{"id":"https://openalex.org/W1262284422","doi":"https://doi.org/10.1177/0165551515587854","title":"Email thread identification using latent Dirichlet allocation and non-negative matrix factorization based clustering techniques","display_name":"Email thread identification using latent Dirichlet allocation and non-negative matrix factorization based clustering techniques","publication_year":2015,"publication_date":"2015-07-03","ids":{"openalex":"https://openalex.org/W1262284422","doi":"https://doi.org/10.1177/0165551515587854","mag":"1262284422"},"language":"en","primary_location":{"id":"doi:10.1177/0165551515587854","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551515587854","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-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/A5006285552","display_name":"Aakanksha Sharaff","orcid":"https://orcid.org/0000-0001-5499-7289"},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aakanksha Sharaff","raw_affiliation_strings":["Department of Computer Science & Engineering, National Institute of Technology, India","[Department of Computer Science & Engineering, National Institute of Technology, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, National Institute of Technology, India","institution_ids":["https://openalex.org/I91277730"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, National Institute of Technology, India]","institution_ids":["https://openalex.org/I91277730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007549080","display_name":"Naresh Kumar Nagwani","orcid":"https://orcid.org/0000-0001-5306-5818"},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Naresh Kumar Nagwani","raw_affiliation_strings":["Department of Computer Science & Engineering, National Institute of Technology, India","[Department of Computer Science & Engineering, National Institute of Technology, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, National Institute of Technology, India","institution_ids":["https://openalex.org/I91277730"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, National Institute of Technology, India]","institution_ids":["https://openalex.org/I91277730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006285552"],"corresponding_institution_ids":["https://openalex.org/I91277730"],"apc_list":null,"apc_paid":null,"fwci":3.297,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.92595929,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"42","issue":"2","first_page":"200","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","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/T11644","display_name":"Spam and Phishing Detection","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9944999814033508,"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/T12607","display_name":"Personal Information Management and User Behavior","score":0.9918000102043152,"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":0.8392813205718994},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.723260223865509},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6872234344482422},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6437469124794006},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4468826949596405},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4280869960784912},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3721684515476227},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3351653218269348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26402729749679565},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.25008466839790344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392813205718994},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.723260223865509},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6872234344482422},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6437469124794006},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4468826949596405},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4280869960784912},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3721684515476227},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3351653218269348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26402729749679565},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.25008466839790344},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0165551515587854","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551515587854","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1541437296","https://openalex.org/W1543320899","https://openalex.org/W1554540371","https://openalex.org/W1603920809","https://openalex.org/W1880262756","https://openalex.org/W1886082488","https://openalex.org/W1902027874","https://openalex.org/W1976975519","https://openalex.org/W1986920245","https://openalex.org/W2000573164","https://openalex.org/W2010405649","https://openalex.org/W2013029404","https://openalex.org/W2026551498","https://openalex.org/W2038705803","https://openalex.org/W2057171495","https://openalex.org/W2061989622","https://openalex.org/W2087382273","https://openalex.org/W2101890001","https://openalex.org/W2107669799","https://openalex.org/W2110746712","https://openalex.org/W2113063049","https://openalex.org/W2113359929","https://openalex.org/W2125441830","https://openalex.org/W2131237666","https://openalex.org/W2155802749","https://openalex.org/W2294110724","https://openalex.org/W2399815506","https://openalex.org/W2541288413","https://openalex.org/W4206262194","https://openalex.org/W4255867791","https://openalex.org/W4297970707"],"related_works":["https://openalex.org/W3107650560","https://openalex.org/W3126382579","https://openalex.org/W4317422773","https://openalex.org/W4315588616","https://openalex.org/W2810542905","https://openalex.org/W4243064001","https://openalex.org/W2129350855","https://openalex.org/W3123667230","https://openalex.org/W2888805565","https://openalex.org/W3096554474"],"abstract_inverted_index":{"Emails":[0],"are":[1,17,45,117,142,183],"the":[2,11,127,145,150,155,163,169,186],"most":[3],"popular":[4,34,131],"and":[5,22,42,58,94,138,181],"effective":[6],"way":[7],"of":[8,15,40,82,88,98],"communicating":[9],"over":[10,144,162],"internet.":[12],"A":[13],"number":[14,97],"applications":[16],"available":[18],"today":[19],"for":[20,25,52,84,185],"computers":[21],"mobile":[23],"devices":[24],"email":[26,106,146,151,165,170],"messaging.":[27],"Email":[28,70],"messaging":[29],"is":[30,49,121,159],"constantly":[31],"getting":[32],"more":[33],"and,":[35],"as":[36],"a":[37,53,73,77,85,91,96,112],"result,":[38],"numbers":[39],"sent":[41],"received":[43],"emails":[44,57,62,83],"also":[46],"increasing.":[47],"It":[48],"very":[50],"difficult":[51],"user":[54,78],"to":[55,63,100,148,167],"remember":[56],"relate":[59],"newer":[60],"incoming":[61],"previous":[64],"communications":[65],"made":[66],"on":[67,111],"similar":[68],"topics.":[69],"threads":[71,171],"provide":[72],"mechanism":[74],"using":[75,172],"which":[76],"can":[79],"obtain":[80],"sequences":[81],"particular":[86],"set":[87],"communication":[89],"in":[90,123,126,154],"time":[92],"frame":[93],"provides":[95],"benefits":[99],"users.":[101],"In":[102],"this":[103],"work":[104,120],"two":[105,124,130],"thread":[107,188],"identification":[108,189],"algorithms":[109],"based":[110],"nested":[113],"textual":[114],"clustering":[115,133,158],"approach":[116],"presented.":[118],"The":[119],"planned":[122],"stages;":[125],"first":[128],"stage":[129],"text":[132],"approaches,":[134],"latent":[135],"Dirichlet":[136],"allocation":[137],"non-negative":[139],"matrix":[140],"factorization,":[141],"applied":[143],"messages":[147],"form":[149],"clusters.":[152],"Then":[153],"second":[156],"stage,":[157],"again":[160],"performed":[161],"created":[164],"clusters":[166],"identify":[168],"threading":[173],"features.":[174],"Performance":[175],"parameters":[176],"like":[177],"accuracy,":[178],"precision,":[179],"recall":[180],"F-measure":[182],"evaluated":[184],"presented":[187],"algorithms.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}