{"id":"https://openalex.org/W1591595875","doi":null,"title":"Semantic explorative evaluation of document clustering algorithms","display_name":"Semantic explorative evaluation of document clustering algorithms","publication_year":2013,"publication_date":"2013-11-07","ids":{"openalex":"https://openalex.org/W1591595875","mag":"1591595875"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.6343","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.6343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://fedcsis.org/proceedings/2013/pliks/273.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ieeexplore.ieee.org/document/6643985/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044883724","display_name":"Hung Son Nguyen","orcid":"https://orcid.org/0000-0002-3236-5456","observed_orcids":["https://orcid.org/0000-0002-3236-5456"]},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Hung Son Nguyen","raw_affiliation_strings":["Inst. of Math., Univ. of Warsaw, Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0002-3236-5456","affiliations":[{"raw_affiliation_string":"Inst. of Math., Univ. of Warsaw, Warsaw, Poland","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047030897","display_name":"Sinh Hoa Nguyen","orcid":"https://orcid.org/0000-0003-1184-6223","observed_orcids":["https://orcid.org/0000-0003-1184-6223"]},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Sinh Hoa Nguyen","raw_affiliation_strings":["Inst. of Math., Univ. of Warsaw, Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0003-1184-6223","affiliations":[{"raw_affiliation_string":"Inst. of Math., Univ. of Warsaw, Warsaw, Poland","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067825788","display_name":"Wojciech \u015awieboda","orcid":"https://orcid.org/0000-0002-5265-5784","observed_orcids":["https://orcid.org/0000-0002-5265-5784"]},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Wojciech \u015awieboda","raw_affiliation_strings":["Inst. of Math., Univ. of Warsaw, Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0002-5265-5784","affiliations":[{"raw_affiliation_string":"Inst. of Math., Univ. of Warsaw, Warsaw, Poland","institution_ids":["https://openalex.org/I4654613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4654613"],"apc_list":null,"apc_paid":null,"fwci":1.6557,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84580402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9872999787330627,"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":0.9872999787330627,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0026000000070780516,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.0017000000225380063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.8939999938011169},{"id":"https://openalex.org/keywords/clustering-evaluation","display_name":"cluster validation","score":0.7310000061988831},{"id":"https://openalex.org/keywords/semantic-evaluation","display_name":"semantic evaluation","score":0.6320000290870667},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"minimum description length","score":0.7319999933242798},{"id":"https://openalex.org/keywords/expert-annotation","display_name":"expert annotation","score":0.7770000100135803},{"id":"https://openalex.org/keywords/medical-subject-headings","display_name":"Medical Subject Headings","score":0.9639999866485596},{"id":"https://openalex.org/keywords/biomedical-literature","display_name":"biomedical literature","score":0.4490000009536743},{"id":"https://openalex.org/keywords/search-result-clustering","display_name":"search result clustering","score":0.8539999723434448},{"id":"https://openalex.org/keywords/semantic-search","display_name":"semantic search","score":0.6679999828338623},{"id":"https://openalex.org/keywords/pubmed-central","display_name":"PubMed Central","score":0.6600000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148790597915649},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6888869404792786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6828781962394714},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5833463668823242},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5686792135238647},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.46282416582107544},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.4579888582229614},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4276401698589325},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39501452445983887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3196355104446411},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.157748281955719}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.6343","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.6343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://fedcsis.org/proceedings/2013/pliks/273.pdf","raw_type":"text"},{"id":"mag:1591595875","doi":null,"is_oa":true,"landing_page_url":"http://ieeexplore.ieee.org/document/6643985/","pdf_url":null,"source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["ddh","doaj","jufo-1","norway-1","oarl"],"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Federated Conference on Computer Science and Information Systems","raw_type":null}],"best_oa_location":{"id":"mag:1591595875","doi":null,"is_oa":true,"landing_page_url":"http://ieeexplore.ieee.org/document/6643985/","pdf_url":null,"source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["ddh","doaj","jufo-1","norway-1","oarl"],"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Federated Conference on Computer Science and Information Systems","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1515984610","https://openalex.org/W1532325895","https://openalex.org/W1533168581","https://openalex.org/W1562753845","https://openalex.org/W2029017735","https://openalex.org/W2033403400","https://openalex.org/W2040888993","https://openalex.org/W2090287317","https://openalex.org/W2097743039","https://openalex.org/W2098146716","https://openalex.org/W2109130989","https://openalex.org/W2118608338","https://openalex.org/W2127218421","https://openalex.org/W2161940749"],"related_works":["https://openalex.org/W66294809","https://openalex.org/W2023747169","https://openalex.org/W170118813","https://openalex.org/W2902541016","https://openalex.org/W1583799796","https://openalex.org/W4242260465","https://openalex.org/W2077490850","https://openalex.org/W2524228334","https://openalex.org/W2168022112","https://openalex.org/W1867952251"],"abstract_inverted_index":{"Abstract\u2014In":[0],"this":[1,41],"paper,":[2],"we":[3],"investigate":[4],"the":[5,33,54,72,77,82,100,114,133,146],"problem":[6],"of":[7,10,26,53,69,71,113,132],"quality":[8],"analysis":[9],"clustering":[11,144],"results":[12],"using":[13,102,145],"semantic":[14,122,139],"annotations":[15],"given":[16],"by":[17,48,99],"experts.":[18],"We":[19,75,136],"propose":[20],"a":[21,111,120,130],"novel":[22],"approach":[23],"to":[24],"construction":[25],"evaluation":[27,56,79],"measure,":[28,43],"which":[29,128],"is":[30,50,110,129],"based":[31],"on":[32,81,116],"Minimal":[34],"Description":[35],"Length":[36],"(MDL)":[37],"principle.":[38],"In":[39],"fact":[40],"proposed":[42,78,147],"called":[44],"SEE":[45],"(Semantic":[46],"Evaluation":[47],"Exploration),":[49],"an":[51],"improvement":[52],"existing":[55],"methods":[57],"such":[58],"as":[59],"Rand":[60],"Index":[61],"or":[62],"Normalized":[63],"Mutual":[64],"Information.":[65],"It":[66],"fixes":[67],"some":[68],"weaknesses":[70],"original":[73],"methods.":[74],"illustrate":[76],"method":[80],"freely":[83],"accessible":[84],"biomedical":[85],"research":[86,115],"articles":[87,93],"from":[88,94],"Pubmed":[89,95],"Central":[90,96],"(PMC).":[91],"Many":[92],"are":[97],"annotated":[98],"experts":[101],"Medical":[103],"Subject":[104],"Headings":[105],"(MeSH)":[106],"thesaurus.":[107],"This":[108],"paper":[109],"part":[112,131],"designing":[117],"and":[118],"developing":[119],"dialog-based":[121],"search":[123,142],"engine":[124],"for":[125,141],"SONCA":[126],"system1":[127],"SYNAT":[134],"project2.":[135],"compare":[137],"different":[138],"techniques":[140],"result":[143],"measure.":[148],"I.":[149]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}
