{"id":"https://openalex.org/W2131076952","doi":"https://doi.org/10.1145/1553374.1553424","title":"Bayesian clustering for email campaign detection","display_name":"Bayesian clustering for email campaign detection","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2131076952","doi":"https://doi.org/10.1145/1553374.1553424","mag":"2131076952"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","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/A5070168211","display_name":"Peter Haider","orcid":null},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Peter Haider","raw_affiliation_strings":["University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007427935","display_name":"Tobias Scheffer","orcid":"https://orcid.org/0000-0003-4405-7925"},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Scheffer","raw_affiliation_strings":["University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070168211"],"corresponding_institution_ids":["https://openalex.org/I176453806"],"apc_list":null,"apc_paid":null,"fwci":3.8815,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9462343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9979000091552734,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7439940571784973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7282512187957764},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6083202958106995},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5214385390281677},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5172634720802307},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5025167465209961},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4956401586532593},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4826717674732208},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.449840784072876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31995582580566406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17656853795051575}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7439940571784973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282512187957764},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6083202958106995},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5214385390281677},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5172634720802307},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5025167465209961},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4956401586532593},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4826717674732208},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.449840784072876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31995582580566406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17656853795051575},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1553374.1553424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.5234","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.5234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~icml2009/papers/328.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.8771","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.8771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uni-potsdam.de/ml/publications/icml2009.pdf","raw_type":"text"},{"id":"pmh:oai:kobv.de-opus4-uni-potsdam:30444","is_oa":false,"landing_page_url":"https://publishup.uni-potsdam.de/frontdoor/index/index/docId/30444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400594","display_name":"publish.UP (University of Potsdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176453806","host_organization_name":"University of Potsdam","host_organization_lineage":["https://openalex.org/I176453806"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1551066950","https://openalex.org/W2066076115","https://openalex.org/W2111574971","https://openalex.org/W2119411048","https://openalex.org/W2128999403","https://openalex.org/W2142992973","https://openalex.org/W2160157087","https://openalex.org/W6680744341"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2158836806","https://openalex.org/W2393816671","https://openalex.org/W2083665254","https://openalex.org/W2942177010"],"abstract_inverted_index":{"We":[0,29,55,127],"discuss":[1],"the":[2,9,34,46,72,79,88,112],"problem":[3,59,83],"of":[4,36,45,51,67,90,103,111],"clustering":[5,135],"elements":[6,16,110],"according":[7],"to":[8,106],"sources":[10],"that":[11,17,39,60,132],"have":[12],"generated":[13],"them.":[14],"For":[15],"are":[18],"characterized":[19],"by":[20,87],"independent":[21,52,68],"binary":[22,69],"attributes,":[23],"a":[24,31,43,49,62,65,100,129],"closed-form":[25],"Bayesian":[26,134],"solution":[27,32],"exists.":[28],"derive":[30,56],"for":[33,93,136],"case":[35,130],"dependent":[37],"attributes":[38],"is":[40,85],"based":[41],"on":[42],"transformation":[44],"instances":[47],"into":[48,64],"space":[50,66],"feature":[53,70],"functions.":[54],"an":[57],"optimization":[58],"produces":[61],"mapping":[63],"vectors;":[71],"features":[73],"can":[74,115,124],"reflect":[75],"arbitrary":[76],"dependencies":[77],"in":[78],"input":[80],"space.":[81],"This":[82],"setting":[84],"motivated":[86],"application":[89],"spam":[91,120],"filtering":[92],"email":[94],"service":[95],"providers.":[96],"Spam":[97],"traps":[98],"deliver":[99],"real-time":[101],"stream":[102],"messages":[104],"known":[105],"be":[107,116,125],"spam.":[108],"If":[109],"same":[113],"campaign":[114],"recognized":[117],"reliably,":[118],"entire":[119],"and":[121],"phishing":[122],"campaigns":[123],"contained.":[126],"present":[128],"study":[131],"evaluates":[133],"this":[137],"application.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}