{"id":"https://openalex.org/W4388526260","doi":"https://doi.org/10.3390/fi15110363","title":"Generating Synthetic Resume Data with Large Language Models for Enhanced Job Description Classification","display_name":"Generating Synthetic Resume Data with Large Language Models for Enhanced Job Description Classification","publication_year":2023,"publication_date":"2023-11-09","ids":{"openalex":"https://openalex.org/W4388526260","doi":"https://doi.org/10.3390/fi15110363"},"language":"en","primary_location":{"id":"doi:10.3390/fi15110363","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi15110363","pdf_url":"https://www.mdpi.com/1999-5903/15/11/363/pdf?version=1699526678","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"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":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/15/11/363/pdf?version=1699526678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093124491","display_name":"Panagiotis Skondras","orcid":null},"institutions":[{"id":"https://openalex.org/I158716096","display_name":"University of Peloponnese","ror":"https://ror.org/04d4d3c02","country_code":"GR","type":"education","lineage":["https://openalex.org/I158716096"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Panagiotis Skondras","raw_affiliation_strings":["Data and Media Laboratory, Department of Electrical and Computer Engineering, University of Peloponnese, 22100 Tripoli, Greece"],"affiliations":[{"raw_affiliation_string":"Data and Media Laboratory, Department of Electrical and Computer Engineering, University of Peloponnese, 22100 Tripoli, Greece","institution_ids":["https://openalex.org/I158716096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091820192","display_name":"Panagiotis Zervas","orcid":"https://orcid.org/0000-0002-6531-4022"},"institutions":[{"id":"https://openalex.org/I158716096","display_name":"University of Peloponnese","ror":"https://ror.org/04d4d3c02","country_code":"GR","type":"education","lineage":["https://openalex.org/I158716096"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Panagiotis Zervas","raw_affiliation_strings":["Data and Media Laboratory, Department of Electrical and Computer Engineering, University of Peloponnese, 22100 Tripoli, Greece"],"affiliations":[{"raw_affiliation_string":"Data and Media Laboratory, Department of Electrical and Computer Engineering, University of Peloponnese, 22100 Tripoli, Greece","institution_ids":["https://openalex.org/I158716096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039150569","display_name":"Giannis Tzimas","orcid":"https://orcid.org/0000-0002-4073-7256"},"institutions":[{"id":"https://openalex.org/I158716096","display_name":"University of Peloponnese","ror":"https://ror.org/04d4d3c02","country_code":"GR","type":"education","lineage":["https://openalex.org/I158716096"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Giannis Tzimas","raw_affiliation_strings":["Data and Media Laboratory, Department of Electrical and Computer Engineering, University of Peloponnese, 22100 Tripoli, Greece"],"affiliations":[{"raw_affiliation_string":"Data and Media Laboratory, Department of Electrical and Computer Engineering, University of Peloponnese, 22100 Tripoli, Greece","institution_ids":["https://openalex.org/I158716096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091820192"],"corresponding_institution_ids":["https://openalex.org/I158716096"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":2.2575,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90565527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"15","issue":"11","first_page":"363","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9969000220298767,"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/T13629","display_name":"Text Readability and Simplification","score":0.98580002784729,"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":0.887641429901123},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6628541946411133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6087464690208435},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5656830072402954},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5446027517318726},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5237779021263123},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.47612980008125305},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.46723490953445435},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41970300674438477},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37086403369903564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.887641429901123},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6628541946411133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6087464690208435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5656830072402954},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5446027517318726},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5237779021263123},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.47612980008125305},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.46723490953445435},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41970300674438477},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37086403369903564},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/fi15110363","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi15110363","pdf_url":"https://www.mdpi.com/1999-5903/15/11/363/pdf?version=1699526678","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"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":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jftint:v:15:y:2023:i:11:p:363-:d:1277030","is_oa":false,"landing_page_url":"https://www.mdpi.com/1999-5903/15/11/363/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:doaj.org/article:f5282e37802142b28007c53883624641","is_oa":true,"landing_page_url":"https://doaj.org/article/f5282e37802142b28007c53883624641","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":"Future Internet, Vol 15, Iss 11, p 363 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/fi15110363","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi15110363","pdf_url":"https://www.mdpi.com/1999-5903/15/11/363/pdf?version=1699526678","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"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":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306129","display_name":"U.S. Department of Labor","ror":"https://ror.org/05mbkbj54"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4388526260.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2081580037","https://openalex.org/W2105472772","https://openalex.org/W2128424290","https://openalex.org/W3081785379","https://openalex.org/W3166840245","https://openalex.org/W3180181113","https://openalex.org/W3198440572","https://openalex.org/W3199400376","https://openalex.org/W4206250065","https://openalex.org/W4284669679","https://openalex.org/W4287854681","https://openalex.org/W4301393026","https://openalex.org/W4367369313","https://openalex.org/W4379781056","https://openalex.org/W4384519236","https://openalex.org/W4385572315","https://openalex.org/W4386815555","https://openalex.org/W4389777127","https://openalex.org/W6798060926","https://openalex.org/W6841665461","https://openalex.org/W6846821209"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287598411","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"In":[0],"this":[1,109,239],"article,":[2],"we":[3,111],"investigate":[4],"the":[5,14,48,61,68,75,87,98,113,166,193,209,221,230],"potential":[6],"of":[7,17,36,63,70,89,170,211,223,229],"synthetic":[8,189,217],"resumes":[9,122,130],"as":[10],"a":[11,90,104,142,147],"means":[12],"for":[13,57,233],"rapid":[15],"generation":[16],"training":[18,71,225],"data":[19,24,101,182,190,214],"and":[20,54,120,134,146,186],"their":[21],"effectiveness":[22],"in":[23,27,40,97,220],"augmentation,":[25],"especially":[26,219],"categories":[28,96],"marked":[29],"by":[30],"sparse":[31],"samples.":[32],"The":[33,199,227],"widespread":[34],"implementation":[35],"machine":[37],"learning":[38],"algorithms":[39,65],"natural":[41],"language":[42],"processing":[43],"(NLP)":[44],"has":[45],"notably":[46],"streamlined":[47],"resume":[49],"classification":[50,168,235],"process,":[51],"delivering":[52],"time":[53],"cost":[55],"efficiencies":[56],"hiring":[58],"organizations.":[59],"However,":[60],"performance":[62],"these":[64],"depends":[66],"on":[67,165,174],"abundance":[69],"data.":[72,226],"While":[73,160],"selecting":[74],"right":[76],"model":[77,144,195,232],"architecture":[78],"is":[79,82],"essential,":[80],"it":[81],"also":[83],"crucial":[84],"to":[85,116,124,137],"ensure":[86],"availability":[88],"robust,":[91],"well-curated":[92],"dataset.":[93],"For":[94],"many":[95],"job":[99],"market,":[100],"sparsity":[102],"remains":[103],"challenge.":[105],"To":[106],"deal":[107],"with":[108,215],"challenge,":[110],"employed":[112],"OpenAI":[114],"API":[115],"generate":[117],"both":[118,161],"structured":[119],"unstructured":[121],"tailored":[123],"specific":[125],"criteria.":[126],"These":[127,206],"synthetically":[128],"generated":[129],"were":[131,163],"cleaned,":[132],"preprocessed":[133],"then":[135],"utilized":[136],"train":[138],"two":[139],"distinct":[140],"models:":[141],"transformer":[143,194],"(BERT)":[145],"feedforward":[148],"neural":[149],"network":[150],"(FFNN)":[151],"that":[152],"incorporated":[153],"Universal":[154],"Sentence":[155],"Encoder":[156],"4":[157],"(USE4)":[158],"embeddings.":[159],"models":[162],"evaluated":[164],"multiclass":[167],"task":[169],"resumes,":[171,218],"when":[172],"trained":[173],"an":[175],"augmented":[176,212],"dataset":[177],"containing":[178],"60":[179],"percent":[180,188],"real":[181],"(from":[183],"Indeed":[184],"website)":[185],"40":[187],"from":[191],"ChatGPT,":[192],"presented":[196],"exceptional":[197],"accuracy.":[198,205],"FFNN,":[200],"albeit":[201],"predictably,":[202],"achieved":[203],"lower":[204],"findings":[207],"highlight":[208],"value":[210],"real-world":[213],"ChatGPT-generated":[216],"context":[222],"limited":[224],"suitability":[228],"BERT":[231],"such":[234],"tasks":[236],"further":[237],"reinforces":[238],"narrative.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}