong><br>":[163],"set":[167],"non-public":[169],"copyright":[172,184,189],"concerns:":[173],"contents":[175],"messages":[179],"(presumably)":[181],"protected":[182],"most":[186],"jurisdictions.":[187],"Most":[188],"doctrines":[190],"contain":[191],"exceptions":[192],"non-commercial":[194],"research":[195,233],"use":[196],"thus,":[198],"we":[199,217,241],"feel":[200],"appropriate":[203],"acceptable":[205],"share":[207,260],"case-by-case":[212],"basis,":[213],"same":[215],"way":[216],"did":[218],"before":[219],"shutting":[220],"down":[221],"When":[223],"requesting":[224],"access":[225],"data,":[228],"please":[229],"briefly":[230],"describe":[231],"what":[232],"you":[234,244,268],"want":[235],"conduct":[237],"with":[238],"it,":[239],"grant":[243],"access.":[245],"We":[246,265],"thus":[247],"do":[248,258],"put":[250],"any":[251,277],"explicit":[252],"license":[253],"dataset.":[256],"raw":[262],"publicly.":[264],"request":[266],"cite":[269],"above-mentioned":[271],"paper":[272],"publications":[278],"result":[280],"it.":[282]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}