{"id":"https://openalex.org/W4386933640","doi":"https://doi.org/10.3390/systems11090483","title":"Adapting Feature Selection Algorithms for the Classification of Chinese Texts","display_name":"Adapting Feature Selection Algorithms for the Classification of Chinese Texts","publication_year":2023,"publication_date":"2023-09-20","ids":{"openalex":"https://openalex.org/W4386933640","doi":"https://doi.org/10.3390/systems11090483"},"language":"en","primary_location":{"id":"doi:10.3390/systems11090483","is_oa":true,"landing_page_url":"https://doi.org/10.3390/systems11090483","pdf_url":"https://www.mdpi.com/2079-8954/11/9/483/pdf?version=1695214400","source":{"id":"https://openalex.org/S4210219410","display_name":"Systems","issn_l":"2079-8954","issn":["2079-8954"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2079-8954/11/9/483/pdf?version=1695214400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100362250","display_name":"Xuan Liu","orcid":"https://orcid.org/0000-0001-5599-2607"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Liu","raw_affiliation_strings":["School of Public Affairs and Administration, University of Electronic Science and Technology of China, Chengdu 611731, China"],"affiliations":[{"raw_affiliation_string":"School of Public Affairs and Administration, University of Electronic Science and Technology of China, Chengdu 611731, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375555","display_name":"Shuang Wang","orcid":"https://orcid.org/0000-0001-5933-074X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Wang","raw_affiliation_strings":["School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102893051","display_name":"Siyu Lu","orcid":"https://orcid.org/0009-0007-7983-9608"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Lu","raw_affiliation_strings":["School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021201289","display_name":"Zhengtong Yin","orcid":"https://orcid.org/0000-0002-9818-9205"},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtong Yin","raw_affiliation_strings":["College of Resource and Environment Engineering, Guizhou University, Guiyang 550025, China"],"affiliations":[{"raw_affiliation_string":"College of Resource and Environment Engineering, Guizhou University, Guiyang 550025, China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382146","display_name":"Xiaolu Li","orcid":"https://orcid.org/0000-0002-8299-7937"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolu Li","raw_affiliation_strings":["School of Geographic Science, Southwest University, Chongqing 400715, China"],"affiliations":[{"raw_affiliation_string":"School of Geographic Science, Southwest University, Chongqing 400715, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023971713","display_name":"Lirong Yin","orcid":"https://orcid.org/0000-0002-5022-610X"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lirong Yin","raw_affiliation_strings":["Department of Geography and Anthropology, Louisiana State University, Baton Rouge, LA 70803, USA"],"affiliations":[{"raw_affiliation_string":"Department of Geography and Anthropology, Louisiana State University, Baton Rouge, LA 70803, USA","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052594084","display_name":"Jiawei Tian","orcid":"https://orcid.org/0000-0001-6398-7461"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Tian","raw_affiliation_strings":["School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062384828","display_name":"Wenfeng Zheng","orcid":"https://orcid.org/0000-0002-8486-1654"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenfeng Zheng","raw_affiliation_strings":["School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5062384828"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":25.051,"has_fulltext":true,"cited_by_count":330,"citation_normalized_percentile":{"value":0.99720999,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"11","issue":"9","first_page":"483","last_page":"483"},"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":0.9955999851226807,"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":0.9952999949455261,"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/feature-selection","display_name":"Feature selection","score":0.7530703544616699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7014369368553162},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6080941557884216},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5860664248466492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5818032026290894},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.559367835521698},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5565224289894104},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.5407626032829285},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5094576478004456},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4810193181037903},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4560219943523407},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.4517216384410858},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4266201853752136},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4178573489189148},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37824755907058716},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3726238012313843}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7530703544616699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7014369368553162},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6080941557884216},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5860664248466492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5818032026290894},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.559367835521698},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5565224289894104},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.5407626032829285},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5094576478004456},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4810193181037903},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4560219943523407},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.4517216384410858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4266201853752136},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4178573489189148},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37824755907058716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3726238012313843},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/systems11090483","is_oa":true,"landing_page_url":"https://doi.org/10.3390/systems11090483","pdf_url":"https://www.mdpi.com/2079-8954/11/9/483/pdf?version=1695214400","source":{"id":"https://openalex.org/S4210219410","display_name":"Systems","issn_l":"2079-8954","issn":["2079-8954"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7803dd34c01c42d4a3b405bf590cf8f5","is_oa":true,"landing_page_url":"https://doaj.org/article/7803dd34c01c42d4a3b405bf590cf8f5","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Systems, Vol 11, Iss 9, p 483 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/systems11090483","is_oa":true,"landing_page_url":"https://doi.org/10.3390/systems11090483","pdf_url":"https://www.mdpi.com/2079-8954/11/9/483/pdf?version=1695214400","source":{"id":"https://openalex.org/S4210219410","display_name":"Systems","issn_l":"2079-8954","issn":["2079-8954"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386933640.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1503487158","https://openalex.org/W1832693441","https://openalex.org/W1974339500","https://openalex.org/W2009190245","https://openalex.org/W2049973339","https://openalex.org/W2082729696","https://openalex.org/W2089870669","https://openalex.org/W2114315281","https://openalex.org/W2117130368","https://openalex.org/W2118020653","https://openalex.org/W2153579005","https://openalex.org/W2155713811","https://openalex.org/W2165612380","https://openalex.org/W2171770604","https://openalex.org/W2194187530","https://openalex.org/W2295002716","https://openalex.org/W2295598076","https://openalex.org/W2317515691","https://openalex.org/W2519106992","https://openalex.org/W2738417325","https://openalex.org/W2750402403","https://openalex.org/W2784182661","https://openalex.org/W2788009253","https://openalex.org/W2883730939","https://openalex.org/W2894231409","https://openalex.org/W2921004873","https://openalex.org/W2921575332","https://openalex.org/W2946235526","https://openalex.org/W2952230511","https://openalex.org/W3081425653","https://openalex.org/W3135387830","https://openalex.org/W3169203486","https://openalex.org/W3187071356","https://openalex.org/W4316655441","https://openalex.org/W4327973200","https://openalex.org/W4379882795","https://openalex.org/W4385454542","https://openalex.org/W6680532216","https://openalex.org/W6683738474","https://openalex.org/W6752918806"],"related_works":["https://openalex.org/W2747837925","https://openalex.org/W2324052717","https://openalex.org/W2614491706","https://openalex.org/W4390352832","https://openalex.org/W3190721986","https://openalex.org/W3203638897","https://openalex.org/W4321635934","https://openalex.org/W4200385031","https://openalex.org/W2086889680","https://openalex.org/W4246466849"],"abstract_inverted_index":{"Text":[0,21],"classification":[1,22,24,65],"has":[2],"been":[3],"highlighted":[4],"as":[5],"the":[6,17,31,37,48,59,63,152,160,178,184,189,192,198,219,234,249,252,261],"key":[7],"process":[8],"to":[9,76,182],"organize":[10],"online":[11],"texts":[12,68,87,172],"for":[13,58,62,82,239],"better":[14],"communication":[15],"in":[16,47,69,224,257,263],"Digital":[18],"Media":[19],"Age.":[20],"establishes":[23],"rules":[25],"based":[26],"on":[27,106,204],"text":[28,40],"features,":[29],"so":[30],"accuracy":[32],"of":[33,39,66,85,109,163,177,191,242,248,251],"feature":[34,60,79,99,220,236,254],"selection":[35,61,80,100,221,237,255],"is":[36,88],"basis":[38],"classification.":[41],"Facing":[42],"fast-increasing":[43],"Chinese":[44,67,86,110],"electronic":[45],"documents":[46],"digital":[49],"environment,":[50],"scholars":[51],"have":[52],"accumulated":[53],"quite":[54],"a":[55,132,143],"few":[56],"algorithms":[57,81,101,194,222],"automatic":[64],"recent":[70],"years.":[71],"However,":[72],"discussion":[73],"about":[74],"how":[75],"adapt":[77],"existing":[78],"various":[83,230],"types":[84,108],"still":[89],"inadequate.":[90],"To":[91],"address":[92],"this,":[93],"this":[94,225],"study":[95,168],"proposes":[96],"three":[97],"improved":[98,253],"and":[102,128,142,187,197,209,260],"tests":[103],"their":[104],"performance":[105,190,228],"different":[107,175],"texts.":[111],"These":[112],"include":[113],"an":[114],"enhanced":[115,150],"CHI":[116],"square":[117,135],"with":[118,151,195],"mutual":[119],"information":[120],"(MI)":[121],"algorithm,":[122,137,157],"which":[123,138,158],"simultaneously":[124],"introduces":[125],"word":[126,164],"frequency":[127,147],"term":[129,133,144],"adjustment":[130],"(CHMI);":[131],"frequency\u2013CHI":[134],"(TF\u2013CHI)":[136],"enhances":[139],"weight":[140],"calculation;":[141],"frequency\u2013inverse":[145],"document":[146],"(TF\u2013IDF)":[148],"algorithm":[149],"extreme":[153],"gradient":[154],"boosting":[155],"(XGBoost)":[156],"improves":[159],"algorithm\u2019s":[161],"ability":[162],"filtering":[165],"(TF\u2013XGBoost).":[166],"This":[167],"randomly":[169],"chooses":[170],"3000":[171],"from":[173],"six":[174],"categories":[176],"Sogou":[179],"news":[180,231],"corpus":[181,243],"obtain":[183],"confusion":[185],"matrix":[186],"evaluate":[188],"new":[193],"precision":[196],"F1-score.":[199],"Experimental":[200],"comparisons":[201],"are":[202,244,265],"conducted":[203],"support":[205],"vector":[206],"machine":[207],"(SVM)":[208],"naive":[210],"Bayes":[211],"(NB)":[212],"classifiers.":[213],"The":[214],"experimental":[215],"results":[216],"demonstrate":[217],"that":[218],"proposed":[223],"paper":[226],"improve":[227],"across":[229],"corpora,":[232],"although":[233],"best":[235],"schemes":[238],"each":[240],"type":[241],"different.":[245],"Further":[246],"studies":[247],"application":[250],"methods":[256],"other":[258],"languages":[259],"improvement":[262],"classifiers":[264],"suggested.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":99},{"year":2023,"cited_by_count":17},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":31},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}