{"id":"https://openalex.org/W4415413131","doi":"https://doi.org/10.18293/seke2025-123","title":"Generating Synthetic Nonfunctional Requirements using Large Language Models for Training Machine Learning Classifiers (S)","display_name":"Generating Synthetic Nonfunctional Requirements using Large Language Models for Training Machine Learning Classifiers (S)","publication_year":2025,"publication_date":"2025-09-29","ids":{"openalex":"https://openalex.org/W4415413131","doi":"https://doi.org/10.18293/seke2025-123"},"language":null,"primary_location":{"id":"doi:10.18293/seke2025-123","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2025-123","pdf_url":"https://doi.org/10.18293/seke2025-123","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.18293/seke2025-123","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115025076","display_name":"To Kim Bao Pham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"To Kim Bao Pham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119363338","display_name":"Ahmad Alshomar","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad Alshomar","raw_affiliation_strings":["Department of Engineering and Computer Science The University of Texas at Dallas Richardson , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering and Computer Science The University of Texas at Dallas Richardson , USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018602456","display_name":"Sam Supakkul","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Supakkul","raw_affiliation_strings":["Department of Engineering and Computer Science The University of Texas at Dallas Richardson , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering and Computer Science The University of Texas at Dallas Richardson , USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020100967","display_name":"Tom Hill","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Hill","raw_affiliation_strings":["Department of Engineering and Computer Science The University of Texas at Dallas Richardson , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering and Computer Science The University of Texas at Dallas Richardson , USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102840118","display_name":"Lawrence Chung","orcid":"https://orcid.org/0000-0003-3269-4097"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawrence Chung","raw_affiliation_strings":["Department of Engineering and Computer Science The University of Texas at Dallas Richardson , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering and Computer Science The University of Texas at Dallas Richardson , USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33916135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2025","issue":null,"first_page":"217","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14470","display_name":"Advanced Data Processing Techniques","score":0.8101000189781189,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14470","display_name":"Advanced Data Processing Techniques","score":0.8101000189781189,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.7953000068664551,"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/T10028","display_name":"Topic Modeling","score":0.7745000123977661,"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/training","display_name":"Training (meteorology)","score":0.5569999814033508},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4611999988555908},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.3248000144958496},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3050999939441681},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.26989999413490295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891999840736389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6263999938964844},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5569999814033508},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5198000073432922},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18293/seke2025-123","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2025-123","pdf_url":"https://doi.org/10.18293/seke2025-123","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18293/seke2025-123","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2025-123","pdf_url":"https://doi.org/10.18293/seke2025-123","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415413131.pdf","grobid_xml":"https://content.openalex.org/works/W4415413131.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Nonfunctional":[0],"requirements":[1],"(NFRs),":[2],"such":[3],"as":[4,57,171,173],"security":[5],"and":[6,72,111,126,138],"usability,":[7],"address":[8,28],"how":[9],"well":[10,172],"a":[11,58,78,88,102],"software":[12],"system":[13],"does":[14],"its":[15],"intended":[16],"functions.Automatic":[17],"NFR":[18,68,84,112,120,158],"classification":[19,35,159],"using":[20,86,151],"machine":[21],"learning":[22],"(ML)":[23],"has":[24,54],"been":[25,55],"proposed":[26],"to":[27,41,80,93,147],"the":[29,95,127,136,141,156],"potential":[30],"problem":[31],"of":[32,36,101,104,109,140],"faulty":[33],"manual":[34],"NFRs.In":[37],"order":[38],"for":[39,50,61,132,155],"ML":[40,149],"be":[42],"effective,":[43],"however,":[44],"we":[45,76,144,162],"need":[46],"large,":[47],"relevant":[48],"datasets":[49,85],"training.Training":[51],"data":[52,69,96,170,175,181],"shortage":[53,97],"identified":[56],"limiting":[59],"factor":[60],"these":[62],"approaches.Even":[63],"when":[64],"available,":[65],"procuring":[66],"proprietary":[67],"is":[70],"challenging":[71],"time-consuming.In":[73],"this":[74],"paper,":[75],"propose":[77],"process":[79,99],"generate":[81],"synthetic":[82,124,142,169],"labeled":[83,119],"GPT-4o,":[87],"large":[89],"language":[90],"model":[91],"(LLM),":[92],"alleviate":[94],"issue.This":[98],"consists":[100],"set":[103],"prompt":[105],"templates,":[106],"iterative":[107],"contextualization":[108],"definition,":[110],"generation":[113,125],"by":[114],"class.We":[115],"produced":[116],"2":[117],"new":[118],"datasets,":[121],"one":[122],"from":[123,129],"other":[128],"real":[130,180],"documents":[131],"validation.To":[133],"determine":[134],"both":[135],"strengths":[137],"weaknesses":[139],"dataset,":[143],"used":[145],"it":[146],"train":[148],"models":[150],"3":[152],"different":[153],"algorithms":[154],"multi-class":[157],"task.Although":[160],"limited,":[161],"feel":[163],"our":[164],"experimental":[165],"results":[166],"show":[167],"that":[168],"augmented":[174],"perform":[176],"better":[177],"than":[178],"just":[179],"alone.":[182]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}