{"id":"https://openalex.org/W2025103722","doi":"https://doi.org/10.1109/tsmcb.2012.2227998","title":"Efficient Semisupervised MEDLINE Document Clustering With MeSH-Semantic and Global-Content Constraints","display_name":"Efficient Semisupervised MEDLINE Document Clustering With MeSH-Semantic and Global-Content Constraints","publication_year":2012,"publication_date":"2012-12-04","ids":{"openalex":"https://openalex.org/W2025103722","doi":"https://doi.org/10.1109/tsmcb.2012.2227998","mag":"2025103722","pmid":"https://pubmed.ncbi.nlm.nih.gov/26502435"},"language":"en","primary_location":{"id":"doi:10.1109/tsmcb.2012.2227998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcb.2012.2227998","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5074862307","display_name":"Jun Gu","orcid":"https://orcid.org/0000-0002-1847-7304"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Gu","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","State Key Lab of Software Engineering, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"State Key Lab of Software Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044432126","display_name":"Wei Feng","orcid":"https://orcid.org/0000-0001-7472-7921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Feng","raw_affiliation_strings":["School of Computer Science and Technology, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University, Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062026103","display_name":"Jia Zeng","orcid":"https://orcid.org/0000-0001-9980-492X"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Zeng","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059001924","display_name":"Hiroshi Mamitsuka","orcid":"https://orcid.org/0000-0002-6607-5617"},"institutions":[{"id":"https://openalex.org/I4399598384","display_name":"Kyoto University Institute for Chemical Research","ror":"https://ror.org/0349bbg69","country_code":null,"type":"facility","lineage":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Mamitsuka","raw_affiliation_strings":["Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji, Japan"],"affiliations":[{"raw_affiliation_string":"Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji, Japan","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045866167","display_name":"Shanfeng Zhu","orcid":"https://orcid.org/0000-0002-6067-5312"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanfeng Zhu","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","State Key Lab of Software Engineering, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"State Key Lab of Software Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074862307"],"corresponding_institution_ids":["https://openalex.org/I24943067","https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":1.6135,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.82531789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"43","issue":"4","first_page":"1265","last_page":"1276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9947999715805054,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7494722604751587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7123668193817139},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5831493139266968},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.43697112798690796},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4346475899219513},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4201996922492981},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3835010528564453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2501569390296936}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7494722604751587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123668193817139},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5831493139266968},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.43697112798690796},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4346475899219513},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4201996922492981},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3835010528564453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2501569390296936},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046650","descriptor_name":"Medical Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046650","descriptor_name":"Medical Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046650","descriptor_name":"Medical Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tsmcb.2012.2227998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcb.2012.2227998","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:26502435","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26502435","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W174753650","https://openalex.org/W1479807131","https://openalex.org/W1488751160","https://openalex.org/W1596382552","https://openalex.org/W1660390307","https://openalex.org/W1835571316","https://openalex.org/W1956559956","https://openalex.org/W1981081578","https://openalex.org/W1985897329","https://openalex.org/W2056714990","https://openalex.org/W2061172803","https://openalex.org/W2096525273","https://openalex.org/W2100935296","https://openalex.org/W2106987717","https://openalex.org/W2117154949","https://openalex.org/W2120413242","https://openalex.org/W2121947440","https://openalex.org/W2125964067","https://openalex.org/W2127603354","https://openalex.org/W2134089414","https://openalex.org/W2136127419","https://openalex.org/W2136930489","https://openalex.org/W2137820941","https://openalex.org/W2139956879","https://openalex.org/W2144181601","https://openalex.org/W2144317357","https://openalex.org/W2153384970","https://openalex.org/W2160484893","https://openalex.org/W2162972849","https://openalex.org/W2165874743","https://openalex.org/W2166190866","https://openalex.org/W2168022112","https://openalex.org/W2325227998","https://openalex.org/W2610360795","https://openalex.org/W2912210943","https://openalex.org/W2917056928","https://openalex.org/W2917293077","https://openalex.org/W4231041617","https://openalex.org/W4253901579","https://openalex.org/W6607080078","https://openalex.org/W6635376254","https://openalex.org/W6675339850","https://openalex.org/W6677328822","https://openalex.org/W6678356393","https://openalex.org/W6684578312","https://openalex.org/W6758700058"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W2387982377"],"abstract_inverted_index":{"For":[0],"clustering":[1,38,69,118,123,187],"biomedical":[2,39],"documents,":[3,17],"we":[4,112],"can":[5],"consider":[6],"three":[7],"different":[8,47,100,106],"types":[9,48,57,101,130],"of":[10,49,58,66,91,94,102,131,159,170,195,211],"information:":[11],"the":[12,18,23,28,64,77,83,92,95,110,125,157,193],"local-content":[13],"(LC)":[14],"information":[15,21,59,103],"from":[16,22,199,207],"global-content":[19],"(GC)":[20],"whole":[24],"MEDLINE":[25,67,162,171],"collections,":[26],"and":[27,79,145,183,202],"medical":[29],"subject":[30],"heading":[31],"(MeSH)-semantic":[32],"(MS)":[33],"information.":[34,81],"Previous":[35],"methods":[36],"for":[37,45,98,122,240],"documents":[40],"are":[41],"not":[42],"necessarily":[43],"effective":[44],"integrating":[46],"information,":[50],"by":[51,73,165],"which":[52],"only":[53,208,238],"one":[54,209],"or":[55],"two":[56,129],"have":[60],"been":[61,71],"used.":[62],"Recently,":[63],"performance":[65,158,194],"document":[68,137,163],"has":[70],"enhanced":[72],"linearly":[74],"combining":[75,99],"both":[76,200],"LC":[78,126],"MS":[80,141,201],"However,":[82],"simple":[84],"linear":[85,180],"combination":[86,181],"could":[87],"be":[88],"ineffective":[89],"because":[90],"limitation":[93],"representation":[96],"space":[97],"(similarities)":[104],"with":[105,128,139,151,197],"reliability.":[107],"To":[108],"overcome":[109],"limitation,":[111],"propose":[113],"a":[114,179],"new":[115],"semisupervised":[116,186],"spectral":[117],"method,":[119],"i.e.,":[120],"SSNCut,":[121],"over":[124],"similarities,":[127],"constraints:":[132],"must-link":[133],"(ML)":[134],"constraints":[135,148,198,219,228],"on":[136,149,161],"pairs":[138],"high":[140],"(or":[142],"GC)":[143],"similarities":[144,204],"cannot-link":[146],"(CL)":[147],"those":[150],"low":[152],"similarities.":[153,212],"We":[154],"empirically":[155],"demonstrate":[156],"SSNCut":[160,177,196],"clustering,":[164],"using":[166],"100":[167],"data":[168],"sets":[169],"records.":[172],"Experimental":[173],"results":[174],"show":[175],"that":[176,206,217],"outperformed":[178,205],"method":[182],"several":[184],"well-known":[185],"methods,":[188],"being":[189],"statistically":[190],"significant.":[191],"Furthermore,":[192],"GC":[203],"type":[210],"Another":[213],"interesting":[214],"finding":[215],"was":[216,237],"ML":[218,241],"more":[220],"effectively":[221],"worked":[222],"than":[223],"CL":[224,227],"constraints,":[225],"since":[226],"include":[229],"around":[230],"10%":[231],"incorrect":[232],"ones,":[233],"whereas":[234],"this":[235],"number":[236],"1%":[239],"constraints.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}