{"id":"https://openalex.org/W2161928750","doi":"https://doi.org/10.1109/hicss.2006.129","title":"Document Clustering with Semantic Analysis","display_name":"Document Clustering with Semantic Analysis","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2161928750","doi":"https://doi.org/10.1109/hicss.2006.129","mag":"2161928750"},"language":"en","primary_location":{"id":"doi:10.1109/hicss.2006.129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hicss.2006.129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th Annual Hawaii International Conference on System Sciences (HICSS'06)","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/A5100424490","display_name":"Yong Wang","orcid":"https://orcid.org/0000-0002-8601-8302"},"institutions":[{"id":"https://openalex.org/I99041443","display_name":"Mississippi State University","ror":"https://ror.org/0432jq872","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I99041443"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yong Wang","raw_affiliation_strings":["Department of Computer Science & Engineering, Mississippi State University, MS, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Mississippi State University, MS, USA","institution_ids":["https://openalex.org/I99041443"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110266967","display_name":"Julia Hodges","orcid":null},"institutions":[{"id":"https://openalex.org/I99041443","display_name":"Mississippi State University","ror":"https://ror.org/0432jq872","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I99041443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Hodges","raw_affiliation_strings":["Department of Computer Science & Engineering, Mississippi State University, MS, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Mississippi State University, MS, USA","institution_ids":["https://openalex.org/I99041443"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100424490"],"corresponding_institution_ids":["https://openalex.org/I99041443"],"apc_list":null,"apc_paid":null,"fwci":3.2242,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.92274084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"54c","last_page":"54c"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9968000054359436,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965000152587891,"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":0.9959999918937683,"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":0.7791568040847778},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7781610488891602},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.7351773381233215},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.6597552299499512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.525686502456665},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.516848623752594},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.49806833267211914},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46946871280670166},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.45828738808631897},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45010679960250854},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4394731819629669},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4266747832298279},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40881210565567017},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3560044765472412},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.354525625705719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791568040847778},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7781610488891602},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7351773381233215},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.6597552299499512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.525686502456665},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.516848623752594},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.49806833267211914},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46946871280670166},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.45828738808631897},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45010679960250854},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4394731819629669},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4266747832298279},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40881210565567017},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3560044765472412},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.354525625705719},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hicss.2006.129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hicss.2006.129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th Annual Hawaii International Conference on System Sciences (HICSS'06)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.100.1462","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.100.1462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csdl.computer.org/comp/proceedings/hicss/2006/2507/03/250730054c.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W30457518","https://openalex.org/W58300928","https://openalex.org/W77382272","https://openalex.org/W184076178","https://openalex.org/W208128215","https://openalex.org/W1501500081","https://openalex.org/W1546703457","https://openalex.org/W1557757161","https://openalex.org/W1561908597","https://openalex.org/W1569415500","https://openalex.org/W1647729745","https://openalex.org/W1651093245","https://openalex.org/W1659833910","https://openalex.org/W1861147070","https://openalex.org/W1940552124","https://openalex.org/W1956559956","https://openalex.org/W1978394996","https://openalex.org/W1996764654","https://openalex.org/W2018560257","https://openalex.org/W2021294551","https://openalex.org/W2038721957","https://openalex.org/W2056105869","https://openalex.org/W2081980673","https://openalex.org/W2100935296","https://openalex.org/W2102381086","https://openalex.org/W2116300950","https://openalex.org/W2117805756","https://openalex.org/W2136480620","https://openalex.org/W2140190241","https://openalex.org/W2140405352","https://openalex.org/W2140887277","https://openalex.org/W2142120379","https://openalex.org/W2158524254","https://openalex.org/W2161377381","https://openalex.org/W2186685905","https://openalex.org/W2325227998","https://openalex.org/W2404470863","https://openalex.org/W2534712034","https://openalex.org/W4235505822","https://openalex.org/W4241122026","https://openalex.org/W4255095576","https://openalex.org/W4285719527","https://openalex.org/W6603139500","https://openalex.org/W6607456971","https://openalex.org/W6629971530","https://openalex.org/W6634008025","https://openalex.org/W6636975626","https://openalex.org/W6637231022","https://openalex.org/W6640516368","https://openalex.org/W6675339850","https://openalex.org/W6681340555","https://openalex.org/W6836850637"],"related_works":["https://openalex.org/W1500125366","https://openalex.org/W2063335787","https://openalex.org/W2551770406","https://openalex.org/W1557970708","https://openalex.org/W2137763598","https://openalex.org/W2611108488","https://openalex.org/W1575842006","https://openalex.org/W1990330161","https://openalex.org/W1996059221","https://openalex.org/W2029157577"],"abstract_inverted_index":{"Document":[0],"clustering":[1,106,143],"generates":[2],"clusters":[3],"from":[4],"the":[5,23,28,33,39,44,48,59,71,77,83,101,109,116],"whole":[6],"document":[7,34,63,87,105],"collection":[8],"automatically":[9],"and":[10,19,47,123],"is":[11],"used":[12,37],"in":[13,32,94],"many":[14],"fields,":[15],"including":[16],"data":[17],"mining":[18],"information":[20],"retrieval.":[21],"In":[22,65,132],"traditional":[24],"vector":[25,85],"space":[26],"model,":[27],"unique":[29],"words":[30,56,80,122,127],"occurring":[31],"set":[35],"are":[36,128],"as":[38],"features.":[40],"But":[41,108],"because":[42],"of":[43,54,61,79,103,126,140],"synonym":[45],"problem":[46],"polysemous":[49],"problem,":[50],"such":[51],"a":[52,62],"bag":[53],"original":[55,120],"cannot":[57],"represent":[58],"content":[60],"precisely.":[64],"this":[66,133],"paper,":[67,134],"we":[68,135],"investigate":[69],"using":[70,97,119,124],"sense":[72,78,98],"disambiguation":[73],"method":[74],"to":[75,81],"identify":[76],"construct":[82],"feature":[84],"for":[86,145],"representation.":[88],"Our":[89],"experimental":[90],"results":[91],"demonstrate":[92],"that":[93,115],"most":[95],"conditions,":[96],"can":[99],"improve":[100],"performance":[102],"our":[104],"system.":[107],"comprehensive":[110],"statistical":[111],"analysis":[112],"performed":[113],"indicates":[114],"differences":[117],"between":[118],"single":[121],"senses":[125],"not":[129],"statistically":[130],"significant.":[131],"also":[136],"provide":[137],"an":[138],"evaluation":[139],"several":[141],"basic":[142],"algorithms":[144],"algorithm":[146],"selection.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}