{"id":"https://openalex.org/W3155561834","doi":"https://doi.org/10.1145/3404835.3463065","title":"Regularized Dual-PPMI Co-clustering for Text Data","display_name":"Regularized Dual-PPMI Co-clustering for Text Data","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3155561834","doi":"https://doi.org/10.1145/3404835.3463065","mag":"3155561834"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463065","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th 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/A5057014835","display_name":"S\u00e9verine Affeldt","orcid":"https://orcid.org/0000-0002-4107-0887"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"S\u00e9verine Affeldt","raw_affiliation_strings":["Universit\u00e9 de Paris, CNRS, Centre Borelli, Paris, France","CB - CB - Centre Borelli - UMR 9010 (Campus ENS Paris-Saclay\r\n4 Avenue des Sciences,\r\n91190 Gif-sur-Yvette - France)"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Paris, CNRS, Centre Borelli, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"CB - CB - Centre Borelli - UMR 9010 (Campus ENS Paris-Saclay\r\n4 Avenue des Sciences,\r\n91190 Gif-sur-Yvette - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000157816","display_name":"Lazhar Labiod","orcid":"https://orcid.org/0000-0001-8641-8050"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lazhar Labiod","raw_affiliation_strings":["Universit\u00e9 de Paris, CNRS, Centre Borelli, Paris, France","CB - CB - Centre Borelli - UMR 9010 (Campus ENS Paris-Saclay\r\n4 Avenue des Sciences,\r\n91190 Gif-sur-Yvette - France)"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Paris, CNRS, Centre Borelli, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"CB - CB - Centre Borelli - UMR 9010 (Campus ENS Paris-Saclay\r\n4 Avenue des Sciences,\r\n91190 Gif-sur-Yvette - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007054746","display_name":"Mohamed Nadif","orcid":"https://orcid.org/0000-0002-0007-3950"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohamed Nadif","raw_affiliation_strings":["Universit\u00e9 de Paris, CNRS, Centre Borelli, Paris, France","CB - CB - Centre Borelli - UMR 9010 (Campus ENS Paris-Saclay\r\n4 Avenue des Sciences,\r\n91190 Gif-sur-Yvette - France)"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Paris, CNRS, Centre Borelli, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"CB - CB - Centre Borelli - UMR 9010 (Campus ENS Paris-Saclay\r\n4 Avenue des Sciences,\r\n91190 Gif-sur-Yvette - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057014835"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I204730241"],"apc_list":null,"apc_paid":null,"fwci":0.649,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67077257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2263","last_page":"2267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9988999962806702,"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":0.9930999875068665,"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":0.8459721803665161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7071278691291809},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5296014547348022},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.4639546275138855},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4401858150959015},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4231826066970825},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4201076626777649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3985936641693115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34590643644332886},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22400587797164917}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8459721803665161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071278691291809},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5296014547348022},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.4639546275138855},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4401858150959015},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4231826066970825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4201076626777649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3985936641693115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34590643644332886},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22400587797164917},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3404835.3463065","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03538921v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03538921","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":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2021, Virtual Event, Canada. pp.2263-2267, ⟨10.1145/3404835.3463065⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.47999998927116394,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W658295343","https://openalex.org/W1790954942","https://openalex.org/W2006255103","https://openalex.org/W2071781501","https://openalex.org/W2097645701","https://openalex.org/W2145001205","https://openalex.org/W2149521737","https://openalex.org/W2168487341","https://openalex.org/W2434205482","https://openalex.org/W2472863357","https://openalex.org/W2597760014","https://openalex.org/W2623274681","https://openalex.org/W2741022122","https://openalex.org/W2788929630","https://openalex.org/W2800909518","https://openalex.org/W3020633614","https://openalex.org/W3093889362","https://openalex.org/W4254955164","https://openalex.org/W4285719527","https://openalex.org/W6600006904","https://openalex.org/W6621984194","https://openalex.org/W6817126606"],"related_works":["https://openalex.org/W1999117613","https://openalex.org/W2040929534","https://openalex.org/W3022637481","https://openalex.org/W2393816671","https://openalex.org/W3120229345","https://openalex.org/W2111119584","https://openalex.org/W3144143113","https://openalex.org/W3039964395","https://openalex.org/W2019737068","https://openalex.org/W2899601636"],"abstract_inverted_index":{"Co-clustering":[0],"of":[1,42,58,94,121,133],"document-term":[2],"matrices":[3],"has":[4],"proved":[5],"to":[6,33,65],"be":[7],"more":[8],"effective":[9],"than":[10],"one-sided":[11],"clustering.":[12],"By":[13,83],"their":[14],"nature,":[15],"text":[16,70,107,115],"data":[17,36,108],"are":[18],"also":[19],"generally":[20,89],"unbalanced":[21,35],"and":[22,80,127,136],"directional.":[23],"Recently,":[24],"the":[25,39,105,118],"von":[26],"Mises-Fisher":[27],"(vMF)":[28],"mixture":[29],"model":[30],"was":[31],"proposed":[32,123],"handle":[34],"while":[37],"harnessing":[38],"directional":[40],"nature":[41],"text.":[43],"In":[44],"this":[45],"paper":[46],"we":[47,96],"propose":[48,97],"a":[49,55,66,98],"novel":[50],"co-clustering":[51,71],"approach":[52,124],"based":[53],"on":[54,112],"matrix":[56],"formulation":[57,63],"vMF":[59],"model-based":[60],"co-clustering.":[61],"This":[62],"leads":[64],"flexible":[67],"method":[68],"for":[69],"that":[72,102],"can":[73],"easily":[74],"incorporate":[75],"both":[76,130],"word-word":[77],"semantic":[78],"relationships":[79],"document-document":[81],"similarities.":[82],"contrast":[84],"with":[85],"existing":[86],"methods,":[87,129],"which":[88],"use":[90],"an":[91],"additive":[92],"incorporation":[93],"similarities,":[95],"dual":[99],"multiplicative":[100],"regularization":[101],"better":[103],"encapsulates":[104],"underlying":[106],"structure.":[109],"Extensive":[110],"evaluations":[111],"various":[113],"real-world":[114],"datasets":[116],"demonstrate":[117],"superior":[119],"performance":[120],"our":[122],"over":[125],"baseline":[126],"competitive":[128],"in":[131],"terms":[132],"clustering":[134],"results":[135],"co-cluster":[137],"topic":[138],"coherence.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}