{"id":"https://openalex.org/W4220893331","doi":"https://doi.org/10.3390/sym14030567","title":"A Novel Classification Method Based on a Two-Phase Technique for Learning Imbalanced Text Data","display_name":"A Novel Classification Method Based on a Two-Phase Technique for Learning Imbalanced Text Data","publication_year":2022,"publication_date":"2022-03-13","ids":{"openalex":"https://openalex.org/W4220893331","doi":"https://doi.org/10.3390/sym14030567"},"language":"en","primary_location":{"id":"doi:10.3390/sym14030567","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym14030567","pdf_url":"https://www.mdpi.com/2073-8994/14/3/567/pdf?version=1647335774","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"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":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/14/3/567/pdf?version=1647335774","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028150954","display_name":"Der\u2010Chiang Li","orcid":"https://orcid.org/0000-0002-0887-1308"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Der-Chiang Li","raw_affiliation_strings":["Department of Industrial and Information Management, National Cheng Kung University, Tainan City 70101, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Industrial and Information Management, National Cheng Kung University, Tainan City 70101, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040570918","display_name":"Szu-Chou Chen","orcid":"https://orcid.org/0000-0003-0192-2675"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Szu-Chou Chen","raw_affiliation_strings":["Institute of Information Management, National Cheng Kung University, Tainan City 70101, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Management, National Cheng Kung University, Tainan City 70101, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070813317","display_name":"Yao-San Lin","orcid":"https://orcid.org/0000-0002-5922-5971"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yao-San Lin","raw_affiliation_strings":["Singapore Centre for Chinese Language, Nanyang Technological University, Singapore 279623, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Centre for Chinese Language, Nanyang Technological University, Singapore 279623, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011526752","display_name":"Wen-Yen Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Yen Hsu","raw_affiliation_strings":["Institute of Information Management, National Cheng Kung University, Tainan City 70101, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Management, National Cheng Kung University, Tainan City 70101, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028150954"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.5303,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69516013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"14","issue":"3","first_page":"567","last_page":"567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9990000128746033,"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8173264265060425},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7201964855194092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7023492455482483},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6617064476013184},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5841009020805359},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5381461381912231},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.47831037640571594},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45230650901794434},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4197162389755249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173264265060425},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7201964855194092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7023492455482483},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6617064476013184},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5841009020805359},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5381461381912231},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47831037640571594},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45230650901794434},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4197162389755249},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/sym14030567","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym14030567","pdf_url":"https://www.mdpi.com/2073-8994/14/3/567/pdf?version=1647335774","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"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":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:333520de20df45d59e04bfad3ab22b0b","is_oa":true,"landing_page_url":"https://doaj.org/article/333520de20df45d59e04bfad3ab22b0b","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":"Symmetry, Vol 14, Iss 3, p 567 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/14/3/567/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/sym14030567","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry; Volume 14; Issue 3; Pages: 567","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym14030567","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym14030567","pdf_url":"https://www.mdpi.com/2073-8994/14/3/567/pdf?version=1647335774","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"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":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3623350938","display_name":null,"funder_award_id":"MOST-110-2221-E-006-194","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220893331.pdf","grobid_xml":"https://content.openalex.org/works/W4220893331.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1551909886","https://openalex.org/W1984323748","https://openalex.org/W1993220166","https://openalex.org/W1994866363","https://openalex.org/W1996216253","https://openalex.org/W2005918389","https://openalex.org/W2020355555","https://openalex.org/W2023158516","https://openalex.org/W2032617530","https://openalex.org/W2048195127","https://openalex.org/W2066072428","https://openalex.org/W2083660761","https://openalex.org/W2088220893","https://openalex.org/W2099550922","https://openalex.org/W2104167780","https://openalex.org/W2108564850","https://openalex.org/W2112119668","https://openalex.org/W2118585731","https://openalex.org/W2118978333","https://openalex.org/W2125069507","https://openalex.org/W2132314509","https://openalex.org/W2132791018","https://openalex.org/W2149024119","https://openalex.org/W2153635508","https://openalex.org/W2214674395","https://openalex.org/W2410415416","https://openalex.org/W2520828129","https://openalex.org/W2586733088","https://openalex.org/W2594674086","https://openalex.org/W2789715252","https://openalex.org/W2792881769","https://openalex.org/W2836242602","https://openalex.org/W2917459525","https://openalex.org/W2963626623","https://openalex.org/W2969876961","https://openalex.org/W3010094765","https://openalex.org/W3047383742","https://openalex.org/W3055187757","https://openalex.org/W3175395877","https://openalex.org/W3211597267","https://openalex.org/W4200127250","https://openalex.org/W4226199246","https://openalex.org/W4239510810","https://openalex.org/W6636982025","https://openalex.org/W6664464457","https://openalex.org/W6677656871","https://openalex.org/W6677954473"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"The":[0,178],"problem":[1],"of":[2,12,18,37,59,174],"imbalanced":[3,20,72,93],"data":[4,25,82,95],"has":[5],"a":[6,35,46,64,79,156,188],"heavy":[7],"impact":[8],"on":[9],"the":[10,16,30,54,98,133,139,147,172,175,183,193,209],"performance":[11,190],"learning":[13,69,90,105,148,210],"models.":[14],"In":[15,107,116,145],"case":[17],"an":[19,124,161],"text":[21,94],"dataset,":[22,195],"minority":[23,38],"class":[24],"are":[26,112,121,153],"often":[27],"classified":[28,137],"to":[29,49,52,77,88,100,159,170,187,192],"majority":[31],"class,":[32],"resulting":[33],"in":[34,130,150],"loss":[36],"information":[39],"and":[40,96,201],"low":[41],"accuracy.":[42],"Thus,":[43],"it":[44],"is":[45,136],"serious":[47],"challenge":[48],"determine":[50],"how":[51],"tackle":[53],"high":[55],"imbalance":[56],"ratio":[57],"distribution":[58],"datasets.":[60],"Here,":[61],"we":[62],"propose":[63],"novel":[65],"classification":[66],"method":[67,80,185,206],"for":[68,81,102],"tasks":[70,91],"with":[71,92,155,196],"test":[73],"data.":[74],"It":[75],"aims":[76],"construct":[78],"preprocessing":[83],"that":[84,182,203],"researchers":[85],"can":[86],"apply":[87],"their":[89],"save":[97],"efforts":[99],"search":[101],"more":[103],"dedicated":[104],"tools.":[106],"our":[108],"proposed":[109,176,184],"method,":[110],"there":[111],"two":[113],"core":[114],"stages.":[115],"stage":[117,131],"one,":[118],"balanced":[119,134],"datasets":[120],"generated":[122],"using":[123,138],"asymmetric":[125],"cost-sensitive":[126,141],"support":[127,142],"vector":[128,143],"machine;":[129],"two,":[132],"dataset":[135,167],"symmetric":[140],"machine.":[144],"addition,":[146],"parameters":[149],"both":[151],"stages":[152],"adjusted":[154],"genetic":[157],"algorithm":[158],"create":[160],"optimal":[162],"model.":[163],"A":[164],"Yelp":[165],"review":[166],"was":[168],"used":[169],"validate":[171],"effectiveness":[173],"method.":[177],"experimental":[179],"results":[180],"showed":[181],"led":[186],"better":[189],"subject":[191],"targeted":[194],"at":[197],"least":[198],"75%":[199],"accuracy,":[200],"revealed":[202],"this":[204],"new":[205],"significantly":[207],"improved":[208],"approach.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}