{"id":"https://openalex.org/W2027679778","doi":"https://doi.org/10.1002/(sici)1098-111x(200007)15:7<633::aid-int4>3.0.co;2-8","title":"Data mining for text categorization with semi-supervised agglomerative hierarchical clustering","display_name":"Data mining for text categorization with semi-supervised agglomerative hierarchical clustering","publication_year":2000,"publication_date":"2000-07-01","ids":{"openalex":"https://openalex.org/W2027679778","doi":"https://doi.org/10.1002/(sici)1098-111x(200007)15:7<633::aid-int4>3.0.co;2-8","mag":"2027679778"},"language":"en","primary_location":{"id":"doi:10.1002/(sici)1098-111x(200007)15:7<633::aid-int4>3.0.co;2-8","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1098-111x(200007)15:7<633::aid-int4>3.0.co;2-8","pdf_url":null,"source":{"id":"https://openalex.org/S57950554","display_name":"International Journal of Intelligent Systems","issn_l":"0884-8173","issn":["0884-8173","1098-111X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Intelligent Systems","raw_type":"journal-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/A5103455971","display_name":"Antonio G\ufffdmez Skarmeta","orcid":null},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Antonio G\ufffdmez Skarmeta","raw_affiliation_strings":["Departamento de Informa\u0301tica, Inteligencia, Artificial, y Electro\u0301nica, Universidad de Murcia, Murcia, Spain","Departamento de Inform\u00e1tica, Inteligencia, Artificial, y Electr\u00f3nica, Universidad de Murcia, Murcia, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Informa\u0301tica, Inteligencia, Artificial, y Electro\u0301nica, Universidad de Murcia, Murcia, Spain","institution_ids":["https://openalex.org/I80180929"]},{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Inteligencia, Artificial, y Electr\u00f3nica, Universidad de Murcia, Murcia, Spain","institution_ids":["https://openalex.org/I80180929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055933277","display_name":"A. Bensaid","orcid":null},"institutions":[{"id":"https://openalex.org/I47844","display_name":"Al Akhawayn University","ror":"https://ror.org/03erkev52","country_code":"MA","type":"education","lineage":["https://openalex.org/I47844"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Amine Bensaid","raw_affiliation_strings":["Computer Science Graduate Division, Al Akhawayn University in Ifrane, (AUI), Ifrane, Morocco"],"affiliations":[{"raw_affiliation_string":"Computer Science Graduate Division, Al Akhawayn University in Ifrane, (AUI), Ifrane, Morocco","institution_ids":["https://openalex.org/I47844"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111371354","display_name":"Nadia Tazi","orcid":null},"institutions":[{"id":"https://openalex.org/I47844","display_name":"Al Akhawayn University","ror":"https://ror.org/03erkev52","country_code":"MA","type":"education","lineage":["https://openalex.org/I47844"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Nadia Tazi","raw_affiliation_strings":["Computer Science Graduate Division, Al Akhawayn University in Ifrane, (AUI), Ifrane, Morocco"],"affiliations":[{"raw_affiliation_string":"Computer Science Graduate Division, Al Akhawayn University in Ifrane, (AUI), Ifrane, Morocco","institution_ids":["https://openalex.org/I47844"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103455971"],"corresponding_institution_ids":["https://openalex.org/I80180929"],"apc_list":{"value":2500,"currency":"USD","value_usd":2500},"apc_paid":null,"fwci":1.0253,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.82034235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"15","issue":"7","first_page":"633","last_page":"646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9941999912261963,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9941999912261963,"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":0.9822999835014343,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9732999801635742,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.74067622423172},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.707313060760498},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6695595979690552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6520112156867981},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.572762668132782},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5360538959503174},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5316892862319946},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.5033788084983826},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5022797584533691},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.501807689666748},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.46597525477409363},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45874035358428955},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.442970871925354},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39041662216186523},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.36587589979171753},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.33162498474121094},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.0819978415966034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74067622423172},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.707313060760498},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6695595979690552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6520112156867981},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.572762668132782},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5360538959503174},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5316892862319946},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.5033788084983826},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5022797584533691},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.501807689666748},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.46597525477409363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45874035358428955},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.442970871925354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39041662216186523},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.36587589979171753},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.33162498474121094},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0819978415966034}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/(sici)1098-111x(200007)15:7<633::aid-int4>3.0.co;2-8","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1098-111x(200007)15:7<633::aid-int4>3.0.co;2-8","pdf_url":null,"source":{"id":"https://openalex.org/S57950554","display_name":"International Journal of Intelligent Systems","issn_l":"0884-8173","issn":["0884-8173","1098-111X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Intelligent Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W31330425","https://openalex.org/W1520963883","https://openalex.org/W1956559956","https://openalex.org/W1969572066","https://openalex.org/W1970974276","https://openalex.org/W1978394996","https://openalex.org/W1983078185","https://openalex.org/W1997841190","https://openalex.org/W2060216474","https://openalex.org/W2094934653","https://openalex.org/W2098162425","https://openalex.org/W2139578439","https://openalex.org/W2325227998","https://openalex.org/W2435251607","https://openalex.org/W2753176400","https://openalex.org/W6601277183","https://openalex.org/W6640862754","https://openalex.org/W6642384972","https://openalex.org/W6642848584","https://openalex.org/W6665863920","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2087424554","https://openalex.org/W2622412490","https://openalex.org/W1981213098","https://openalex.org/W4231226332","https://openalex.org/W2161927371","https://openalex.org/W2384052049","https://openalex.org/W2385630304","https://openalex.org/W2367205823","https://openalex.org/W4220814143"],"abstract_inverted_index":{"In":[0],"this":[1,79],"paper":[2],"we":[3,76,81,100],"study":[4],"the":[5,63,72,93,96,102,106,119,124],"use":[6,77],"of":[7,20,40,55,95,109],"a":[8,30,36,52,84],"semi-supervised":[9],"agglomerative":[10,46],"hierarchical":[11,47],"clustering":[12,31,48],"(ssAHC)":[13],"algorithm":[14,32,104,126],"to":[15,24,43,65,91,105,118,123,139],"text":[16,22,73],"categorization,":[17],"which":[18],"consists":[19],"assigning":[21],"documents":[23,110],"predefined":[25],"categories.":[26],"ssAHC":[27,103,135],"is":[28,89,116],"(i)":[29],"that":[33,88,113,134],"(ii)":[34],"uses":[35],"finite":[37,53],"design":[38],"set":[39,54],"labeled":[41],"data":[42,57],"(iii)":[44],"help":[45],"(AHC)":[49],"algorithms":[50],"partition":[51],"unlabeled":[56],"and":[58,111,122],"then":[59,82],"(iv)":[60],"terminates":[61],"without":[62],"capability":[64],"label":[66],"other":[67],"objects.":[68],"We":[69,131],"first":[70],"describe":[71],"representation":[74],"method":[75,87],"in":[78],"work;":[80],"present":[83],"feature":[85,97],"selection":[86],"used":[90],"reduce":[92],"dimensionality":[94],"space.":[98],"Finally,":[99],"apply":[101],"Reuters":[107],"database":[108],"show":[112],"its":[114],"performance":[115],"superior":[117],"Bayes":[120,129],"classifier":[121],"Expectation-Maximization":[125],"combined":[127],"with":[128],"classifier.":[130],"showed":[132],"also":[133],"helps":[136],"AHC":[137],"techniques":[138],"improve":[140],"their":[141],"performance.":[142],"\u00a9":[143],"2000":[144],"John":[145],"Wiley":[146],"&":[147],"Sons,":[148],"Inc.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}