{"id":"https://openalex.org/W2085505597","doi":"https://doi.org/10.5539/cis.v3n1p91","title":"Semantic Clustering for Large-Scale Documents.doc","display_name":"Semantic Clustering for Large-Scale Documents.doc","publication_year":2010,"publication_date":"2010-01-19","ids":{"openalex":"https://openalex.org/W2085505597","doi":"https://doi.org/10.5539/cis.v3n1p91","mag":"2085505597"},"language":"en","primary_location":{"id":"doi:10.5539/cis.v3n1p91","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v3n1p91","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/4377/4304","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ccsenet.org/journal/index.php/cis/article/download/4377/4304","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100773530","display_name":"Ming Liu","orcid":"https://orcid.org/0009-0001-9684-0009"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4390039265","display_name":"PRG S&Tech (South Korea)","ror":"https://ror.org/02sr2ee22","country_code":null,"type":"company","lineage":["https://openalex.org/I4390039265"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ming Liu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology PO box 319, Harbin, Heilongjiang Province, 150001, China","Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology PO box 319, Harbin, Heilongjiang Province, 150001, China","institution_ids":["https://openalex.org/I4210161462","https://openalex.org/I204983213"]},{"raw_affiliation_string":"Computer Science and Technology","institution_ids":["https://openalex.org/I4390039265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100773530"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462","https://openalex.org/I4390039265"],"apc_list":null,"apc_paid":null,"fwci":0.4664,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74366002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9681000113487244,"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":0.9681000113487244,"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":0.9449999928474426,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9444000124931335,"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/computer-science","display_name":"Computer science","score":0.8880497217178345},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7289358377456665},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6685823798179626},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6259868741035461},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5236936807632446},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5076583623886108},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46834298968315125},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44473692774772644},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4387873113155365},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43338093161582947},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41345587372779846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3952980637550354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8880497217178345},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7289358377456665},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6685823798179626},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6259868741035461},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5236936807632446},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5076583623886108},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46834298968315125},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44473692774772644},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4387873113155365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43338093161582947},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41345587372779846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3952980637550354},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5539/cis.v3n1p91","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v3n1p91","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/4377/4304","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5539/cis.v3n1p91","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v3n1p91","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/4377/4304","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G239599399","display_name":null,"funder_award_id":"60435020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4243412236","display_name":null,"funder_award_id":"863 Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2085505597.pdf","grobid_xml":"https://content.openalex.org/works/W2085505597.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W286208473","https://openalex.org/W1710422233","https://openalex.org/W1963847195","https://openalex.org/W2011092306","https://openalex.org/W2015469910","https://openalex.org/W2039752655","https://openalex.org/W2060371459","https://openalex.org/W2066846405","https://openalex.org/W2079153738","https://openalex.org/W2080018251","https://openalex.org/W2081980673","https://openalex.org/W2097221264","https://openalex.org/W2101746535","https://openalex.org/W2122473047","https://openalex.org/W2127994824","https://openalex.org/W2130669657","https://openalex.org/W2138498160","https://openalex.org/W2147163628","https://openalex.org/W2153233077","https://openalex.org/W2162161511","https://openalex.org/W2165464561","https://openalex.org/W2166070360","https://openalex.org/W2168701898","https://openalex.org/W4240965474"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W1795405792","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":{"Along":[0],"with":[1,79],"explosion":[2],"of":[3,66,97],"information,":[4],"how":[5],"to":[6,25,38,72],"cluster":[7,74],"large-scale":[8],"documents":[9,44,47,78,102],"has":[10,106],"become":[11],"more":[12,14],"and":[13,46],"important.":[15],"This":[16,29],"paper":[17],"proposes":[18],"a":[19],"novel":[20],"document":[21,111],"clustering":[22,112],"algorithm":[23,30],"(CLCL)":[24],"solve":[26],"this":[27,59],"problem.":[28],"first":[31],"constructs":[32],"lexical":[33,56],"chains":[34],"from":[35,86],"feature":[36],"space":[37],"reflect":[39],"different":[40,101],"topics":[41],"which":[42],"input":[43],"contain,":[45],"also":[48,90],"can":[49],"be":[50],"separated":[51],"into":[52,82],"clusters":[53],"by":[54],"these":[55],"chains.":[57],"However,":[58],"separation":[60],"is":[61,70],"too":[62],"rough.":[63],"So,":[64],"idea":[65],"self":[67],"organizing":[68],"mapping":[69],"used":[71],"optimize":[73],"partition.":[75],"For":[76],"agglomerating":[77],"semantic":[80,98],"similarities":[81,99],"one":[83],"cluster,":[84],"influences":[85],"similar":[87],"features":[88],"are":[89,103],"considered.":[91],"Experiments":[92],"demonstrate":[93],"that":[94],"because":[95],"effects":[96],"between":[100],"considered,":[104],"CLCL":[105],"better":[107],"performance":[108],"than":[109],"traditional":[110],"algorithms.":[113]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
