{"id":"https://openalex.org/W4250619709","doi":"https://doi.org/10.1137/1.9781611972771.40","title":"Topic Models over Text Streams: A Study of Batch and Online Unsupervised Learning","display_name":"Topic Models over Text Streams: A Study of Batch and Online Unsupervised Learning","publication_year":2007,"publication_date":"2007-04-26","ids":{"openalex":"https://openalex.org/W4250619709","doi":"https://doi.org/10.1137/1.9781611972771.40"},"language":"en","primary_location":{"id":"doi:10.1137/1.9781611972771.40","is_oa":false,"landing_page_url":"https://doi.org/10.1137/1.9781611972771.40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 SIAM International Conference on Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5014459472","display_name":"Arindam Banerjee","orcid":"https://orcid.org/0000-0002-7856-5699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arindam Banerjee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112572279","display_name":"Sugato Basu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sugato Basu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.73,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.96236559,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"431","last_page":"436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.960099995136261,"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":0.946399986743927,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8713608980178833},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.8375864028930664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.826757550239563},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7083914875984192},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5235323905944824},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.49194976687431335},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4789905250072479},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46342742443084717},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.437010794878006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43219515681266785},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4295658469200134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38152217864990234}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8713608980178833},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.8375864028930664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826757550239563},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7083914875984192},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5235323905944824},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.49194976687431335},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4789905250072479},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46342742443084717},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.437010794878006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43219515681266785},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4295658469200134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38152217864990234},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/1.9781611972771.40","is_oa":false,"landing_page_url":"https://doi.org/10.1137/1.9781611972771.40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 SIAM International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.215.2788","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.215.2788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.siam.org/proceedings/datamining/2007/dm07_040Banerjee.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W3159709618","https://openalex.org/W4309228610","https://openalex.org/W4294597112"],"abstract_inverted_index":{"Topic":[0],"modeling":[1],"techniques":[2],"have":[3],"widespread":[4],"use":[5,13],"in":[6,23,100,131,179],"text":[7,132,152],"data":[8,78],"mining":[9,133],"applications.":[10,134],"Some":[11],"applications":[12,171],"batch":[14,37,156,191],"models,":[15],"which":[16,127,145],"perform":[17],"clustering":[18,58,73],"on":[19,59,95,150,159],"the":[20,32,102,188],"document":[21,61,98],"collection":[22],"aggregate.":[24],"In":[25,54],"this":[26,83],"paper,":[27],"we":[28,85,136],"analyze":[29],"and":[30,48,68,92,104,153,194],"compare":[31],"performance":[33,189],"of":[34,89,176,190,196],"three":[35],"recently-proposed":[36],"topic":[38,123,143,148,157],"models\u2014Latent":[39],"Dirichlet":[40,43],"Allocation":[41],"(LDA),":[42],"Compound":[44],"Multinomial":[45],"(DCM)":[46],"mixtures":[47],"von-Mises":[49],"Fisher":[50],"(vMF)":[51],"mixture":[52],"models.":[53],"cases":[55],"where":[56],"offline":[57,103,192],"complete":[60],"collections":[62],"is":[63,111,128,167],"infeasible":[64],"due":[65],"to":[66],"resource":[67],"response-rate":[69],"constraints,":[70],"online":[71,87,105,147,198],"unsupervised":[72],"methods":[74],"that":[75,108,182],"process":[76],"incoming":[77],"incrementally":[79],"are":[80],"necessary.":[81],"To":[82],"end,":[84],"propose":[86,137],"variants":[88],"vMF,":[90],"EDCM":[91],"LDA.":[93],"Experiments":[94],"large":[96],"real-world":[97],"collections,":[99],"both":[101],"settings,":[106],"demonstrate":[107],"though":[109],"LDA":[110],"a":[112,138,164,184],"good":[113,185],"model":[114,166],"for":[115,141,169],"finding":[116],"word-level":[117],"topics,":[118],"vMF":[119],"finds":[120],"better":[121],"document-level":[122],"clusters":[124],"more":[125],"efficiently,":[126],"often":[129],"important":[130],"Finally,":[135],"practical":[139],"heuristic":[140],"hybrid":[142,165],"modeling,":[144],"learns":[146],"models":[149,158],"streaming":[151],"intermittently":[154],"runs":[155],"aggregated":[160],"documents":[161],"offline.":[162],"Such":[163],"useful":[168],"several":[170],"(e.g.,":[172],"dynamic":[173],"topic-based":[174],"aggregation":[175],"user-generated":[177],"content":[178],"social":[180],"networks)":[181],"need":[183],"tradeoff":[186],"between":[187],"algorithms":[193],"efficiency":[195],"incremental":[197],"algorithms.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}