{"id":"https://openalex.org/W2808998506","doi":"https://doi.org/10.1145/3219819.3220094","title":"Model-based Clustering of Short Text Streams","display_name":"Model-based Clustering of Short Text Streams","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2808998506","doi":"https://doi.org/10.1145/3219819.3220094","mag":"2808998506"},"language":"en","primary_location":{"id":"doi:10.1145/3219819.3220094","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3219819.3220094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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":null,"display_name":"Jianhua Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianhua Yin","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087419700","display_name":"Daren Chao","orcid":"https://orcid.org/0000-0003-1813-419X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daren Chao","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027425274","display_name":"Zhongkun Liu","orcid":"https://orcid.org/0009-0006-4842-287X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongkun Liu","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101541045","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0001-6763-8146"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071285426","display_name":"Xiaohui Yu","orcid":"https://orcid.org/0000-0001-8170-2327"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Yu","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100630868","display_name":"Jianyong Wang","orcid":"https://orcid.org/0000-0002-7555-170X"},"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":"Jianyong Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":5.4151,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.96501073,"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":"2634","last_page":"2642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9998000264167786,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9998000264167786,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9839000105857849,"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":0.9807000160217285,"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":0.8447598814964294},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7446327805519104},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.6910996437072754},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.5432002544403076},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5400292873382568},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.4731282591819763},{"id":"https://openalex.org/keywords/affinity-propagation","display_name":"Affinity propagation","score":0.4704631268978119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4162612557411194},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4145907461643219},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.3396235406398773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3208593726158142},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26295533776283264},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.259859561920166},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.2485504150390625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447598814964294},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7446327805519104},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6910996437072754},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.5432002544403076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5400292873382568},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.4731282591819763},{"id":"https://openalex.org/C109659709","wikidata":"https://www.wikidata.org/wiki/Q3407504","display_name":"Affinity propagation","level":5,"score":0.4704631268978119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4162612557411194},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4145907461643219},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.3396235406398773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3208593726158142},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26295533776283264},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.259859561920166},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.2485504150390625},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3219819.3220094","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3219819.3220094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4000000059604645,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W48679198","https://openalex.org/W95577512","https://openalex.org/W182707955","https://openalex.org/W258053484","https://openalex.org/W1540921703","https://openalex.org/W1680797894","https://openalex.org/W1680822381","https://openalex.org/W1880262756","https://openalex.org/W1967687583","https://openalex.org/W2007267444","https://openalex.org/W2011430131","https://openalex.org/W2014615172","https://openalex.org/W2028544407","https://openalex.org/W2045938006","https://openalex.org/W2046677795","https://openalex.org/W2061922307","https://openalex.org/W2069429561","https://openalex.org/W2072169887","https://openalex.org/W2072644219","https://openalex.org/W2088340225","https://openalex.org/W2089484716","https://openalex.org/W2097089247","https://openalex.org/W2097645701","https://openalex.org/W2137644567","https://openalex.org/W2165612380","https://openalex.org/W2170936641","https://openalex.org/W2171343266","https://openalex.org/W2361559774","https://openalex.org/W2382102351","https://openalex.org/W2390768509","https://openalex.org/W2403008614","https://openalex.org/W2436677952","https://openalex.org/W2442340835","https://openalex.org/W4235539094","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2362911195","https://openalex.org/W2794209582","https://openalex.org/W2245611357","https://openalex.org/W2358586643","https://openalex.org/W2897883632","https://openalex.org/W2065347048","https://openalex.org/W2567087402","https://openalex.org/W2181939267","https://openalex.org/W2361333219","https://openalex.org/W4313288899"],"abstract_inverted_index":{"Short":[0],"text":[1,17,30],"stream":[2,31],"clustering":[3,32],"has":[4],"become":[5],"an":[6,78],"increasingly":[7],"important":[8],"problem":[9,42,45],"due":[10],"to":[11],"the":[12,39,59],"explosive":[13],"growth":[14],"of":[15,58,72,81,97],"short":[16,29],"in":[18],"diverse":[19],"social":[20],"medias.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,68],"propose":[26,77],"a":[27],"model-based":[28],"algorithm":[33,49,80],"(MStream)":[34],"which":[35,88],"can":[36,50,62,89,109],"deal":[37],"with":[38,54,83],"concept":[40],"drift":[41],"and":[43,61,107],"sparsity":[44],"naturally.":[46],"The":[47],"MStream":[48,82,106],"achieve":[51,110],"state-of-the-art":[52],"performance":[53,66,112],"only":[55],"one":[56],"pass":[57],"stream,":[60],"have":[63],"even":[64],"better":[65,111],"when":[67],"allow":[69],"multiple":[70],"iterations":[71],"each":[73],"batch.":[74],"We":[75],"further":[76],"improved":[79],"forgetting":[84],"rules":[85],"called":[86],"MStreamF,":[87],"efficiently":[90],"delete":[91],"outdated":[92,98],"documents":[93],"by":[94],"deleting":[95],"clusters":[96],"batches.":[99],"Our":[100],"extensive":[101],"experimental":[102],"study":[103],"shows":[104],"that":[105],"MStreamF":[108],"than":[113],"three":[114],"baselines":[115],"on":[116],"several":[117],"real":[118],"datasets.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":5}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}