{"id":"https://openalex.org/W4415776450","doi":"https://doi.org/10.1007/s10664-025-10736-9","title":"Improving the Multi-Class Classification of Non-Functional Requirements in Spanish: A Study of Dataset Balancing and Performance","display_name":"Improving the Multi-Class Classification of Non-Functional Requirements in Spanish: A Study of Dataset Balancing and Performance","publication_year":2025,"publication_date":"2025-11-02","ids":{"openalex":"https://openalex.org/W4415776450","doi":"https://doi.org/10.1007/s10664-025-10736-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10664-025-10736-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-025-10736-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-025-10736-9.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10664-025-10736-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025018071","display_name":"Mar\u00eda-Isabel Limaylla-Lunarejo","orcid":"https://orcid.org/0000-0002-9619-924X"},"institutions":[{"id":"https://openalex.org/I4210124246","display_name":"CITIC Group (China)","ror":"https://ror.org/037b6wy35","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210124246"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"M. Limaylla-Lunarejo","raw_affiliation_strings":["Centro de Investigaci\u00f3n CITIC , Database Lab, Universidade da Coru\u00f1a, CITIC, 15071, A Coru\u00f1a, Spain"],"raw_orcid":"https://orcid.org/0000-0002-9619-924X","affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n CITIC , Database Lab, Universidade da Coru\u00f1a, CITIC, 15071, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I4210124246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018839069","display_name":"Nelly Condor\u00ed-Fern\u00e1ndez","orcid":"https://orcid.org/0000-0002-1044-3871"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]},{"id":"https://openalex.org/I4210111807","display_name":"Center for Research in Molecular Medicine and Chronic Diseases","ror":"https://ror.org/0280bnq76","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210111807"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"N. Condori-Fernandez","raw_affiliation_strings":["Centro Singular de Investigaci\u00f3n en Tecnolox\u00edas Intelixentes (CiTIUS), Departamento de Electr\u00f3nica e Computaci\u00f3n, Universidade de Santiago de Compostela, 15782, Santiago de Compostela, Spain"],"raw_orcid":"https://orcid.org/0000-0002-1044-3871","affiliations":[{"raw_affiliation_string":"Centro Singular de Investigaci\u00f3n en Tecnolox\u00edas Intelixentes (CiTIUS), Departamento de Electr\u00f3nica e Computaci\u00f3n, Universidade de Santiago de Compostela, 15782, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I4210111807","https://openalex.org/I200284239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007513751","display_name":"Miguel R. Luaces","orcid":"https://orcid.org/0000-0003-0549-2000"},"institutions":[{"id":"https://openalex.org/I4210124246","display_name":"CITIC Group (China)","ror":"https://ror.org/037b6wy35","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210124246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"M. Rodr\u00edguez Luaces","raw_affiliation_strings":["Centro de Investigaci\u00f3n CITIC , Database Lab, Universidade da Coru\u00f1a, CITIC, 15071, A Coru\u00f1a, Spain"],"raw_orcid":"https://orcid.org/0000-0003-0549-2000","affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n CITIC , Database Lab, Universidade da Coru\u00f1a, CITIC, 15071, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I4210124246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034942489","display_name":"Oliver Karras","orcid":"https://orcid.org/0000-0001-5336-6899"},"institutions":[{"id":"https://openalex.org/I2802635041","display_name":"Technische Informationsbibliothek (TIB)","ror":"https://ror.org/04aj4c181","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2802635041","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"O. Karras","raw_affiliation_strings":["TIB \u2013 Leibniz Information Centre for Science and Technology, Hannover, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5336-6899","affiliations":[{"raw_affiliation_string":"TIB \u2013 Leibniz Information Centre for Science and Technology, Hannover, Germany","institution_ids":["https://openalex.org/I2802635041"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025018071"],"corresponding_institution_ids":["https://openalex.org/I4210124246"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15526916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.45680001378059387,"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":0.45680001378059387,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.08219999819993973,"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":0.04740000143647194,"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/undersampling","display_name":"Undersampling","score":0.7026000022888184},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.6873999834060669},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.541700005531311},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.47609999775886536},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.45579999685287476},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4481000006198883},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.43650001287460327},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.35429999232292175}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7871999740600586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466999888420105},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.7026000022888184},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.6873999834060669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6819000244140625},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.541700005531311},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40880000591278076},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.35429999232292175},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10664-025-10736-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-025-10736-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-025-10736-9.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10664-025-10736-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-025-10736-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-025-10736-9.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1622782223","display_name":null,"funder_award_id":"MCIN/AEI/10","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5080475149","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7535663061","display_name":null,"funder_award_id":"AEI/10.","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320328562","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415776450.pdf","grobid_xml":"https://content.openalex.org/works/W4415776450.grobid-xml"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1975675278","https://openalex.org/W2118978333","https://openalex.org/W2128065064","https://openalex.org/W2148143831","https://openalex.org/W2261812172","https://openalex.org/W2302501749","https://openalex.org/W2330219538","https://openalex.org/W2560229946","https://openalex.org/W2583774357","https://openalex.org/W2622918375","https://openalex.org/W2757291415","https://openalex.org/W2758253540","https://openalex.org/W2792398993","https://openalex.org/W2799028668","https://openalex.org/W2799462250","https://openalex.org/W2810197415","https://openalex.org/W2888831776","https://openalex.org/W2904689355","https://openalex.org/W2907303038","https://openalex.org/W2909182718","https://openalex.org/W2961502088","https://openalex.org/W2963059063","https://openalex.org/W2963626623","https://openalex.org/W2968852317","https://openalex.org/W2973944318","https://openalex.org/W2979624122","https://openalex.org/W2980748755","https://openalex.org/W2993303751","https://openalex.org/W2993891741","https://openalex.org/W2996713668","https://openalex.org/W3036369531","https://openalex.org/W3043428550","https://openalex.org/W3087413080","https://openalex.org/W3091973425","https://openalex.org/W3096660185","https://openalex.org/W3097513514","https://openalex.org/W3153451655","https://openalex.org/W3153990350","https://openalex.org/W3162638223","https://openalex.org/W3180181113","https://openalex.org/W3194114348","https://openalex.org/W3202390408","https://openalex.org/W3216699912","https://openalex.org/W4200433340","https://openalex.org/W4212777404","https://openalex.org/W4212949066","https://openalex.org/W4214535227","https://openalex.org/W4214616937","https://openalex.org/W4220886045","https://openalex.org/W4225645722","https://openalex.org/W4252661582","https://openalex.org/W4287385199","https://openalex.org/W4287829148","https://openalex.org/W4288045646","https://openalex.org/W4293149414","https://openalex.org/W4298147704","https://openalex.org/W4313151857","https://openalex.org/W4313563649","https://openalex.org/W4324054705","https://openalex.org/W4327795748","https://openalex.org/W4327919569","https://openalex.org/W4362514045","https://openalex.org/W4366523435","https://openalex.org/W4372334257","https://openalex.org/W4379115435","https://openalex.org/W4379746236","https://openalex.org/W4380359240","https://openalex.org/W4382180665","https://openalex.org/W4384130140","https://openalex.org/W4385516995","https://openalex.org/W4389519841","https://openalex.org/W4390430615","https://openalex.org/W4390606433","https://openalex.org/W4391182711","https://openalex.org/W4391839537","https://openalex.org/W4392414327","https://openalex.org/W4392844946","https://openalex.org/W4396876085","https://openalex.org/W4398183782","https://openalex.org/W4399203759","https://openalex.org/W4401990274","https://openalex.org/W4403605964","https://openalex.org/W4403717565","https://openalex.org/W4404095534"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Context":[1],"In":[2],"recent":[3],"years,":[4],"the":[5,15,46,66,78,81,116,143,158,172,195,211],"multi-class":[6],"classification":[7,202],"of":[8,17,49,68,80,93,148,197,213],"non-functional":[9,55,185],"requirements":[10,56],"has":[11],"seen":[12],"improvements":[13],"through":[14],"use":[16],"Machine":[18,50,177],"Learning":[19,51,178],"algorithms.":[20],"However,":[21],"challenges":[22,212],"such":[23,37,164],"as":[24,38,165],"data":[25,128,190],"scarcity":[26],"and":[27,59,72,95,115,136,150,167,207],"class":[28],"imbalance":[29],"persist,":[30],"particularly":[31,187],"for":[32,53,182,204],"languages":[33],"other":[34],"than":[35],"English,":[36],"Spanish.":[39,63],"Objective":[40],"This":[41],"study":[42,193],"aims":[43],"to":[44,76,129],"analyze":[45],"performance":[47,141,155,203],"metrics":[48],"algorithms":[52,99,179],"classifying":[54,183],"translated":[57,144],"into":[58,210],"originally":[60],"written":[61],"in":[62,102,200],"It":[64],"evaluates":[65],"effectiveness":[67],"dataset":[69,85,198],"balancing":[70,86,173,199],"techniques":[71],"conducts":[73],"cross-dataset":[74],"validation":[75],"assess":[77],"generalizability":[79],"models.":[82],"Method":[83],"A":[84],"process":[87],"was":[88],"conducted":[89],"using":[90,105],"a":[91,106],"combination":[92],"oversampling":[94],"undersampling":[96],"techniques.":[97],"Six":[98],"were":[100,123],"trained":[101],"two":[103,111],"experiments":[104],"hyperparameter":[107],"tuning":[108],"process,":[109],"employing":[110],"different":[112],"datasets:":[113],"PROMISE_exp_translated":[114],"newly":[117],"PROMISE_exp_balanced":[118],".":[119],"The":[120,192],"best-performing":[121],"models":[122,215],"further":[124],"tested":[125],"on":[126,142,157],"unseen":[127],"evaluate":[130],"their":[131],"generalizability.":[132],"Results":[133],"Logistic":[134],"Regression":[135],"Naive":[137],"Bayes":[138],"demonstrated":[139],"superior":[140],"dataset,":[145,160],"achieving":[146],"f1-scores":[147],"82%":[149],"81%,":[151],"respectively.":[152],"Although":[153],"overall":[154],"decreased":[156],"balanced":[159],"specific":[161,205],"underrepresented":[162],"classes":[163,206],"Portability":[166],"Fault":[168],"Tolerance":[169],"benefited":[170],"from":[171],"process.":[174],"Conclusion":[175],"Shallow":[176],"are":[180],"effective":[181],"Spanish":[184],"requirements,":[186],"when":[188],"addressing":[189],"imbalance.":[191],"highlights":[194],"importance":[196],"improving":[201],"provides":[208],"insights":[209],"generalizing":[214],"across":[216],"datasets.":[217]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-11-02T00:00:00"}