{"id":"https://openalex.org/W4387847740","doi":"https://doi.org/10.1145/3583780.3615462","title":"Content-Based Email Classification at Scale","display_name":"Content-Based Email Classification at Scale","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387847740","doi":"https://doi.org/10.1145/3583780.3615462"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615462","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3583780.3615462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","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/A5027325691","display_name":"Kirstin Early","orcid":"https://orcid.org/0000-0002-1627-0094"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kirstin Early","raw_affiliation_strings":["Yahoo Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061972189","display_name":"Neil O\u2019Hare","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil O'Hare","raw_affiliation_strings":["Yahoo Research, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044096493","display_name":"Christopher C. LuVogt","orcid":"https://orcid.org/0009-0002-2567-1305"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Luvogt","raw_affiliation_strings":["Yahoo Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027325691"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23676145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"4559","last_page":"4566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9975000023841858,"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":0.8270026445388794},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6516798734664917},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6451330184936523},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49436163902282715},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.43726634979248047},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4170762300491333},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4040085971355438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.386464923620224},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37222549319267273},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3202322721481323},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.286155641078949},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10599294304847717},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08274787664413452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270026445388794},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6516798734664917},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6451330184936523},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49436163902282715},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.43726634979248047},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4170762300491333},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4040085971355438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.386464923620224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37222549319267273},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3202322721481323},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.286155641078949},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10599294304847717},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08274787664413452},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3615462","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3583780.3615462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2059014657","https://openalex.org/W2255862008","https://openalex.org/W2294370754","https://openalex.org/W2474838075","https://openalex.org/W2493916176","https://openalex.org/W2595551253","https://openalex.org/W2620998106","https://openalex.org/W2739879705","https://openalex.org/W2798599891","https://openalex.org/W2952230191","https://openalex.org/W2962784628","https://openalex.org/W2963626623","https://openalex.org/W2995837271","https://openalex.org/W2999905431","https://openalex.org/W3034368386","https://openalex.org/W3034457371","https://openalex.org/W3035690777","https://openalex.org/W3105966348","https://openalex.org/W3138154797","https://openalex.org/W3177378457","https://openalex.org/W4229643319","https://openalex.org/W4283793248","https://openalex.org/W4290944172","https://openalex.org/W4385245566","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411"],"abstract_inverted_index":{"Understanding":[0],"the":[1,51,79,128,132],"content":[2],"of":[3,56,81,107,127,131,142,154],"email":[4,17,34],"messages":[5,42],"can":[6,64],"enable":[7],"new":[8],"features":[9,160],"that":[10,49,115,161],"highlight":[11],"what":[12],"matters":[13],"to":[14,24,36,40,44,76,110,125,145],"users,":[15],"making":[16],"a":[18,32,45,84,91,104],"more":[19],"useful":[20],"tool":[21],"for":[22,68,118],"people":[23,163],"manage":[25],"their":[26,165],"lives.":[27],"We":[28],"present":[29],"work":[30],"from":[31,96],"consumer":[33],"platform":[35],"build":[37,90],"multilabel":[38],"models":[39,63,72,114,122,151],"classify":[41,152],"according":[43],"mail-specific,":[46],"content-based":[47],"taxonomy":[48],"represents":[50],"topic,":[52],"type,":[53],"and":[54,101,158],"objective":[55],"an":[57],"email.":[58,82],"While":[59],"state-of-the-art":[60],"Transformer-based":[61],"language":[62],"achieve":[65],"impressive":[66],"results":[67],"text":[69],"classification,":[70],"these":[71,150],"are":[73,116],"too":[74],"costly":[75],"deploy":[77],"at":[78],"scale":[80],"Using":[83],"knowledge":[85],"distillation":[86],"framework,":[87],"we":[88],"first":[89],"complex,":[92],"accurate":[93],"teacher":[94,133],"model":[95,134],"limited":[97],"human-labeled":[98],"training":[99],"data":[100,109],"then":[102],"use":[103],"large":[105],"amount":[106],"teacher-labeled":[108],"train":[111],"lightweight":[112],"student":[113,121],"suitable":[117],"deployment.":[119],"The":[120],"retain":[123],"up":[124],"91%":[126],"predictive":[129],"performance":[130],"while":[135],"reducing":[136],"inference":[137],"cost":[138],"by":[139],"three":[140],"orders":[141],"magnitude.":[143],"Deployed":[144],"production":[146],"in":[147],"Yahoo":[148],"Mail,":[149],"billions":[153],"emails":[155],"every":[156],"day":[157],"power":[159],"help":[162],"tackle":[164],"inboxes.":[166]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}