{"id":"https://openalex.org/W2157936684","doi":"https://doi.org/10.1109/cidm.2013.6597240","title":"E-mail address categorization based on semantics of surnames","display_name":"E-mail address categorization based on semantics of surnames","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2157936684","doi":"https://doi.org/10.1109/cidm.2013.6597240","mag":"2157936684"},"language":"en","primary_location":{"id":"doi:10.1109/cidm.2013.6597240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cidm.2013.6597240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)","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/A5103585909","display_name":"Suresh Veluru","orcid":null},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Suresh Veluru","raw_affiliation_strings":["Information Security Group, School of Engineering and Mathematical Sciences, City University London, London, UK"],"affiliations":[{"raw_affiliation_string":"Information Security Group, School of Engineering and Mathematical Sciences, City University London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021724967","display_name":"Yogachandran Rahulamathavan","orcid":"https://orcid.org/0000-0002-1722-8621"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yogachandran Rahulamathavan","raw_affiliation_strings":["Information Security Group, School of Engineering and Mathematical Sciences, City University London, London, UK"],"affiliations":[{"raw_affiliation_string":"Information Security Group, School of Engineering and Mathematical Sciences, City University London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789705","display_name":"P. Viswanath","orcid":"https://orcid.org/0000-0001-5953-6246"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. Viswanath","raw_affiliation_strings":["Department of CSE, R.G.M.C.E.T, Nandyal, Andhra Pradesh, India"],"affiliations":[{"raw_affiliation_string":"Department of CSE, R.G.M.C.E.T, Nandyal, Andhra Pradesh, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089476688","display_name":"Paul Longley","orcid":"https://orcid.org/0000-0002-4727-6384"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul Longley","raw_affiliation_strings":["Department of Geography, University College London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Geography, University College London, London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059640195","display_name":"Muttukrishnan Rajarajan","orcid":"https://orcid.org/0000-0001-5814-9922"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Muttukrishnan Rajarajan","raw_affiliation_strings":["Information Security Group, School of Engineering and Mathematical Sciences, City University London, London, UK"],"affiliations":[{"raw_affiliation_string":"Information Security Group, School of Engineering and Mathematical Sciences, City University London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103585909"],"corresponding_institution_ids":["https://openalex.org/I180825142"],"apc_list":null,"apc_paid":null,"fwci":1.9775,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89142543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"222","last_page":"229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9882000088691711,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9882000088691711,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9663000106811523,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9643999934196472,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.7478940486907959},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6728315353393555},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6389776468276978},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6036972999572754},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48880669474601746},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4851556420326233},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4575132727622986},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.435427188873291},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4070781171321869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36853086948394775},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34123897552490234},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1705167591571808},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10941323637962341}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7478940486907959},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6728315353393555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6389776468276978},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6036972999572754},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48880669474601746},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4851556420326233},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4575132727622986},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.435427188873291},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4070781171321869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36853086948394775},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34123897552490234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1705167591571808},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10941323637962341},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cidm.2013.6597240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cidm.2013.6597240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)","raw_type":"proceedings-article"},{"id":"pmh:oai:openaccess.city.ac.uk:2913","is_oa":false,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/suresh=2Eveluru=2E1.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1423836","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1423836/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"   2013 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DATA MINING (CIDM)     pp. 222-229.   (2013)      ","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7900000214576721,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W1982026570","https://openalex.org/W1992419399","https://openalex.org/W2006439594","https://openalex.org/W2007452682","https://openalex.org/W2020258599","https://openalex.org/W2045812729","https://openalex.org/W2046369891","https://openalex.org/W2072671633","https://openalex.org/W2080695900","https://openalex.org/W2090971815","https://openalex.org/W2108886327","https://openalex.org/W2118020653","https://openalex.org/W2158997610","https://openalex.org/W2480436008","https://openalex.org/W6652315468"],"related_works":["https://openalex.org/W1583922594","https://openalex.org/W1542422837","https://openalex.org/W1974038726","https://openalex.org/W2998448420","https://openalex.org/W1598224733","https://openalex.org/W4280502676","https://openalex.org/W2000769876","https://openalex.org/W2112822946","https://openalex.org/W204227468","https://openalex.org/W2023946029"],"abstract_inverted_index":{"Surname":[0],"(family":[1],"name)":[2],"analysis":[3,109],"is":[4,79,86,104,110,113,127,144,147],"used":[5,35],"in":[6,39,52,88,137,149,170],"geography":[7],"to":[8,36,131],"understand":[9],"population":[10],"origins,":[11],"migration,":[12],"identity,":[13],"social":[14],"norms":[15],"and":[16,97,172],"cultural":[17],"customs.":[18],"Some":[19],"of":[20,47,77,82,133],"these":[21,183],"are":[22],"supposedly":[23],"evolved":[24],"over":[25],"generations.":[26],"Surnames":[27],"exhibit":[28],"good":[29],"statistical":[30],"properties":[31],"that":[32,181],"can":[33],"be":[34,66],"extract":[37],"information":[38],"names":[40],"data":[41,157],"set":[42],"such":[43],"as":[44,60,129,185],"automatic":[45],"detection":[46],"ethnic":[48],"or":[49,68],"community":[50],"groups":[51],"names.":[53],"An":[54,70],"e-mail":[55,71,179],"address,":[56],"often":[57],"contains":[58],"surname":[59,95],"a":[61,100],"substring.":[62],"This":[63,85],"containment":[64],"may":[65],"full":[67],"partial.":[69],"address":[72],"categorization":[73],"based":[74],"on":[75],"semantics":[76],"surnames":[78,169,184],"the":[80,116,122,134,164,178],"objective":[81],"this":[83],"paper.":[84],"achieved":[87],"two":[89],"phases.":[90],"First":[91],"phase":[92],"deals":[93],"with":[94],"representation":[96],"clustering.":[98],"Here,":[99],"vector":[101],"space":[102],"model":[103],"proposed":[105],"where":[106],"latent":[107],"semantic":[108],"performed.":[111],"Clustering":[112],"done":[114,148],"using":[115,154],"method":[117],"called":[118],"average-linkage":[119],"method.":[120],"In":[121],"second":[123],"phase,":[124],"an":[125,150],"email":[126],"categorized":[128],"belonging":[130],"one":[132],"categories":[135],"(discovered":[136],"first":[138],"phase).":[139],"For":[140],"this,":[141],"substring":[142],"matching":[143],"required,":[145],"which":[146],"efficient":[151],"way":[152],"by":[153],"suffix":[155],"tree":[156],"structure.":[158],"We":[159],"perform":[160],"experimental":[161],"evaluation":[162],"for":[163],"500":[165],"most":[166],"frequently":[167],"occurring":[168],"India":[171],"United":[173],"Kingdom.":[174],"Also,":[175],"we":[176],"categorize":[177],"addresses":[180],"have":[182],"substrings.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}