{"id":"https://openalex.org/W2028424170","doi":"https://doi.org/10.1109/fskd.2010.5569324","title":"A two-stage feature selection method for text categorization","display_name":"A two-stage feature selection method for text categorization","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W2028424170","doi":"https://doi.org/10.1109/fskd.2010.5569324","mag":"2028424170"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2010.5569324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2010.5569324","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/A5101611041","display_name":"Jiana Meng","orcid":"https://orcid.org/0000-0002-7220-5748"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiana Meng","raw_affiliation_strings":["College of Science, Dalian Nationalities of University, Dalian, China","Department of Computer Science and Engineering, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"College of Science, Dalian Nationalities of University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023931221","display_name":"Hongfei Lin","orcid":"https://orcid.org/0000-0003-0872-7688"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Lin","raw_affiliation_strings":["Department of Computer Science and Engineering, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101611041"],"corresponding_institution_ids":["https://openalex.org/I27357992","https://openalex.org/I61565387"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.20493359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"1492","last_page":"1496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.989300012588501,"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":0.9865000247955322,"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":0.7655683755874634},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.741239070892334},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6324038505554199},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6156085729598999},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.5973663330078125},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.5793164968490601},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5772926807403564},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5669106245040894},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.54013991355896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5377858281135559},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5249588489532471},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.5066774487495422},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4921669363975525},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48872828483581543},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.48036202788352966},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4608596861362457},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.40789344906806946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39325737953186035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16464707255363464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655683755874634},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.741239070892334},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6324038505554199},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6156085729598999},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.5973663330078125},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.5793164968490601},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5772926807403564},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5669106245040894},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.54013991355896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5377858281135559},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5249588489532471},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.5066774487495422},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4921669363975525},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48872828483581543},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.48036202788352966},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4608596861362457},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.40789344906806946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39325737953186035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16464707255363464},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2010.5569324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2010.5569324","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":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1549887922","https://openalex.org/W1810646324","https://openalex.org/W1970974276","https://openalex.org/W2035411645","https://openalex.org/W2103333826","https://openalex.org/W2122324501","https://openalex.org/W2147152072","https://openalex.org/W2148633389","https://openalex.org/W2156909104","https://openalex.org/W2324238452","https://openalex.org/W2435251607","https://openalex.org/W4238546739","https://openalex.org/W6638249524","https://openalex.org/W6675969814","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W2588002110","https://openalex.org/W2111020819","https://openalex.org/W2775171027","https://openalex.org/W4389358025","https://openalex.org/W2373137943","https://openalex.org/W2364497041","https://openalex.org/W2042126095","https://openalex.org/W2347927631","https://openalex.org/W1553347578","https://openalex.org/W2076813128"],"abstract_inverted_index":{"Feature":[0],"selection":[1,28,36,163,199],"for":[2],"text":[3,45],"classification":[4,14,84],"is":[5,116],"a":[6,25,32,59,106,119,149,159,173],"well-studied":[7],"problem":[8],"and":[9,38,67],"the":[10,54,65,73,91,122,129,134,142,167],"goals":[11],"are":[12],"improving":[13],"effectiveness,":[15],"computational":[16],"efficiency,":[17],"or":[18,114],"both.":[19],"In":[20],"this":[21,154],"paper,":[22],"we":[23,157,171,193],"propose":[24],"two-stage":[26,197],"feature":[27,35,162,198],"algorithm":[29],"based":[30,44,180],"on":[31,181],"kind":[33,160],"of":[34,101,141,147,161],"method":[37,164,200],"latent":[39,182],"semantic":[40,74,87,151,176,183],"indexing.":[41],"Traditional":[42],"word-matching":[43],"categorization":[46],"system":[47],"uses":[48],"vector":[49,108,120],"space":[50,62,109,177],"model":[51],"to":[52,63,82,165],"represent":[53,64],"document.":[55],"However,":[56],"it":[57],"needs":[58],"high":[60],"dimensional":[61],"document,":[66],"does":[68],"not":[69,125],"take":[70],"into":[71],"account":[72],"relationship":[75,137],"between":[76,138,178],"terms,":[77],"which":[78,111],"can":[79,89],"also":[80,132],"lead":[81],"poor":[83],"accuracy.":[85],"Latent":[86],"indexing":[88,184],"overcome":[90],"problems":[92],"caused":[93],"by":[94],"using":[95],"statistically":[96],"derived":[97],"conceptual":[98,107],"indices":[99],"instead":[100],"individual":[102],"words.":[103],"It":[104,124],"constructs":[105],"in":[110,121,153],"each":[112],"term":[113,168],"document":[115],"represented":[117],"as":[118],"space.":[123],"only":[126],"greatly":[127],"reduces":[128],"dimensionality":[130],"but":[131],"discovers":[133],"important":[135],"associative":[136],"terms.":[139],"Because":[140],"too":[143],"much":[144],"calculation":[145],"time":[146],"constructing":[148],"new":[150,174],"space,":[152],"algorithm,":[155],"firstly":[156],"apply":[158],"reduce":[166],"dimensions.":[169],"Secondly,":[170],"construct":[172],"reduced":[175],"terms":[179],"method.":[185],"Through":[186],"some":[187],"applications":[188],"involving":[189],"spam":[190],"database":[191],"categorization,":[192],"find":[194],"that":[195],"our":[196],"performs":[201],"better.":[202]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}