{"id":"https://openalex.org/W1997571094","doi":"https://doi.org/10.1145/2494266.2494296","title":"Incremental hierarchical text clustering with privileged information","display_name":"Incremental hierarchical text clustering with privileged information","publication_year":2013,"publication_date":"2013-09-03","ids":{"openalex":"https://openalex.org/W1997571094","doi":"https://doi.org/10.1145/2494266.2494296","mag":"1997571094"},"language":"en","primary_location":{"id":"doi:10.1145/2494266.2494296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2494266.2494296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM symposium on Document engineering","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/A5103168466","display_name":"Ricardo Marcondes Marcacini","orcid":"https://orcid.org/0000-0002-2309-3487"},"institutions":[{"id":"https://openalex.org/I122558511","display_name":"Universidade Federal de Mato Grosso do Sul","ror":"https://ror.org/0366d2847","country_code":"BR","type":"education","lineage":["https://openalex.org/I122558511"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ricardo Marcondes Marcacini","raw_affiliation_strings":["Federal University of Mato Grosso do Sul, Tr\u00eas Lagoas - MS, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Mato Grosso do Sul, Tr\u00eas Lagoas - MS, Brazil","institution_ids":["https://openalex.org/I122558511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073365814","display_name":"Solange Oliveira Rezende","orcid":"https://orcid.org/0000-0002-5233-7639"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Solange Oliveira Rezende","raw_affiliation_strings":["Mathematical and Computer Sciences Institute - ICMC, University of S\u00e3o Paulo - USP, S\u00e3o Carlos - SP, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematical and Computer Sciences Institute - ICMC, University of S\u00e3o Paulo - USP, S\u00e3o Carlos - SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4354,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.95357382,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9984999895095825,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9932000041007996,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8990219831466675},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.759442925453186},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.753259539604187},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6687231063842773},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.5942273139953613},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.5536513924598694},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.5161970257759094},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5137889981269836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4928014576435089},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.48168930411338806},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4695746600627899},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4462173283100128},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4368336498737335},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.40964072942733765},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36428403854370117}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8990219831466675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759442925453186},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.753259539604187},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6687231063842773},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.5942273139953613},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.5536513924598694},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.5161970257759094},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5137889981269836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4928014576435089},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.48168930411338806},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4695746600627899},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4462173283100128},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4368336498737335},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.40964072942733765},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36428403854370117},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2494266.2494296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2494266.2494296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM symposium on Document engineering","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":4,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W2067562626","https://openalex.org/W2100904656","https://openalex.org/W2404930856"],"related_works":["https://openalex.org/W4285159010","https://openalex.org/W2954628966","https://openalex.org/W2387287989","https://openalex.org/W4385594911","https://openalex.org/W4237106426","https://openalex.org/W2556924671","https://openalex.org/W4238952262","https://openalex.org/W3020292803","https://openalex.org/W4229037312","https://openalex.org/W2922812195"],"abstract_inverted_index":{"In":[0,64,78,102],"many":[1],"text":[2,27,75,92,110,136,147],"clustering":[3,24,28,76,118,132,159,167],"tasks,":[4],"there":[5],"is":[6,86,112,128],"some":[7],"valuable":[8],"knowledge":[9],"about":[10,108],"the":[11,17,23,69,83,105,109,134,150,158],"problem":[12],"domain,":[13],"in":[14,22,61],"addition":[15],"to":[16,32,57,72,114,163],"original":[18],"textual":[19,100],"data":[20,39],"involved":[21],"process.":[25],"Traditional":[26],"methods":[29],"are":[30],"unable":[31],"incorporate":[33,58],"such":[34],"additional":[35],"(privileged)":[36],"information":[37,60,107],"into":[38],"clustering.":[40,124],"Recently,":[41],"a":[42,164],"new":[43],"paradigm":[44,71,85],"called":[45],"LUPI":[46,70,84],"-":[47,52],"Learning":[48],"Using":[49],"Privileged":[50],"Information":[51],"was":[53],"proposed":[54],"by":[55,120],"Vapnik":[56],"privileged":[59,106],"classification":[62],"tasks.":[63,77],"this":[65],"paper,":[66],"we":[67,80],"extend":[68],"deal":[73],"with":[74],"particular,":[79],"show":[81],"that":[82,153],"potentially":[87],"promising":[88],"for":[89,97,130],"incremental":[90,131],"hierarchical":[91,166],"clustering,":[93],"being":[94],"very":[95],"useful":[96],"organizing":[98],"large":[99],"databases.":[101],"our":[103,154],"method,":[104],"documents":[111],"applied":[113],"refine":[115],"an":[116,141],"initial":[117,126],"model":[119,127],"means":[121],"of":[122,133],"consensus":[123],"The":[125],"used":[129],"remaining":[135],"documents.":[137],"We":[138],"carried":[139],"out":[140],"experimental":[142],"evaluation":[143],"on":[144],"two":[145],"benchmark":[146],"collections":[148],"and":[149],"results":[151],"showed":[152],"method":[155],"significantly":[156],"improves":[157],"accuracy":[160],"when":[161],"compared":[162],"traditional":[165],"method.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}