{"id":"https://openalex.org/W4409635001","doi":"https://doi.org/10.3390/info16040330","title":"Evaluating the Impact of Synthetic Data on Emotion Classification: A Linguistic and Structural Analysis","display_name":"Evaluating the Impact of Synthetic Data on Emotion Classification: A Linguistic and Structural Analysis","publication_year":2025,"publication_date":"2025-04-21","ids":{"openalex":"https://openalex.org/W4409635001","doi":"https://doi.org/10.3390/info16040330"},"language":"en","primary_location":{"id":"doi:10.3390/info16040330","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16040330","pdf_url":"https://www.mdpi.com/2078-2489/16/4/330/pdf?version=1745228829","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/16/4/330/pdf?version=1745228829","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020960256","display_name":"Istv\u00e1n \u00dcveges","orcid":"https://orcid.org/0000-0001-5897-9379"},"institutions":[{"id":"https://openalex.org/I4210137611","display_name":"Centre for Social Sciences","ror":"https://ror.org/0492k9x16","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210137611","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Istv\u00e1n \u00dcveges","raw_affiliation_strings":["HUN-REN Centre for Social Sciences, T\u00f3th K\u00e1lm\u00e1n u. 4, 1097 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0001-5897-9379","affiliations":[{"raw_affiliation_string":"HUN-REN Centre for Social Sciences, T\u00f3th K\u00e1lm\u00e1n u. 4, 1097 Budapest, Hungary","institution_ids":["https://openalex.org/I4210137611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083820676","display_name":"Orsolya Ring","orcid":"https://orcid.org/0000-0002-3710-1118"},"institutions":[{"id":"https://openalex.org/I4210137611","display_name":"Centre for Social Sciences","ror":"https://ror.org/0492k9x16","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210137611","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Orsolya Ring","raw_affiliation_strings":["HUN-REN Centre for Social Sciences, T\u00f3th K\u00e1lm\u00e1n u. 4, 1097 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0002-3710-1118","affiliations":[{"raw_affiliation_string":"HUN-REN Centre for Social Sciences, T\u00f3th K\u00e1lm\u00e1n u. 4, 1097 Budapest, Hungary","institution_ids":["https://openalex.org/I4210137611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020960256"],"corresponding_institution_ids":["https://openalex.org/I4210137611"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":6.2328,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95743622,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"16","issue":"4","first_page":"330","last_page":"330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9994999766349792,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.996399998664856,"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":0.9901999831199646,"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/linguistics","display_name":"Linguistics","score":0.6067298650741577},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5210451483726501},{"id":"https://openalex.org/keywords/linguistic-analysis","display_name":"Linguistic analysis","score":0.4781959056854248},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40948736667633057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3758697807788849},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.34239673614501953},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09192276000976562}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6067298650741577},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5210451483726501},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.4781959056854248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40948736667633057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3758697807788849},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34239673614501953},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09192276000976562}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info16040330","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16040330","pdf_url":"https://www.mdpi.com/2078-2489/16/4/330/pdf?version=1745228829","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},{"id":"pmh:oai:real.mtak.hu:223636","is_oa":true,"landing_page_url":null,"pdf_url":"https://real.mtak.hu/223636/1/information-16-003302.pdf","source":{"id":"https://openalex.org/S4306400081","display_name":"Repository of the Academy's Library (Library of the Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210140733","host_organization_name":"Library and Information Centre of the Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I4210140733"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:ee57e5a6e3a446ac973943ccf220d274","is_oa":true,"landing_page_url":"https://doaj.org/article/ee57e5a6e3a446ac973943ccf220d274","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 16, Iss 4, p 330 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info16040330","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16040330","pdf_url":"https://www.mdpi.com/2078-2489/16/4/330/pdf?version=1745228829","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409635001.pdf","grobid_xml":"https://content.openalex.org/works/W4409635001.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W131780060","https://openalex.org/W1512175247","https://openalex.org/W1616853180","https://openalex.org/W2007035566","https://openalex.org/W2014332385","https://openalex.org/W2019829209","https://openalex.org/W2023153377","https://openalex.org/W2028852424","https://openalex.org/W2044877801","https://openalex.org/W2048299746","https://openalex.org/W2076107117","https://openalex.org/W2077265369","https://openalex.org/W2083633991","https://openalex.org/W2250539671","https://openalex.org/W2324328502","https://openalex.org/W2405154930","https://openalex.org/W2521348577","https://openalex.org/W2579724346","https://openalex.org/W2618530766","https://openalex.org/W2626568907","https://openalex.org/W2724492314","https://openalex.org/W2773532513","https://openalex.org/W2780932362","https://openalex.org/W2848303245","https://openalex.org/W2932514169","https://openalex.org/W2971296908","https://openalex.org/W2980704391","https://openalex.org/W3021546923","https://openalex.org/W3030163527","https://openalex.org/W3035390927","https://openalex.org/W3099554308","https://openalex.org/W3130015284","https://openalex.org/W3164440087","https://openalex.org/W3170491554","https://openalex.org/W3174828871","https://openalex.org/W4205184193","https://openalex.org/W4205471878","https://openalex.org/W4254879869","https://openalex.org/W4283688409","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4306732251","https://openalex.org/W4310969345","https://openalex.org/W4380536907","https://openalex.org/W4385572315","https://openalex.org/W4389519059","https://openalex.org/W6607467106","https://openalex.org/W6671412936","https://openalex.org/W6701014381","https://openalex.org/W6769627184","https://openalex.org/W6797201572"],"related_works":["https://openalex.org/W4379034307","https://openalex.org/W3204019825","https://openalex.org/W2769555045","https://openalex.org/W4402838874","https://openalex.org/W2288790064","https://openalex.org/W4403385743","https://openalex.org/W4391812776","https://openalex.org/W4407417491","https://openalex.org/W4401870285","https://openalex.org/W2277728784"],"abstract_inverted_index":{"Emotion":[0],"classification":[1,156],"in":[2,15,111,188,205],"natural":[3],"language":[4,54],"processing":[5],"(NLP)":[6],"has":[7,57],"recently":[8],"witnessed":[9],"significant":[10],"advancements.":[11],"However,":[12,168],"class":[13],"imbalance":[14],"emotion":[16,24,84,161,206],"datasets":[17],"remains":[18],"a":[19,60,108,112,122,210],"critical":[20],"challenge,":[21],"as":[22,40,59],"dominant":[23],"categories":[25],"tend":[26],"to":[27,33,139,143,226],"overshadow":[28],"less":[29],"frequent":[30],"ones,":[31],"leading":[32],"biased":[34],"model":[35,69,110,118,145,166],"predictions.":[36],"Traditional":[37],"techniques,":[38],"such":[39],"undersampling":[41,97],"and":[42,67,100,136,180,198,216],"oversampling,":[43],"offer":[44],"partial":[45],"solutions.":[46],"More":[47],"recently,":[48],"synthetic":[49,79,102,128,152,174,202],"data":[50,80,103,153,203],"generation":[51],"using":[52,107],"large":[53],"models":[55,233],"(LLMs)":[56],"emerged":[58],"promising":[61],"strategy":[62],"for":[63,104,159,234],"augmenting":[64],"minority":[65,160],"classes":[66,99],"improving":[68,231],"robustness.":[70],"In":[71],"this":[72,223],"study,":[73],"we":[74,90,120],"investigate":[75],"the":[76,127,196,199,217,227],"impact":[77],"of":[78,126,201,213,220],"augmentation":[81,204],"on":[82,230],"German-language":[83],"classification.":[85,207],"Using":[86],"an":[87],"imbalanced":[88],"dataset,":[89],"systematically":[91],"evaluate":[92],"multiple":[93],"balancing":[94,214],"strategies,":[95],"including":[96],"overrepresented":[98],"generating":[101],"underrepresented":[105,235],"emotions":[106],"GPT-4\u2013based":[109],"few-shot":[113],"prompting":[114],"setting.":[115],"Beyond":[116],"enhancing":[117],"performance,":[119,157],"conduct":[121],"detailed":[123],"linguistic":[124,170,218,236],"analysis":[125],"samples,":[129],"examining":[130],"their":[131,141],"lexical":[132,178],"diversity,":[133],"syntactic":[134,182],"structures,":[135,183],"semantic":[137],"coherence":[138],"determine":[140],"contribution":[142],"overall":[144,165],"generalization.":[146],"Our":[147],"results":[148],"demonstrate":[149],"that":[150,173],"integrating":[151],"significantly":[154],"improves":[155],"particularly":[158],"categories,":[162],"while":[163],"maintaining":[164],"stability.":[167],"our":[169],"evaluation":[171,212],"reveals":[172],"examples":[175],"exhibit":[176],"reduced":[177],"diversity":[179],"simplified":[181],"which":[184],"may":[185],"introduce":[186],"limitations":[187],"certain":[189],"real-world":[190],"applications.":[191],"These":[192],"findings":[193],"highlight":[194],"both":[195],"potential":[197],"challenges":[200],"By":[208],"providing":[209],"comprehensive":[211],"techniques":[215],"properties":[219],"generated":[221],"text,":[222],"study":[224],"contributes":[225],"ongoing":[228],"discourse":[229],"NLP":[232],"phenomena.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}