{"id":"https://openalex.org/W2119411048","doi":"https://doi.org/10.1145/1273496.1273540","title":"Supervised clustering of streaming data for email batch detection","display_name":"Supervised clustering of streaming data for email batch detection","publication_year":2007,"publication_date":"2007-06-20","ids":{"openalex":"https://openalex.org/W2119411048","doi":"https://doi.org/10.1145/1273496.1273540","mag":"2119411048"},"language":"en","primary_location":{"id":"doi:10.1145/1273496.1273540","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1273496.1273540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th 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/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Peter Haider","raw_affiliation_strings":["Max Planck Institute for Computer Science, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Computer Science, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049583553","display_name":"Ulf Brefeld","orcid":"https://orcid.org/0000-0001-9600-6463"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulf Brefeld","raw_affiliation_strings":["Max Planck Institute for Computer Science, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Computer Science, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"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/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Scheffer","raw_affiliation_strings":["Max Planck Institute for Computer Science, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Computer Science, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070168211"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":5.7982,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95884762,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"345","last_page":"352"},"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9965999722480774,"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":0.84058678150177},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7918421626091003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7879222631454468},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5043362379074097},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4813431203365326},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.4404396414756775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38957738876342773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3727027177810669},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13083091378211975}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.84058678150177},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7918421626091003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879222631454468},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5043362379074097},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4813431203365326},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.4404396414756775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38957738876342773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3727027177810669},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13083091378211975},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1273496.1273540","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1273496.1273540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th international conference on Machine learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.323.6431","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.323.6431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://user.cs.tu-berlin.de/~brefeld/publications/clustering07.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.6618","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.6618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2007/papers/366.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:356412","is_oa":false,"landing_page_url":"http://edoc.mpg.de/356412","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ghahramani, Zoubin: ICML 2007 : proceedings of the Twenty-Fourth International Conference on Machine Learning, ACM, 345-352 (2007)","raw_type":"Conference-Paper"},{"id":"pmh:oai:pure.mpg.de:item_1328105","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-000F-20DF-D","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICML'07","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494372926","https://openalex.org/W1505906253","https://openalex.org/W1511938660","https://openalex.org/W1601412462","https://openalex.org/W2017732166","https://openalex.org/W2054638878","https://openalex.org/W2105644991","https://openalex.org/W2105842272","https://openalex.org/W2117154949","https://openalex.org/W2123297508","https://openalex.org/W2134089414","https://openalex.org/W2146081992","https://openalex.org/W2149029960","https://openalex.org/W2155421596","https://openalex.org/W2159583439","https://openalex.org/W2295665070","https://openalex.org/W3010318089","https://openalex.org/W6629691672","https://openalex.org/W6630268475","https://openalex.org/W6675760969"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W4302615923","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2017509870","https://openalex.org/W2542937328","https://openalex.org/W4251141768","https://openalex.org/W4360952157","https://openalex.org/W4220731478","https://openalex.org/W2069409835"],"abstract_inverted_index":{"We":[0,101,116],"address":[1],"the":[2,15,23,44,67,84,88,92,109,118,127],"problem":[3,19,45,94,112],"of":[4,7,37,47,52,69,87,113,120,123,129],"detecting":[5],"batches":[6,36,125],"emails":[8],"that":[9],"have":[10,78],"been":[11,79],"created":[12],"according":[13],"to":[14,25,83],"same":[16],"template.":[17],"This":[18],"is":[20],"motivated":[21],"by":[22,30],"desire":[24],"filter":[26],"spam":[27,131],"more":[28],"effectively":[29],"exploiting":[31],"collective":[32,121],"information":[33],"about":[34],"entire":[35],"jointly":[38],"generated":[39],"messages.":[40],"The":[41],"application":[42],"matches":[43],"setting":[46],"supervised":[48,62,114],"clustering,":[49],"because":[50],"examples":[51],"correct":[53],"clusterings":[54],"can":[55,95],"be":[56,74,96],"collected.":[57],"Known":[58],"decoding":[59,93,105],"procedures":[60],"for":[61],"clustering":[63],"are":[64],"cubic":[65],"in":[66,98],"number":[68],"instances.":[70],"When":[71],"decisions":[72],"cannot":[73],"reconsidered":[75],"once":[76],"they":[77],"made":[80],"---":[81,90],"owing":[82],"streaming":[85],"nature":[86],"data":[89],"then":[91],"solved":[97],"linear":[99],"time.":[100],"devise":[102],"a":[103],"sequential":[104],"procedure":[106],"and":[107],"derive":[108],"corresponding":[110],"optimization":[111],"clustering.":[115],"study":[117],"impact":[119],"attributes":[122],"email":[124],"on":[126],"effectiveness":[128],"recognizing":[130],"emails.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}