{"id":"https://openalex.org/W4220765732","doi":"https://doi.org/10.1587/transinf.2021edp7144","title":"A Method of K-Means Clustering Based on TF-IDF for Software Requirements Documents Written in Chinese Language","display_name":"A Method of K-Means Clustering Based on TF-IDF for Software Requirements Documents Written in Chinese Language","publication_year":2022,"publication_date":"2022-03-31","ids":{"openalex":"https://openalex.org/W4220765732","doi":"https://doi.org/10.1587/transinf.2021edp7144"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2021edp7144","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7144","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/4/E105.D_2021EDP7144/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/4/E105.D_2021EDP7144/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032747681","display_name":"Jing Zhu","orcid":"https://orcid.org/0000-0001-5625-1480"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing ZHU","raw_affiliation_strings":["Command and Control Engineering College, Army Engineering University of PLA","Training Management Department, Navy Command College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Command and Control Engineering College, Army Engineering University of PLA","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Training Management Department, Navy Command College","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076283897","display_name":"Song Huang","orcid":"https://orcid.org/0000-0003-0289-9390"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song HUANG","raw_affiliation_strings":["Command and Control Engineering College, Army Engineering University of PLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Command and Control Engineering College, Army Engineering University of PLA","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075390889","display_name":"Yaqing Shi","orcid":"https://orcid.org/0000-0001-5691-8484"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqing SHI","raw_affiliation_strings":["Command and Control Engineering College, Army Engineering University of PLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Command and Control Engineering College, Army Engineering University of PLA","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007049772","display_name":"Kaishun Wu","orcid":"https://orcid.org/0000-0002-7756-7529"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaishun WU","raw_affiliation_strings":["Command and Control Engineering College, Army Engineering University of PLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Command and Control Engineering College, Army Engineering University of PLA","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027173610","display_name":"Yanqiu WANG","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115494","display_name":"Baogang Group (China)","ror":"https://ror.org/01rt7y457","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115494"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanqiu WANG","raw_affiliation_strings":["Baopo technology Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baopo technology Co. Ltd","institution_ids":["https://openalex.org/I4210115494"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032747681"],"corresponding_institution_ids":["https://openalex.org/I4210163363"],"apc_list":null,"apc_paid":null,"fwci":0.7611,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73187295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"E105.D","issue":"4","first_page":"736","last_page":"754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10260","display_name":"Software Engineering Research","score":0.9850000143051147,"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/T13832","display_name":"Advanced Decision-Making Techniques","score":0.9596999883651733,"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":0.8822011947631836},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7348442673683167},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7011330723762512},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5481614470481873},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5298290848731995},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.525716245174408},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5222662091255188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5194793939590454},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5130990743637085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4851280152797699},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4400544762611389},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40736058354377747},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3835078179836273},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12666821479797363},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.07977840304374695},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07146185636520386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8822011947631836},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7348442673683167},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7011330723762512},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5481614470481873},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5298290848731995},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.525716245174408},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5222662091255188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5194793939590454},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5130990743637085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4851280152797699},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4400544762611389},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40736058354377747},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3835078179836273},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12666821479797363},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.07977840304374695},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07146185636520386},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2021edp7144","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7144","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/4/E105.D_2021EDP7144/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2021edp7144","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7144","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/4/E105.D_2021EDP7144/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4220765732.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W190190587","https://openalex.org/W2005881232","https://openalex.org/W2032254535","https://openalex.org/W2178196558","https://openalex.org/W2231866622","https://openalex.org/W2353429781","https://openalex.org/W2590881928","https://openalex.org/W2792696229","https://openalex.org/W2897098357","https://openalex.org/W3010667076","https://openalex.org/W3213422946"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W1629127207","https://openalex.org/W138569904","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W3092506759","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"Nowadays":[0],"there":[1],"is":[2,37,107,113],"no":[3],"way":[4],"to":[5,39,117],"automatically":[6],"obtain":[7],"the":[8,20,28,47,67,72,103,110,120,125,129,168,174],"function":[9,13,73,154,180],"points":[10,155],"when":[11,109],"using":[12],"point":[14],"analyze":[15],"(FPA)":[16],"method,":[17],"especially":[18],"for":[19,66,136,150],"requirement":[21,93],"documents":[22,94,159],"written":[23,95,160],"in":[24,33,57,96,161,173],"Chinese":[25,31,43,97],"language.":[26,98],"Considering":[27],"characteristics":[29],"of":[30,71,81,122,128,132,142,153,170,177],"grammar":[32],"words":[34,41],"segmentation,":[35],"it":[36],"necessary":[38],"divide":[40],"accurately":[42],"words,":[44],"so":[45],"that":[46,102],"subsequent":[48],"entity":[49],"recognition":[50],"and":[51,87,119,140,165],"disambiguation":[52],"can":[53],"be":[54],"carried":[55],"out":[56],"a":[58,63,79],"smaller":[59],"range,":[60],"which":[61],"lays":[62],"solid":[64],"foundation":[65],"efficient":[68],"automatic":[69,151,178],"extraction":[70,152],"points.":[74,181],"Therefore,":[75],"this":[76,138,143],"paper":[77],"proposed":[78],"method":[80,139],"K-Means":[82],"clustering":[83,105],"based":[84],"on":[85],"TF-IDF,":[86],"conducts":[88],"experiments":[89],"with":[90],"24":[91],"software":[92,157],"The":[99],"results":[100],"show":[101],"best":[104],"effect":[106],"achieved":[108],"extracted":[111],"information":[112],"retained":[114],"by":[115],"55%":[116],"75%":[118],"number":[121,131],"clusters":[123],"takes":[124],"middle":[126],"value":[127],"total":[130],"clusters.":[133],"Not":[134],"only":[135],"Chinese,":[137],"conclusion":[141],"paper,":[144],"but":[145],"provides":[146],"an":[147],"important":[148],"reference":[149],"from":[156],"requirements":[158],"other":[162],"Oriental":[163],"languages,":[164],"also":[166],"fills":[167],"gaps":[169],"data":[171],"preprocessing":[172],"early":[175],"stage":[176],"calculation":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}
