{"id":"https://openalex.org/W3159439818","doi":"https://doi.org/10.3233/jifs-202716","title":"A two-stage balancing strategy based on data augmentation for imbalanced text sentiment classification","display_name":"A two-stage balancing strategy based on data augmentation for imbalanced text sentiment classification","publication_year":2021,"publication_date":"2021-04-22","ids":{"openalex":"https://openalex.org/W3159439818","doi":"https://doi.org/10.3233/jifs-202716","mag":"3159439818"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-202716","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-202716","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-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/A5047902933","display_name":"Zhicheng Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhicheng Pang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339431","display_name":"Hong Li","orcid":"https://orcid.org/0000-0003-1353-7838"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Li","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101982501","display_name":"Chiyu Wang","orcid":"https://orcid.org/0000-0002-6296-779X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chiyu Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086304638","display_name":"Jiawen Shi","orcid":"https://orcid.org/0000-0003-2897-0319"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawen Shi","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101723818","display_name":"Jiale Zhou","orcid":"https://orcid.org/0000-0002-7643-7984"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047902933"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.05689297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"40","issue":"5","first_page":"10073","last_page":"10086"},"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":0.9957000017166138,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9897000193595886,"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":0.8399333357810974},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7082537412643433},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.5964748859405518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5766311287879944},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5531505346298218},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49540460109710693},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.48758596181869507},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4609189033508301},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4351135492324829},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4139316976070404},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3593316674232483},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34954944252967834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33010101318359375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1050507128238678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8399333357810974},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7082537412643433},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.5964748859405518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5766311287879944},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5531505346298218},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49540460109710693},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.48758596181869507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4609189033508301},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4351135492324829},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4139316976070404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3593316674232483},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34954944252967834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33010101318359375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1050507128238678},{"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-202716","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-202716","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1976186848","https://openalex.org/W1996216253","https://openalex.org/W2021137987","https://openalex.org/W2043865575","https://openalex.org/W2122120365","https://openalex.org/W2170240176","https://openalex.org/W2300921526","https://openalex.org/W2520488855","https://openalex.org/W2562319768","https://openalex.org/W2612634114","https://openalex.org/W2751084232","https://openalex.org/W2802835792","https://openalex.org/W2836242602","https://openalex.org/W2910364449","https://openalex.org/W2914767245","https://openalex.org/W2915626801","https://openalex.org/W2921386177","https://openalex.org/W2971644666","https://openalex.org/W6685053522","https://openalex.org/W6760320446"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052515325","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2050948537","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W2767646790","https://openalex.org/W164103134","https://openalex.org/W2283145973"],"abstract_inverted_index":{"In":[0,108],"practice,":[1],"the":[2,26,36,40,96,109,129,132,136,160],"class":[3,97],"imbalance":[4],"is":[5,12],"prevalent":[6],"in":[7],"sentiment":[8,75,137,173],"classification":[9,191],"tasks,":[10],"which":[11,49,91,156],"harmful":[13],"to":[14,42,123,128,158],"classifiers.":[15],"Recently,":[16],"over-sampling":[17],"strategies":[18],"based":[19],"on":[20,64,116,170],"data":[21],"augmentation":[22],"techniques":[23],"have":[24],"caught":[25],"eyes":[27],"of":[28,61,99,120,138],"researchers.":[29],"They":[30],"generate":[31],"new":[32,125],"samples":[33,41,53,118,122,163],"by":[34],"rewriting":[35],"original":[37],"samples.":[38,62,126,140],"Nevertheless,":[39],"be":[43,55,86,187],"rewritten":[44,162],"are":[45],"usually":[46],"selected":[47],"randomly,":[48],"means":[50],"that":[51,177],"useless":[52],"may":[54],"selected,":[56],"thus":[57],"adding":[58],"this":[59,65,142],"type":[60],"Based":[63],"observation,":[66],"we":[67,112,144],"propose":[68,145],"a":[69],"novel":[70],"balancing":[71],"strategy":[72],"for":[73,152],"text":[74,154],"classification.":[76],"Our":[77],"approach":[78],"takes":[79],"word":[80,114],"replacement":[81,115],"as":[82],"foundation":[83],"and":[84,164,185],"can":[85,94,104,186],"divided":[87],"into":[88],"two":[89],"stages,":[90],"not":[92],"only":[93],"balance":[95],"distribution":[98],"training":[100],"set,":[101],"but":[102],"also":[103],"modify":[105],"noisy":[106,139],"data.":[107],"first":[110],"stage,":[111],"perform":[113],"specific":[117],"instead":[119],"random":[121],"obtain":[124],"According":[127],"noise":[130],"detection,":[131],"second":[133],"stage":[134],"revises":[135],"Toward":[141],"aim,":[143],"an":[146],"improved":[147],"term":[148],"weighting":[149],"called":[150],"TF-IGM-CW":[151],"imbalanced":[153],"datasets,":[155],"contributes":[157],"extracting":[159],"target":[161],"feature":[165],"words.":[166],"We":[167],"conduct":[168],"experiments":[169],"four":[171],"public":[172],"datasets.":[174],"Results":[175],"suggest":[176],"our":[178],"method":[179],"outperforms":[180],"several":[181],"other":[182],"resampling":[183],"methods":[184],"integrated":[188],"with":[189],"various":[190],"algorithms":[192],"easily.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}