{"id":"https://openalex.org/W2113063049","doi":"https://doi.org/10.1145/1148170.1148180","title":"Thread detection in dynamic text message streams","display_name":"Thread detection in dynamic text message streams","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2113063049","doi":"https://doi.org/10.1145/1148170.1148180","mag":"2113063049"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5105366551","display_name":"Dou Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Dou Shen","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636286","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0001-5059-8360"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102139311","display_name":"Jian-Tao Sun","orcid":null},"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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Jian-Tao Sun","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P.R.China","[Microsoft Research Asia, Beijing, P.R. China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088372348","display_name":"Zheng Chen","orcid":"https://orcid.org/0000-0003-4013-3492"},"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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Zheng Chen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P.R.China","[Microsoft Research Asia, Beijing, P.R. China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5105366551"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":7.3876,"has_fulltext":false,"cited_by_count":119,"citation_normalized_percentile":{"value":0.96592197,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9973999857902527,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9973000288009644,"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":0.874936580657959},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6595338582992554},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6544999480247498},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.47749564051628113},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.46375396847724915},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45395344495773315},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.4466170370578766},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4430614709854126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3478434085845947},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14588478207588196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.874936580657959},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6595338582992554},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6544999480247498},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.47749564051628113},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.46375396847724915},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45395344495773315},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.4466170370578766},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4430614709854126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3478434085845947},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14588478207588196},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1148170.1148180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-30584","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-30584","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1557925196","https://openalex.org/W1651093245","https://openalex.org/W1833785989","https://openalex.org/W1888178673","https://openalex.org/W1971817345","https://openalex.org/W1991695254","https://openalex.org/W1998224037","https://openalex.org/W2028757787","https://openalex.org/W2063657079","https://openalex.org/W2078693345","https://openalex.org/W2120022849","https://openalex.org/W2136987143","https://openalex.org/W2151734548","https://openalex.org/W2169279737","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4389449520","https://openalex.org/W127192698","https://openalex.org/W2570600173","https://openalex.org/W2893008024","https://openalex.org/W2743735673","https://openalex.org/W4361801939","https://openalex.org/W2360131081","https://openalex.org/W2985941356","https://openalex.org/W2802243998","https://openalex.org/W1521014365"],"abstract_inverted_index":{"Text":[0],"message":[1],"stream":[2,38],"is":[3,12,28,124],"a":[4,87,106,147],"newly":[5],"emerging":[6],"type":[7],"of":[8,20,69,90,105,157,195],"Web":[9],"data":[10,71],"which":[11,73],"produced":[13],"in":[14,35,72,115,193],"enormous":[15],"quantities":[16],"with":[17,142,183],"the":[18,32,36,67,70,74,91,112,116,130,158,162,174,184,189],"popularity":[19],"Instant":[21],"Messaging":[22],"and":[23,47,80,95,179,188],"Internet":[24],"Relay":[25],"Chat.":[26],"It":[27],"beneficial":[29],"for":[30,39,110],"detecting":[31],"threads":[33],"contained":[34],"text":[37],"various":[40],"applications,":[41],"including":[42],"information":[43,114],"retrieval,":[44],"expert":[45],"recognition":[46],"even":[48],"crime":[49],"prevention.":[50],"Despite":[51],"its":[52],"importance,":[53],"not":[54],"much":[55],"research":[56],"has":[57],"been":[58],"conducted":[59,135],"so":[60],"far":[61],"on":[62,121,146,170],"this":[63,83],"problem":[64],"due":[65],"to":[66,99,128,138],"characteristics":[68],"messages":[75],"are":[76],"usually":[77],"very":[78],"short":[79],"incomplete.":[81],"In":[82],"paper,":[84],"we":[85],"present":[86],"stringent":[88],"definition":[89],"thread":[92],"detection":[93],"task":[94],"our":[96,140],"preliminary":[97],"solution":[98],"it.":[100],"We":[101,134],"propose":[102],"three":[103,155],"variations":[104,156],"single-pass":[107,159,164,186],"clustering":[108],"algorithm":[109,119,160,168,187,192],"exploiting":[111],"temporal":[113],"streams.":[117],"An":[118],"based":[120,169],"linguistic":[122,171],"features":[123,172],"also":[125],"put":[126],"forward":[127],"exploit":[129],"discourse":[131],"structure":[132],"information.":[133],"several":[136],"experiments":[137],"compare":[139],"approaches":[141],"some":[143],"existing":[144],"algorithms":[145],"real":[148],"dataset.":[149],"The":[150],"results":[151],"show":[152],"that":[153],"all":[154],"outperform":[161],"basic":[163,185],"algorithm.":[165],"Our":[166],"proposed":[167],"improves":[173],"performance":[175],"relatively":[176],"by":[177],"69.5%":[178],"9.7%":[180],"when":[181],"compared":[182],"best":[190],"variation":[191],"terms":[194],"F1":[196],"respectively.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}