{"id":"https://openalex.org/W2255862008","doi":"https://doi.org/10.1145/2835776.2835780","title":"Hierarchical Label Propagation and Discovery for Machine Generated Email","display_name":"Hierarchical Label Propagation and Discovery for Machine Generated Email","publication_year":2016,"publication_date":"2016-02-04","ids":{"openalex":"https://openalex.org/W2255862008","doi":"https://doi.org/10.1145/2835776.2835780","mag":"2255862008"},"language":"en","primary_location":{"id":"doi:10.1145/2835776.2835780","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2835776.2835780","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2835776.2835780","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2835776.2835780","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060825780","display_name":"James B. Wendt","orcid":"https://orcid.org/0000-0003-4980-5152"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"James B. Wendt","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032248436","display_name":"Michael Bendersky","orcid":"https://orcid.org/0000-0002-2941-6240"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Bendersky","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014833056","display_name":"Llu\u00eds Garcia-Pueyo","orcid":"https://orcid.org/0000-0002-3278-2997"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lluis Garcia-Pueyo","raw_affiliation_strings":["Google, Inc., Mountani View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountani View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037908462","display_name":"Vanja Josifovski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vanja Josifovski","raw_affiliation_strings":["Pinterest, Inc., San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Pinterest, Inc., San Francisco, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076271495","display_name":"Mikl\u00f3s B\u00e1lint","orcid":"https://orcid.org/0000-0003-0499-8536"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Balint Miklos","raw_affiliation_strings":["Google, Inc., Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051716545","display_name":"Ivo Krka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ivo Krka","raw_affiliation_strings":["Google, Inc., Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037325864","display_name":"Amitabh Saikia","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amitabh Saikia","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384175","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0002-5019-6393"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Yang","raw_affiliation_strings":["Google, Inc., Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050568895","display_name":"Marc-Allen Cartright","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc-Allen Cartright","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104067009","display_name":"Sujith Ravi","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sujith Ravi","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5060825780"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":12.9284,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.98507178,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"317","last_page":"326"},"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":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"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":0.8260889649391174},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.6617156267166138},{"id":"https://openalex.org/keywords/affinity-propagation","display_name":"Affinity propagation","score":0.5293486714363098},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5286175608634949},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5004212856292725},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.49223271012306213},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.48834893107414246},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48724809288978577},{"id":"https://openalex.org/keywords/template-matching","display_name":"Template matching","score":0.4793694317340851},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4420648515224457},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4355728030204773},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4044831097126007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36409899592399597},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3546912670135498},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.19875475764274597},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.14276766777038574},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.11050951480865479},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10215213894844055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260889649391174},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.6617156267166138},{"id":"https://openalex.org/C109659709","wikidata":"https://www.wikidata.org/wiki/Q3407504","display_name":"Affinity propagation","level":5,"score":0.5293486714363098},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5286175608634949},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5004212856292725},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.49223271012306213},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.48834893107414246},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48724809288978577},{"id":"https://openalex.org/C158096908","wikidata":"https://www.wikidata.org/wiki/Q3983303","display_name":"Template matching","level":3,"score":0.4793694317340851},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4420648515224457},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4355728030204773},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4044831097126007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36409899592399597},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3546912670135498},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19875475764274597},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.14276766777038574},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.11050951480865479},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10215213894844055},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2835776.2835780","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2835776.2835780","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2835776.2835780","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2835776.2835780","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2835776.2835780","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2835776.2835780","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2255862008.pdf","grobid_xml":"https://content.openalex.org/works/W2255862008.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1544537492","https://openalex.org/W1553019137","https://openalex.org/W1630959083","https://openalex.org/W1880262756","https://openalex.org/W1974922810","https://openalex.org/W1995395515","https://openalex.org/W2007652426","https://openalex.org/W2037096232","https://openalex.org/W2050042708","https://openalex.org/W2051461667","https://openalex.org/W2052742498","https://openalex.org/W2085302848","https://openalex.org/W2098034778","https://openalex.org/W2114748216","https://openalex.org/W2134004204","https://openalex.org/W2149604555","https://openalex.org/W2150721933","https://openalex.org/W2154455818","https://openalex.org/W2157638128","https://openalex.org/W2166490929","https://openalex.org/W2166706824","https://openalex.org/W2474838075","https://openalex.org/W2901597048","https://openalex.org/W3103973800","https://openalex.org/W3105187107","https://openalex.org/W3151142710","https://openalex.org/W4250803253","https://openalex.org/W6682494755","https://openalex.org/W6755634636","https://openalex.org/W6793870845"],"related_works":["https://openalex.org/W1966431033","https://openalex.org/W4237492828","https://openalex.org/W4362587931","https://openalex.org/W78181647","https://openalex.org/W2130194910","https://openalex.org/W2189374779","https://openalex.org/W2605148547","https://openalex.org/W2016788389","https://openalex.org/W2551770406","https://openalex.org/W1978021877"],"abstract_inverted_index":{"Machine-generated":[0],"documents":[1,95],"such":[2,60],"as":[3,23,61],"email":[4,157],"or":[5,136],"dynamic":[6],"web":[7],"pages":[8],"are":[9,124],"single":[10,75],"instantiations":[11],"of":[12,26,149,189],"a":[13,24,74,128,154],"pre-defined":[14],"structural":[15],"template.":[16,99],"As":[17],"such,":[18],"they":[19,88],"can":[20,89],"be":[21],"viewed":[22],"hierarchy":[25],"template":[27,34,65,76,129,164,199],"and":[28,43,114,119,139,159,175,183,207],"document":[29,41,71,108,173,192],"specific":[30],"content.":[31],"This":[32],"hierarchical":[33,116,177],"representation":[35],"has":[36],"several":[37],"important":[38],"advantages":[39,106],"for":[40,107],"clustering":[42],"classification.":[44],"First,":[45],"templates":[46,82],"capture":[47],"common":[48],"topics":[49],"among":[50],"the":[51,56,94,98,142,147,150,162,171,176,187,190,198,212],"documents,":[52,87],"while":[53,210],"filtering":[54],"out":[55],"potentially":[57],"noisy":[58],"variabilities":[59],"personal":[62],"information.":[63],"Second,":[64],"representations":[66,72],"scale":[67],"far":[68],"better":[69],"than":[70,170,204,217],"since":[73,81],"captures":[77],"numerous":[78],"documents.":[79,144],"Finally,":[80],"group":[83],"together":[84],"structurally":[85],"similar":[86],"propagate":[90],"properties":[91],"between":[92],"all":[93],"that":[96,161,197],"match":[97],"In":[100],"this":[101],"paper,":[102],"we":[103],"use":[104],"these":[105],"classification":[109,193],"by":[110,215],"formulating":[111],"an":[112],"efficient":[113,182],"effective":[115,184],"label":[117,178,200,213],"propagation":[118,179,201],"discovery":[120],"algorithm.":[121,194],"The":[122],"labels":[123],"propagated":[125],"first":[126],"over":[127],"graph":[130,165,174],"(constructed":[131],"based":[132],"on":[133],"either":[134],"term-based":[135],"topic-based":[137],"similarities),":[138],"then":[140],"to":[141],"matching":[143],"We":[145,195],"evaluate":[146],"performance":[148],"proposed":[151],"algorithm":[152],"using":[153],"large":[155],"donated":[156],"corpus":[158],"show":[160],"resulting":[163],"is":[166,180],"significantly":[167],"more":[168,203,216],"compact":[169],"corresponding":[172],"both":[181],"in":[185],"increasing":[186,211],"coverage":[188,214],"baseline":[191],"demonstrate":[196],"achieves":[202],"91%":[205],"precision":[206],"93%":[208],"recall,":[209],"11%.":[218]},"counts_by_year":[{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}