{"id":"https://openalex.org/W1984223097","doi":"https://doi.org/10.1109/fskd.2010.5569827","title":"A feature selection method for document clustering based on part-of-speech and word co-occurrence","display_name":"A feature selection method for document clustering based on part-of-speech and word co-occurrence","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W1984223097","doi":"https://doi.org/10.1109/fskd.2010.5569827","mag":"1984223097"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2010.5569827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2010.5569827","pdf_url":null,"source":{"id":"https://openalex.org/S4363608217","display_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","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/A5014957271","display_name":"Zitao Liu","orcid":"https://orcid.org/0000-0003-0491-307X"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zitao Liu","raw_affiliation_strings":["International School of Software, Wuhan University of China, Wuhan, China","International School of Software, WuHan University, China#TAB#"],"affiliations":[{"raw_affiliation_string":"International School of Software, Wuhan University of China, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"International School of Software, WuHan University, China#TAB#","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210504","display_name":"Wenchao Yu","orcid":"https://orcid.org/0000-0002-2480-448X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchao Yu","raw_affiliation_strings":["International School of Software, Wuhan University of China, Wuhan, China","International School of Software, WuHan University, China#TAB#"],"affiliations":[{"raw_affiliation_string":"International School of Software, Wuhan University of China, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"International School of Software, WuHan University, China#TAB#","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102084049","display_name":"Yalan Deng","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yalan Deng","raw_affiliation_strings":["International School of Software, Wuhan University of China, Wuhan, China","International School of Software, WuHan University, China#TAB#"],"affiliations":[{"raw_affiliation_string":"International School of Software, Wuhan University of China, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"International School of Software, WuHan University, China#TAB#","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781631","display_name":"Yongtao Wang","orcid":"https://orcid.org/0000-0003-1379-2206"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongtao Wang","raw_affiliation_strings":["International School of Software, Wuhan University of China, Wuhan, China","International School of Software, WuHan University, China#TAB#"],"affiliations":[{"raw_affiliation_string":"International School of Software, Wuhan University of China, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"International School of Software, WuHan University, China#TAB#","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031392746","display_name":"Zhiqi Bian","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Bian","raw_affiliation_strings":["International School of Software, Wuhan University of China, Wuhan, China","International School of Software, WuHan University, China#TAB#"],"affiliations":[{"raw_affiliation_string":"International School of Software, Wuhan University of China, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"International School of Software, WuHan University, China#TAB#","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014957271"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":1.4294,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81404175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2331","last_page":"2334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9940000176429749,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9829999804496765,"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":0.8048044443130493},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6823176145553589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6670944690704346},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6658263802528381},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5538371205329895},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.538478672504425},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5116470456123352},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5078654885292053},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4726879894733429},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.46574485301971436},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4601050615310669},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45585522055625916},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.440575510263443},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4108700752258301},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3613680899143219},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3416876196861267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07764589786529541},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07666850090026855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8048044443130493},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6823176145553589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6670944690704346},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6658263802528381},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5538371205329895},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.538478672504425},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5116470456123352},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5078654885292053},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4726879894733429},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.46574485301971436},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4601050615310669},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45585522055625916},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.440575510263443},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4108700752258301},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3613680899143219},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3416876196861267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07764589786529541},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07666850090026855},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2010.5569827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2010.5569827","pdf_url":null,"source":{"id":"https://openalex.org/S4363608217","display_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1526719228","https://openalex.org/W1970974276","https://openalex.org/W2005422315","https://openalex.org/W2063198646","https://openalex.org/W2097292227","https://openalex.org/W2105645651","https://openalex.org/W2116237179","https://openalex.org/W2133462743","https://openalex.org/W2151100221","https://openalex.org/W2170597658","https://openalex.org/W2172159410","https://openalex.org/W2435251607","https://openalex.org/W2538688051","https://openalex.org/W4237265687","https://openalex.org/W6631457093","https://openalex.org/W6677504887","https://openalex.org/W6682569070","https://openalex.org/W6684886601","https://openalex.org/W6685115837","https://openalex.org/W6717827561","https://openalex.org/W6728946187"],"related_works":["https://openalex.org/W1569283511","https://openalex.org/W2380784125","https://openalex.org/W4236193183","https://openalex.org/W3004057759","https://openalex.org/W2889085215","https://openalex.org/W2914806737","https://openalex.org/W2053866214","https://openalex.org/W2607505004","https://openalex.org/W2231795205","https://openalex.org/W4308273529"],"abstract_inverted_index":{"Feature":[0],"selection":[1,40,58],"is":[2],"a":[3,7,27,55,142],"process":[4],"which":[5],"chooses":[6],"subset":[8],"from":[9,107],"the":[10,31,43,67,75,99,104],"original":[11,22],"feature":[12,20,39,57],"set":[13],"according":[14],"to":[15,79,95,110,121],"some":[16,112],"rules.":[17],"The":[18,130],"selected":[19],"retains":[21],"physical":[23],"meaning":[24],"and":[25,33,63,88,114,117,140],"provides":[26],"better":[28,138],"understanding":[29],"for":[30],"data":[32],"learning":[34],"process.":[35],"However,":[36],"few":[37],"modern":[38],"approaches":[41],"take":[42],"advantage":[44],"of":[45,69,82,126],"features'":[46],"context":[47],"information.":[48],"Based":[49],"on":[50,61],"this":[51],"analysis,":[52],"we":[53,73,86,102],"propose":[54],"novel":[56],"method":[59,135],"based":[60],"part-of-speech":[62,77,94],"word":[64],"co-occurrence.":[65],"According":[66],"components":[68],"Chinese":[70],"document":[71,127],"text,":[72],"utilize":[74],"words'":[76],"attributes":[78],"filter":[80],"lots":[81],"meaningless":[83],"terms.":[84],"Then":[85],"define":[87],"use":[89,103,115],"co-occurrence":[90],"words":[91],"by":[92],"their":[93],"select":[96,137],"features.":[97],"In":[98],"evaluating":[100],"process,":[101],"text":[105],"corpus":[106],"Sogou":[108],"Lab":[109],"do":[111],"experiments":[113],"Entropy":[116],"Precision":[118],"as":[119],"criteria":[120],"give":[122],"an":[123],"objective":[124],"evaluation":[125],"clustering":[128,145],"performance.":[129,146],"results":[131],"show":[132],"that":[133],"our":[134],"can":[136],"features":[139],"get":[141],"more":[143],"pleasant":[144]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}