{"id":"https://openalex.org/W2533524949","doi":"https://doi.org/10.1109/cist.2014.7016601","title":"Exploiting statistical and semantic information for document clustering: An evaluation on feature selection","display_name":"Exploiting statistical and semantic information for document clustering: An evaluation on feature selection","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2533524949","doi":"https://doi.org/10.1109/cist.2014.7016601","mag":"2533524949"},"language":"en","primary_location":{"id":"doi:10.1109/cist.2014.7016601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cist.2014.7016601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 Third IEEE International Colloquium in Information Science and Technology (CIST)","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/A5026677528","display_name":"Asmaa Benghabrit","orcid":"https://orcid.org/0000-0003-4330-439X"},"institutions":[{"id":"https://openalex.org/I4210153608","display_name":"Universit\u00e9 Moulay Ismail de Meknes","ror":"https://ror.org/04cnscd67","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210153608"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Asmaa Benghabrit","raw_affiliation_strings":["LM2I Laboratory, MoulayIsma\u00efl University, Mekn\u00e8s, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LM2I Laboratory, MoulayIsma\u00efl University, Mekn\u00e8s, Morocco","institution_ids":["https://openalex.org/I4210153608"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035878397","display_name":"Brahim Ouhbi","orcid":"https://orcid.org/0000-0002-6340-5617"},"institutions":[{"id":"https://openalex.org/I4210153608","display_name":"Universit\u00e9 Moulay Ismail de Meknes","ror":"https://ror.org/04cnscd67","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210153608"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Brahim Ouhbi","raw_affiliation_strings":["LM2I Laboratory, MoulayIsma\u00efl University, Mekn\u00e8s, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LM2I Laboratory, MoulayIsma\u00efl University, Mekn\u00e8s, Morocco","institution_ids":["https://openalex.org/I4210153608"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083034608","display_name":"El Moukhtar Zemmouri","orcid":"https://orcid.org/0000-0001-9165-0858"},"institutions":[{"id":"https://openalex.org/I4210153608","display_name":"Universit\u00e9 Moulay Ismail de Meknes","ror":"https://ror.org/04cnscd67","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210153608"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"El Moukhtar Zemmouri","raw_affiliation_strings":["LM2I Laboratory, MoulayIsma\u00efl University, Mekn\u00e8s, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LM2I Laboratory, MoulayIsma\u00efl University, Mekn\u00e8s, Morocco","institution_ids":["https://openalex.org/I4210153608"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015335959","display_name":"Bouchra Frikh","orcid":"https://orcid.org/0000-0002-9711-0841"},"institutions":[{"id":"https://openalex.org/I4210132968","display_name":"Agence pour le D\u00e9veloppement et la R\u00e9habilitation de la Ville de F\u00e8s","ror":"https://ror.org/043jwkg64","country_code":"MA","type":"government","lineage":["https://openalex.org/I4210132968"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Bouchra Frikh","raw_affiliation_strings":["LTTI Laboratory, EST-F\u00e8s, F\u00e8s, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTTI Laboratory, EST-F\u00e8s, F\u00e8s, Morocco","institution_ids":["https://openalex.org/I4210132968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054841123","display_name":"Hicham Behja","orcid":"https://orcid.org/0000-0002-3710-5629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hicham Behja","raw_affiliation_strings":["Greentic Laobarory, ENSEM, Casablanca, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Greentic Laobarory, ENSEM, Casablanca, Morocco","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.23990442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"39","issue":null,"first_page":"96","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9987000226974487,"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":0.9987000226974487,"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":0.998199999332428,"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":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.7904442548751831},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6512279510498047},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6442661881446838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6106845140457153},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5478264689445496},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4925599694252014},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.49137774109840393},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48457658290863037},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.48251864314079285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4515938460826874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904442548751831},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6512279510498047},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6442661881446838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6106845140457153},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5478264689445496},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4925599694252014},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.49137774109840393},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48457658290863037},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.48251864314079285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4515938460826874},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cist.2014.7016601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cist.2014.7016601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 Third IEEE International Colloquium in Information Science and Technology (CIST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W74108380","https://openalex.org/W1522930108","https://openalex.org/W1526719228","https://openalex.org/W1736751365","https://openalex.org/W1964095207","https://openalex.org/W1965168311","https://openalex.org/W1992419399","https://openalex.org/W1993318811","https://openalex.org/W1999635750","https://openalex.org/W2006533296","https://openalex.org/W2016001305","https://openalex.org/W2028424170","https://openalex.org/W2029062710","https://openalex.org/W2031648200","https://openalex.org/W2049633694","https://openalex.org/W2053503966","https://openalex.org/W2087962968","https://openalex.org/W2091669653","https://openalex.org/W2099322651","https://openalex.org/W2109535575","https://openalex.org/W2115665694","https://openalex.org/W2116237179","https://openalex.org/W2116892373","https://openalex.org/W2118020653","https://openalex.org/W2118587067","https://openalex.org/W2134720043","https://openalex.org/W2135330499","https://openalex.org/W2137570937","https://openalex.org/W2138229177","https://openalex.org/W2151100221","https://openalex.org/W2162223169","https://openalex.org/W2165612380","https://openalex.org/W2168939622","https://openalex.org/W2181602638","https://openalex.org/W2435251607","https://openalex.org/W3129711340","https://openalex.org/W4239007182","https://openalex.org/W4250042253","https://openalex.org/W4285719527","https://openalex.org/W4302197414","https://openalex.org/W6602984415","https://openalex.org/W6631307971","https://openalex.org/W6631457093","https://openalex.org/W6674952872","https://openalex.org/W6677408164","https://openalex.org/W6677504887","https://openalex.org/W6677796945","https://openalex.org/W6680166039","https://openalex.org/W6680524308","https://openalex.org/W6682569070","https://openalex.org/W6684798363","https://openalex.org/W6685671405","https://openalex.org/W6717827561","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W4296209631","https://openalex.org/W2561617217","https://openalex.org/W3097449145","https://openalex.org/W4294811468","https://openalex.org/W2355801475","https://openalex.org/W106004901","https://openalex.org/W2119708974","https://openalex.org/W2611996841","https://openalex.org/W2203841906","https://openalex.org/W1558035149"],"abstract_inverted_index":{"Feature":[0],"selection":[1,73,101],"is":[2],"not":[3],"only":[4],"a":[5,65,68,94],"key":[6],"to":[7,25,39,85],"handle":[8],"the":[9,15,27,31,42,47,50,54,87,109,115,124],"high":[10],"dimensionality":[11],"phenomenon":[12],"caused":[13],"by":[14,30],"vector":[16],"space":[17,56],"model":[18],"representation,":[19],"but":[20],"mainly":[21],"an":[22,104],"efficient":[23],"technique":[24],"reduce":[26],"noise":[28],"generated":[29],"irrelevant":[32],"and":[33,49,67,71,78,103,120,126],"redundant":[34],"terms.":[35],"However,":[36],"in":[37,83,139],"order":[38,84],"effectively":[40],"capture":[41],"most":[43,88],"important":[44],"features,":[45],"both":[46],"semantic":[48,79,110,121],"statistical":[51,77,99,119],"information":[52],"within":[53],"feature":[55,72,80,100],"should":[57],"be":[58],"taken":[59],"into":[60],"account.":[61],"Thereby,":[62],"we":[63,113],"propose":[64],"sequential":[66,125],"hybrid":[69,127],"clustering":[70],"approaches":[74],"that":[75],"combines":[76],"weight":[81],"estimation":[82],"select":[86],"informative":[89],"features.":[90],"We":[91],"first":[92],"perform":[93],"comparative":[95],"study":[96],"on":[97,132],"powerful":[98],"methods":[102,122],"analysis":[105],"was":[106],"done":[107],"for":[108,123],"methods.":[111],"Then,":[112],"extract":[114],"best":[116],"combination":[117],"of":[118],"approaches.":[128],"Detailed":[129],"experimental":[130],"results":[131],"three":[133],"different":[134],"data":[135],"sets":[136],"are":[137],"provided":[138],"this":[140],"paper.":[141]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}