{"id":"https://openalex.org/W2109932952","doi":"https://doi.org/10.1145/1081870.1081926","title":"Email data cleaning","display_name":"Email data cleaning","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2109932952","doi":"https://doi.org/10.1145/1081870.1081926","mag":"2109932952"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081926","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044791875","display_name":"Jie Tang","orcid":"https://orcid.org/0000-0003-3487-4593"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Tang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455129","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-1230-4007"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Li","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011542448","display_name":"Yunbo Cao","orcid":"https://orcid.org/0009-0005-2558-5206"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Cao","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101410185","display_name":"Zhaohui Tang","orcid":"https://orcid.org/0000-0003-4415-7707"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaohui Tang","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2515,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.95176849,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"489","last_page":"498"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12607","display_name":"Personal Information Management and User Behavior","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.566058337688446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.566058337688446}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1081870.1081926","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.387.1550","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.387.1550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/class/fa05/cs591han/kdd05/docs/p489.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.408.6244","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.408.6244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.uab.edu/zhang/Spam-mining-papers/Email.Data.Cleaning.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"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":33,"referenced_works":["https://openalex.org/W617751628","https://openalex.org/W1490831147","https://openalex.org/W1519468639","https://openalex.org/W1528056001","https://openalex.org/W1610496399","https://openalex.org/W1612155886","https://openalex.org/W1632767318","https://openalex.org/W1934019294","https://openalex.org/W1974358129","https://openalex.org/W1988217119","https://openalex.org/W1989338554","https://openalex.org/W1994485670","https://openalex.org/W2008652694","https://openalex.org/W2016871293","https://openalex.org/W2018616927","https://openalex.org/W2019264297","https://openalex.org/W2026669942","https://openalex.org/W2034797903","https://openalex.org/W2057900969","https://openalex.org/W2096175520","https://openalex.org/W2119821739","https://openalex.org/W2124436456","https://openalex.org/W2127767383","https://openalex.org/W2127973959","https://openalex.org/W2129311323","https://openalex.org/W2134164043","https://openalex.org/W2147880316","https://openalex.org/W2154292298","https://openalex.org/W2156909104","https://openalex.org/W2164107060","https://openalex.org/W2295081780","https://openalex.org/W2884262036","https://openalex.org/W6654761134"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Addressed":[0],"in":[1,68,122,167,171],"this":[2,84,100,168],"paper":[3],"is":[4,26,32,80,88,115],"the":[5,46,57,60,69,78,153,156,172,181,189,213,224],"issue":[6,79],"of":[7,48,59,93,158,215],"\u2018email":[8],"data":[9,25,225],"cleaning":[10,43,63,87,103,226],"\u2019":[11],"for":[12,151,192],"text":[13,16,97,109,206],"mining.":[14,38],"Many":[15],"mining":[17,110,207],"applications":[18],"need":[19],"take":[20],"emails":[21],"as":[22,90,137],"input.":[23],"Email":[24],"usually":[27],"noisy":[28],"and":[29,74,96,132,142],"thus":[30,81],"it":[31,36],"necessary":[33],"to":[34,201],"clean":[35],"before":[37],"Several":[39],"products":[40],"offer":[41],"email":[42,62,86,102,121,193],"features,":[44],"however,":[45],"types":[47],"noises":[49],"that":[50,180,212],"can":[51,186,218],"be":[52,219],"eliminated":[53],"are":[54],"restricted.":[55],"Despite":[56],"importance":[58],"problem,":[61],"has":[64,198],"received":[65],"little":[66],"attention":[67],"research":[70],"community.":[71],"A":[72,112],"thorough":[73],"systematic":[75],"investigation":[76],"on":[77,155],"needed.":[82],"In":[83,99],"paper,":[85],"formalized":[89],"a":[91,204],"problem":[92],"non-text":[94,126,140],"filtering":[95,141],"normalization.":[98,134],"way,":[101],"becomes":[104],"independent":[105],"from":[106],"any":[107],"specific":[108],"processing.":[111,208],"cascaded":[113],"approach":[114],"proposed,":[116],"which":[117],"cleans":[118],"up":[119],"an":[120],"four":[123],"passes":[124],"including":[125],"filtering,":[127],"paragraph":[128,143],"normalization,":[129,131],"sentence":[130],"word":[133],"As":[135],"far":[136],"we":[138],"know,":[139],"normalization":[144],"have":[145,163,174],"not":[146],"been":[147,165,175,199],"investigated":[148],"previously.":[149],"Methods":[150],"performing":[152],"tasks":[154],"basis":[157],"Support":[159],"Vector":[160],"Machines":[161],"(SVM)":[162],"also":[164],"proposed":[166,182,196],"paper.":[169],"Features":[170],"models":[173],"defined.":[176],"Experimental":[177,209],"results":[178,210],"indicate":[179],"SVM":[183],"based":[184],"methods":[185,191],"significantly":[187,220],"outperform":[188],"baseline":[190],"cleaning.":[194],"The":[195],"method":[197],"applied":[200],"term":[202,216],"extraction,":[203],"typical":[205],"show":[211],"accuracy":[214],"extraction":[217],"improved":[221],"by":[222],"using":[223],"method.":[227]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}