{"id":"https://openalex.org/W7165923389","doi":"https://doi.org/10.1007/s11219-026-09768-1","title":"Lexical and semantic representations for similar bug report detection: A TF-IDF and frozen T5 comparative study","display_name":"Lexical and semantic representations for similar bug report detection: A TF-IDF and frozen T5 comparative study","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7165923389","doi":"https://doi.org/10.1007/s11219-026-09768-1"},"language":"en","primary_location":{"id":"doi:10.1007/s11219-026-09768-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11219-026-09768-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11219-026-09768-1.pdf","source":{"id":"https://openalex.org/S7504070","display_name":"Software Quality Journal","issn_l":"0963-9314","issn":["0963-9314","1573-1367"],"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":"Software Quality Journal","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/s11219-026-09768-1.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125207286","display_name":"I C Q Barbosa","orcid":null},"institutions":[{"id":"https://openalex.org/I41455075","display_name":"Universidade Federal de Campina Grande","ror":"https://ror.org/00eftnx64","country_code":"BR","type":"education","lineage":["https://openalex.org/I41455075"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Iann Barbosa","raw_affiliation_strings":["Department of Systems and Computing, Center for Electrical Engineering and Informatics, Federal University of Campina Grande, Apr\u00edgio Veloso Street, 882, Universit\u00e1rio District, Campina Grande, Para\u00edba, 58429-900, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Computing, Center for Electrical Engineering and Informatics, Federal University of Campina Grande, Apr\u00edgio Veloso Street, 882, Universit\u00e1rio District, Campina Grande, Para\u00edba, 58429-900, Brazil","institution_ids":["https://openalex.org/I41455075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025746911","display_name":"Jo\u00e3o Brunet","orcid":null},"institutions":[{"id":"https://openalex.org/I41455075","display_name":"Universidade Federal de Campina Grande","ror":"https://ror.org/00eftnx64","country_code":"BR","type":"education","lineage":["https://openalex.org/I41455075"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Brunet","raw_affiliation_strings":["Department of Systems and Computing, Center for Electrical Engineering and Informatics, Federal University of Campina Grande, Apr\u00edgio Veloso Street, 882, Universit\u00e1rio District, Campina Grande, Para\u00edba, 58429-900, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Computing, Center for Electrical Engineering and Informatics, Federal University of Campina Grande, Apr\u00edgio Veloso Street, 882, Universit\u00e1rio District, Campina Grande, Para\u00edba, 58429-900, Brazil","institution_ids":["https://openalex.org/I41455075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011498557","display_name":"Franklin Ramalho","orcid":"https://orcid.org/0009-0008-6024-0096"},"institutions":[{"id":"https://openalex.org/I41455075","display_name":"Universidade Federal de Campina Grande","ror":"https://ror.org/00eftnx64","country_code":"BR","type":"education","lineage":["https://openalex.org/I41455075"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Franklin Ramalho","raw_affiliation_strings":["Department of Systems and Computing, Center for Electrical Engineering and Informatics, Federal University of Campina Grande, Apr\u00edgio Veloso Street, 882, Universit\u00e1rio District, Campina Grande, Para\u00edba, 58429-900, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Computing, Center for Electrical Engineering and Informatics, Federal University of Campina Grande, Apr\u00edgio Veloso Street, 882, Universit\u00e1rio District, Campina Grande, Para\u00edba, 58429-900, Brazil","institution_ids":["https://openalex.org/I41455075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5125207286"],"corresponding_institution_ids":["https://openalex.org/I41455075"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8279483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.004800000227987766,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.0032999999821186066,"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/pipeline","display_name":"Pipeline (software)","score":0.6940000057220459},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6690999865531921},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5587000250816345},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5583000183105469},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.532800018787384},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4729999899864197},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44929999113082886},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4034000039100647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267000079154968},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6940000057220459},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6690999865531921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.57669997215271},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5587000250816345},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5583000183105469},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5314000248908997},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4729999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47130000591278076},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44929999113082886},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C15708719","wikidata":"https://www.wikidata.org/wiki/Q2271801","display_name":"Domain analysis","level":5,"score":0.2824999988079071},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11219-026-09768-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11219-026-09768-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11219-026-09768-1.pdf","source":{"id":"https://openalex.org/S7504070","display_name":"Software Quality Journal","issn_l":"0963-9314","issn":["0963-9314","1573-1367"],"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":"Software Quality Journal","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11219-026-09768-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11219-026-09768-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11219-026-09768-1.pdf","source":{"id":"https://openalex.org/S7504070","display_name":"Software Quality Journal","issn_l":"0963-9314","issn":["0963-9314","1573-1367"],"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":"Software Quality Journal","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2823776494","display_name":null,"funder_award_id":"88887","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G3519237112","display_name":null,"funder_award_id":"2021-00","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"}],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7165923389.pdf","grobid_xml":"https://content.openalex.org/works/W7165923389.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1582774210","https://openalex.org/W1655956671","https://openalex.org/W1662133657","https://openalex.org/W1966716734","https://openalex.org/W1971040550","https://openalex.org/W1974971448","https://openalex.org/W1976526581","https://openalex.org/W1981109290","https://openalex.org/W2014538668","https://openalex.org/W2018582844","https://openalex.org/W2041282815","https://openalex.org/W2118978333","https://openalex.org/W2122902902","https://openalex.org/W2139270835","https://openalex.org/W2158698691","https://openalex.org/W2160517961","https://openalex.org/W2165612380","https://openalex.org/W2170505850","https://openalex.org/W2250539671","https://openalex.org/W2318802957","https://openalex.org/W2803187616","https://openalex.org/W2919115771","https://openalex.org/W2963341956","https://openalex.org/W4213009331","https://openalex.org/W4237854095","https://openalex.org/W4239549338","https://openalex.org/W4292779060","https://openalex.org/W4320523283","https://openalex.org/W4385245566","https://openalex.org/W4386576685"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"In":[1,152],"software":[2],"development,":[3],"bug":[4,185],"reports":[5,16],"(BRs)":[6],"are":[7],"essential":[8],"for":[9,31,126,137,144,195],"identifying":[10],"defects,":[11],"but":[12],"the":[13,153,159,165,176,184],"volume":[14],"of":[15,155],"in":[17,147],"large":[18],"projects":[19],"makes":[20],"manual":[21],"relatedness":[22,34],"analysis":[23],"slow":[24],"and":[25,52,67,112,123,132,149,164],"error-prone.":[26],"We":[27,42,69],"study":[28],"machine-learning":[29],"approaches":[30],"predicting":[32],"BR":[33],"under":[35],"a":[36,53,129,134,193],"file-overlap":[37],"target,":[38],"File-Change":[39],"Similarity":[40],"(FCS).":[41],"compare":[43],"TF-IDF,":[44],"frozen":[45,156],"sentence-level":[46],"T5":[47,122,157,162,177],"embeddings":[48],"(without":[49],"domain":[50,187],"fine-tuning),":[51],"hybrid":[54,92,130],"lexical-semantic":[55],"representation.":[56],"Our":[57],"pipeline":[58],"covers":[59],"data":[60],"retrieval,":[61],"preprocessing,":[62],"vectorization,":[63],"normalization,":[64],"neural-network":[65],"training,":[66],"evaluation.":[68],"evaluated":[70],"56":[71],"models":[72,105],"using":[73,80],"various":[74],"modeling":[75],"strategies.":[76],"Analysis":[77],"reveals":[78],"that":[79],"complete":[81],"vectors":[82],"as":[83,192],"features":[84],"is":[85],"more":[86],"effective":[87],"than":[88],"cosine":[89],"distance.":[90],"The":[91],"approach":[93],"shows":[94],"competitive":[95],"descriptive":[96],"performance":[97,125,163],"comparable":[98],"to":[99],"TF-IDF":[100,124,169],"alone.":[101],"Fine-tuning":[102],"on":[103,161,183],"14":[104],"tested":[106],"168":[107],"hyperparameter":[108],"combinations,":[109],"with":[110,167],"Adam":[111],"RMSprop":[113],"optimizers":[114],"showing":[115],"best":[116],"performance.":[117],"Key":[118],"contributions":[119],"include":[120],"evaluating":[121],"BRs,":[127],"exploring":[128],"approach,":[131],"providing":[133],"methodological":[135],"framework":[136],"representation":[138],"comparison.":[139],"This":[140],"research":[141,173],"offers":[142],"suggestions":[143],"improving":[145],"efficiency":[146],"development":[148],"resource":[150],"allocation.":[151],"context":[154],"embeddings,":[158],"findings":[160],"comparison":[166],"strong":[168],"baselines":[170],"drive":[171],"future":[172,196],"directions.":[174],"Since":[175],"weights":[178],"were":[179],"not":[180],"specifically":[181],"trained":[182],"report":[186],"(frozen),":[188],"these":[189],"results":[190],"serve":[191],"baseline":[194],"fine-tuning":[197],"experiments.":[198]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-06-26T00:00:00"}