{"id":"https://openalex.org/W4205279407","doi":"https://doi.org/10.1109/ieem50564.2021.9672875","title":"A Study of Applying Unsupervised Learning Methods for Document Clustering and Automatic Categorization of Software","display_name":"A Study of Applying Unsupervised Learning Methods for Document Clustering and Automatic Categorization of Software","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4205279407","doi":"https://doi.org/10.1109/ieem50564.2021.9672875"},"language":"en","primary_location":{"id":"doi:10.1109/ieem50564.2021.9672875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieem50564.2021.9672875","pdf_url":null,"source":{"id":"https://openalex.org/S4363607822","display_name":"2021 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","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":"2021 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101675126","display_name":"Kaiwen Chen","orcid":"https://orcid.org/0000-0001-6816-6910"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Wen Chen","raw_affiliation_strings":["National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan","Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018423117","display_name":"Chin\u2010Yu Huang","orcid":"https://orcid.org/0000-0003-4931-4572"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chin-Yu Huang","raw_affiliation_strings":["National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan","Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","Institue of Information Systems and Applications, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Institue of Information Systems and Applications, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1626","last_page":"1630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9933000206947327,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9933000206947327,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9860000014305115,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8504252433776855},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7797658443450928},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6821088194847107},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6018433570861816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5006747245788574},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.4969775974750519},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46230000257492065},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.4232550263404846},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4105527102947235},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.383539617061615},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.3130835294723511},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.1896059215068817},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.10060924291610718},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05811193585395813}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8504252433776855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797658443450928},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6821088194847107},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6018433570861816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5006747245788574},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.4969775974750519},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46230000257492065},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.4232550263404846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4105527102947235},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.383539617061615},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.3130835294723511},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.1896059215068817},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.10060924291610718},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05811193585395813}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieem50564.2021.9672875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieem50564.2021.9672875","pdf_url":null,"source":{"id":"https://openalex.org/S4363607822","display_name":"2021 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","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":"2021 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3975554533","display_name":null,"funder_award_id":"MOST 108-2221-E-007-033-MY3,MOST 110-2221-E-007-035-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1902027874","https://openalex.org/W2015583498","https://openalex.org/W2044428238","https://openalex.org/W2072240081","https://openalex.org/W2101234009","https://openalex.org/W2121947440","https://openalex.org/W2132914434","https://openalex.org/W2135029798","https://openalex.org/W2135674549","https://openalex.org/W2148781711","https://openalex.org/W2165401136","https://openalex.org/W2165874743","https://openalex.org/W2744136779","https://openalex.org/W2953320089","https://openalex.org/W2963088772","https://openalex.org/W2963868858","https://openalex.org/W2997975441","https://openalex.org/W3108150468","https://openalex.org/W4235169531","https://openalex.org/W4254240410","https://openalex.org/W6675354045","https://openalex.org/W6676702705","https://openalex.org/W6680012447","https://openalex.org/W6684578312"],"related_works":["https://openalex.org/W13324992","https://openalex.org/W10015831","https://openalex.org/W10697079","https://openalex.org/W2390764","https://openalex.org/W7724241","https://openalex.org/W7857228","https://openalex.org/W15008681","https://openalex.org/W4185409","https://openalex.org/W3383526","https://openalex.org/W4173819"],"abstract_inverted_index":{"Software":[0],"categorization":[1,26,36,64,80],"is":[2,113],"the":[3,13,19,61,90,110],"task":[4],"to":[5,45,59],"group":[6],"software":[7,25,35,63,79],"into":[8],"categories":[9],"that":[10],"briefly":[11],"represent":[12],"behavior":[14],"of":[15,22,107,115],"software.":[16],"However,":[17],"with":[18,75],"rapid":[20],"growth":[21],"software,":[23],"manual":[24],"has":[27,37],"become":[28,38],"almost":[29],"impossible":[30],"and":[31,56,124,134],"expensive.":[32],"Therefore,":[33],"automatic":[34,62,78],"necessary.":[39],"In":[40,66],"this":[41],"paper,":[42],"we":[43,69,84],"propose":[44],"utilize":[46],"two":[47,130],"different":[48],"document":[49],"clustering":[50,95],"methods,":[51],"nonnegative":[52],"matrix":[53],"factorization":[54],"(NMF)":[55],"spectral":[57],"clustering,":[58],"fulfill":[60],"respectively.":[65],"our":[67,73,93],"work,":[68],"not":[70],"only":[71,100],"compare":[72],"performance":[74],"an":[76],"existing":[77],"method":[81],"LACT,":[82,119],"but":[83],"also":[85],"make":[86],"profound":[87],"analysis":[88],"on":[89,129],"difference":[91],"between":[92],"both":[94],"methods.":[96],"Our":[97],"methods":[98],"require":[99],"at":[101,121],"most":[102,122],"about":[103],"1/10":[104],"execution":[105],"time":[106],"LACT":[108],"while":[109],"fastest":[111],"one":[112],"hundreds":[114],"times":[116],"faster":[117],"than":[118],"achieving":[120],"26%":[123],"100%":[125],"better":[126],"performances":[127],"based":[128],"criteria,":[131],"BCubed":[132],"F1-measure":[133],"Adjusted":[135],"Rand":[136],"Index.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}
