{"id":"https://openalex.org/W7146967672","doi":"https://doi.org/10.1109/tbdata.2026.3679463","title":"Semi-Supervised Short Text Stream Clustering With Dual-View Semantic Representation and Cluster-Complement Learning","display_name":"Semi-Supervised Short Text Stream Clustering With Dual-View Semantic Representation and Cluster-Complement Learning","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7146967672","doi":"https://doi.org/10.1109/tbdata.2026.3679463"},"language":null,"primary_location":{"id":"doi:10.1109/tbdata.2026.3679463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2026.3679463","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","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":null,"display_name":"Yaru Zhang","orcid":"https://orcid.org/0009-0002-8792-4603"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaru Zhang","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-8792-4603","affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132693739","display_name":"Peipei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peipei Li","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9142-448X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35554873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"4","first_page":"1304","last_page":"1317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.41499999165534973,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.41499999165534973,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.07900000363588333,"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/T10028","display_name":"Topic Modeling","score":0.06459999829530716,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7315000295639038},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.4961000084877014},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4587000012397766},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.44339999556541443},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43209999799728394},{"id":"https://openalex.org/keywords/semantic-compression","display_name":"Semantic compression","score":0.41670000553131104},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.3919999897480011},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.36899998784065247},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.36500000953674316},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.3467999994754791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8603000044822693},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7315000295639038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.599399983882904},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.4961000084877014},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C202708506","wikidata":"https://www.wikidata.org/wiki/Q7449050","display_name":"Semantic compression","level":5,"score":0.41670000553131104},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3799000084400177},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3790000081062317},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.3467999994754791},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.33320000767707825},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.32420000433921814},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C173862523","wikidata":"https://www.wikidata.org/wiki/Q5421270","display_name":"Explicit semantic analysis","level":5,"score":0.267300009727478},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C110903229","wikidata":"https://www.wikidata.org/wiki/Q7449064","display_name":"Semantic integration","level":4,"score":0.258899986743927},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2026.3679463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2026.3679463","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1128271767","display_name":null,"funder_award_id":"62120106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2263702567","display_name":null,"funder_award_id":"62376085","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Short":[0],"text":[1,18,59,79],"stream":[2,60],"clustering":[3,48,61,132],"is":[4,248],"a":[5,45,56,127,134,159,175],"challenging":[6],"task":[7],"since":[8],"1)":[9],"the":[10,25,33,41,88,93,99,104,113,152,167,170,195,202,223],"limited":[11],"words":[12],"in":[13,47,209],"short":[14,58],"texts":[15,180],"lead":[16],"to":[17,23,37,72,150,165,214],"sparsity,":[19,80],"making":[20],"it":[21],"difficult":[22],"capture":[24],"comprehensive":[26],"semantic":[27,65,75,84,90,95,101,115],"information":[28,76],"of":[29,40,87,162,169,178,204,212,217,225],"texts,":[30],"and":[31,67,92,111,172,181],"2)":[32],"topic":[34,144],"evolution":[35],"leads":[36],"catastrophic":[38,140],"forgetting":[39,141],"learning":[42,69,149,193],"model,":[43],"causing":[44],"degradation":[46],"performance.":[49],"To":[50,138],"address":[51,73,139],"these":[52],"issues,":[53],"we":[54,81,146,221],"propose":[55],"semi-supervised":[57],"method":[62,227],"with":[63,198],"Dual-View":[64],"representation":[66],"Cluster-Complement":[68],"(DVCC).":[70],"Specifically,":[71],"insufficient":[74],"caused":[77,142],"by":[78,117,143,228],"introduce":[82,147],"dual-view":[83],"representation,":[85],"consisting":[86],"word-level":[89,100],"view":[91,102,116],"sentence-level":[94,114],"view.":[96],"We":[97,156],"model":[98,110,129],"using":[103],"Dirichlet":[105],"Process":[106],"Multinomial":[107],"Mixture":[108],"(DPMM)":[109],"generate":[112],"an":[118],"encoder.":[119],"These":[120],"two":[121],"views":[122],"are":[123],"then":[124,173],"integrated":[125],"into":[126],"unified":[128],"for":[130,187],"online":[131],"via":[133],"Bernoulli":[135],"random":[136],"variable.":[137],"evolution,":[145],"cluster-complement":[148,192],"update":[151],"encoder":[153],"offline":[154],"periodically.":[155],"initially":[157],"use":[158,174],"small":[160],"amount":[161,177],"labeled":[163],"data":[164,186,197,213],"initialize":[166],"parameters":[168],"encoder,":[171],"large":[176],"unlabeled":[179],"their":[182],"pseudo-labels":[183],"as":[184],"training":[185,196],"subsequent":[188],"updates.":[189],"The":[190,236,246],"proposed":[191],"supplements":[194],"cluster":[199],"centroids,":[200],"ensuring":[201],"centroids":[203],"all":[205],"active":[206],"clusters":[207],"appear":[208],"each":[210],"batch":[211],"maintain":[215],"knowledge":[216],"old":[218],"topics.":[219],"Finally,":[220],"validate":[222],"effectiveness":[224],"our":[226],"conducting":[229],"extensive":[230],"experiments":[231],"on":[232],"six":[233],"benchmark":[234],"datasets.":[235],"experimental":[237],"results":[238],"show":[239],"that":[240],"DVCC":[241],"outperforms":[242],"existing":[243],"state-of-the-art":[244],"methods.":[245],"code":[247],"available":[249],"at":[250],"<uri":[251],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[252],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/yaru-Zhangz/DVCC</uri>.":[253]},"counts_by_year":[],"updated_date":"2026-07-11T05:44:25.926202","created_date":"2026-04-02T00:00:00"}