{"id":"https://openalex.org/W1966811099","doi":"https://doi.org/10.1145/1458082.1458271","title":"An extension of PLSA for document clustering","display_name":"An extension of PLSA for document clustering","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W1966811099","doi":"https://doi.org/10.1145/1458082.1458271","mag":"1966811099"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"preprint","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/A5100337295","display_name":"Youngmin Kim","orcid":"https://orcid.org/0000-0002-1295-1837"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Young-Min Kim","raw_affiliation_strings":["Universit\u00e9 Pierre et Marie Curie, Paris, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Pierre et Marie Curie, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061485115","display_name":"Jean-Fran\u00e7ois Pessiot","orcid":null},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Fran\u00e7ois Pessiot","raw_affiliation_strings":["Universit\u00e9 Pierre et Marie Curie, Paris, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Pierre et Marie Curie, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111523904","display_name":"Massih Amini","orcid":null},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Massih Reza Amini","raw_affiliation_strings":["Universit\u00e9 Pierre et Marie Curie, Paris, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Pierre et Marie Curie, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103252936","display_name":"Patrick Gallinari","orcid":"https://orcid.org/0000-0002-5679-0617"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Gallinari","raw_affiliation_strings":["Universit\u00e9 Pierre et Marie Curie, Paris, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Pierre et Marie Curie, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100337295"],"corresponding_institution_ids":["https://openalex.org/I39804081"],"apc_list":null,"apc_paid":null,"fwci":2.9483,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91164928,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1345","last_page":"1346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994999766349792,"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":0.9994999766349792,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9993000030517578,"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/T11106","display_name":"Data Management and Algorithms","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.9588315486907959},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.7085285782814026},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7060176730155945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6491897106170654},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.644328236579895},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.4584559500217438},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4500303268432617},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.43133482336997986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42270082235336304},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4203302562236786},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40011146664619446},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3448197543621063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.250810831785202},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19339317083358765}],"concepts":[{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.9588315486907959},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.7085285782814026},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7060176730155945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6491897106170654},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.644328236579895},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.4584559500217438},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4500303268432617},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.43133482336997986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42270082235336304},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4203302562236786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40011146664619446},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3448197543621063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.250810831785202},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19339317083358765},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1458082.1458271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01301612v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01301612","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"17th ACM Conference on Information and Knowledge Management (CIKM 2008), Oct 2008, Napa Valley, CA, United States. pp.1345-1346, ⟨10.1145/1458082.1458271⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1996764654","https://openalex.org/W2010425028","https://openalex.org/W2049633694","https://openalex.org/W2097645701","https://openalex.org/W2107743791","https://openalex.org/W2109527084","https://openalex.org/W2160799467","https://openalex.org/W4233135949","https://openalex.org/W4241122026","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2242083226","https://openalex.org/W1603253275","https://openalex.org/W1514645777","https://openalex.org/W2884410131","https://openalex.org/W111011176","https://openalex.org/W2138996412","https://openalex.org/W2906932471","https://openalex.org/W2763292376","https://openalex.org/W2097596242","https://openalex.org/W2270140793"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"an":[5,13],"extension":[6],"of":[7],"the":[8,18,46,50],"PLSA":[9,48],"model":[10,19,34],"in":[11],"which":[12],"extra":[14],"latent":[15],"variable":[16],"allows":[17],"to":[20,41],"co-cluster":[21],"documents":[22],"and":[23,49],"terms":[24],"simultaneously.":[25],"We":[26],"show":[27],"on":[28],"three":[29],"datasets":[30],"that":[31],"our":[32],"extended":[33],"produces":[35],"statistically":[36],"significant":[37],"improvements":[38],"with":[39],"respect":[40],"two":[42],"clustering":[43],"measures":[44],"over":[45],"original":[47],"multinomial":[51],"mixture":[52],"MM":[53],"models.":[54]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}