{"id":"https://openalex.org/W2124089375","doi":"https://doi.org/10.1145/1141753.1141802","title":"A comprehensive comparison study of document clustering for a biomedical digital library MEDLINE","display_name":"A comprehensive comparison study of document clustering for a biomedical digital library MEDLINE","publication_year":2006,"publication_date":"2006-06-11","ids":{"openalex":"https://openalex.org/W2124089375","doi":"https://doi.org/10.1145/1141753.1141802","mag":"2124089375"},"language":"en","primary_location":{"id":"doi:10.1145/1141753.1141802","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","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/A5011662726","display_name":"Illhoi Yoo","orcid":"https://orcid.org/0000-0003-2536-3660"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Illhoi Yoo","raw_affiliation_strings":["Drexel University, Philadelphia, PA","Coll. of Inf. Sci. & Technol., Drexel Univ., Philadelphia, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Coll. of Inf. Sci. & Technol., Drexel Univ., Philadelphia, PA#TAB#","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101569677","display_name":"Xiaohua Hu","orcid":"https://orcid.org/0000-0001-6942-490X"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohua Hu","raw_affiliation_strings":["Drexel University, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":5.5941,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.95616182,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"220","last_page":"229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9986000061035156,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9986000061035156,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9980000257492065,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9884999990463257,"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":0.7891086339950562},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7840335369110107},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7240002155303955},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6792181730270386},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5886083245277405},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.5658878087997437},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.508721649646759},{"id":"https://openalex.org/keywords/biomedicine","display_name":"Biomedicine","score":0.48542770743370056},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.48270702362060547},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4663003981113434},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4318057596683502},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4125766158103943},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.3340684175491333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2597205638885498},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.16238027811050415},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.160816490650177},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.1231735348701477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891086339950562},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7840335369110107},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7240002155303955},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6792181730270386},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5886083245277405},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.5658878087997437},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.508721649646759},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.48542770743370056},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.48270702362060547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4663003981113434},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4318057596683502},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4125766158103943},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.3340684175491333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2597205638885498},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.16238027811050415},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.160816490650177},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.1231735348701477},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1141753.1141802","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.135.8811","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.8811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://idea.library.drexel.edu/bitstream/1860/915/3/2006150019.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.538.7345","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.538.7345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cci.drexel.edu/faculty/thu/research-papers/FP_52_Yoo.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W181283514","https://openalex.org/W1525341925","https://openalex.org/W1620204465","https://openalex.org/W1651093245","https://openalex.org/W1672197616","https://openalex.org/W1971318281","https://openalex.org/W1979270574","https://openalex.org/W1996764654","https://openalex.org/W2065811242","https://openalex.org/W2066667100","https://openalex.org/W2070412788","https://openalex.org/W2070670538","https://openalex.org/W2074449313","https://openalex.org/W2081980673","https://openalex.org/W2100958137","https://openalex.org/W2103986443","https://openalex.org/W2133109597","https://openalex.org/W2133249310","https://openalex.org/W2140942285","https://openalex.org/W2145036943","https://openalex.org/W2542057642","https://openalex.org/W2999729612","https://openalex.org/W3139328003","https://openalex.org/W4233939430","https://openalex.org/W4241122026","https://openalex.org/W4254311734","https://openalex.org/W4285719527","https://openalex.org/W4298882835","https://openalex.org/W6677992525"],"related_works":["https://openalex.org/W2592952084","https://openalex.org/W2899601636","https://openalex.org/W2187059365","https://openalex.org/W2118873177","https://openalex.org/W3192757256","https://openalex.org/W2282393731","https://openalex.org/W2992227719","https://openalex.org/W2541044624","https://openalex.org/W2184440854","https://openalex.org/W2124089375"],"abstract_inverted_index":{"Document":[0],"clustering":[1,29,67,77],"has":[2],"been":[3],"used":[4],"for":[5,79,94],"better":[6],"document":[7,9,28,66],"retrieval,":[8],"browsing,":[10],"and":[11,38,44,55,135],"text":[12],"mining":[13],"in":[14,48,149],"digital":[15,147],"library.":[16],"In":[17,58],"this":[18],"paper,":[19],"we":[20,60],"perform":[21],"a":[22,62,86,91,95,104],"comprehensive":[23],"comparison":[24],"study":[25],"of":[26,50,90,97,101],"various":[27],"approaches":[30],"such":[31,73,113,128],"as":[32,74,114,129],"three":[33],"hierarchical":[34],"methods":[35],"(single-link,":[36],"complete-link,":[37],"complete":[39],"link),":[40],"Bisecting":[41],"K-means,":[42,43],"Suffix":[45],"Tree":[46],"Clustering":[47],"terms":[49],"the":[51,53,56,71,99,144],"efficiency,":[52],"effectiveness,":[54],"scalability.":[57],"addition,":[59],"apply":[61],"domain":[63,96],"ontology":[64,72,84],"to":[65,68,107],"investigate":[69],"if":[70],"MeSH":[75],"improves":[76],"qualify":[78],"MEDLINE":[80],"articles.":[81],"Because":[82],"an":[83],"is":[85,103],"formal,":[87],"explicit":[88],"specification":[89],"shared":[92],"conceptualization":[93],"interest,":[98],"use":[100],"ontologies":[102],"natural":[105],"way":[106],"solve":[108],"traditional":[109],"information":[110],"retrieval":[111],"problems":[112],"synonym/hypernym/":[115],"hyponym":[116],"problems.":[117],"We":[118],"conducted":[119],"fairly":[120],"extensive":[121],"experiments":[122],"based":[123],"on":[124,137],"different":[125],"evaluation":[126],"metrics":[127],"misclassification":[130],"index,":[131],"F-measure,":[132],"cluster":[133],"purity,":[134],"Entropy":[136],"very":[138],"large":[139],"article":[140],"sets":[141],"from":[142],"MEDLINE,":[143],"largest":[145],"biomedical":[146],"library":[148],"biomedicine.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}