{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T14:38:41Z","timestamp":1786977521306,"version":"build-2736575974"},"reference-count":117,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Software fault prediction (SFP) plays a crucial role in modern software development by enabling early identification of fault\u2010prone modules and efficient allocation of testing resources. While deep learning approaches have shown promise in this domain, challenges persist regarding architectural choices, metric selection, and class imbalance issues. This study presents a comprehensive comparison between deep neural networks (DNNs) and hybrid Graph Neural Network\u2010Long Short\u2010Term Memory (GNN+LSTM) models for SFP, investigating their effectiveness when combined with both conventional software metrics and error\u2010type metrics. We evaluate these approaches on four real\u2010world Java projects: ANTLR v4, JUnit, OrientDB, and Elastic Search. Our results demonstrate that GNN+LSTM models consistently outperform traditional DNN approaches, achieving improvements of up to 4% in accuracy and 4% in F1\u2010score. However, we identify challenges in combining different metric sets, with performance actually degrading compared to our previous study using error\u2010type metrics alone, suggesting potential multi\u2010collinearity issues. Additionally, we examine the effectiveness of the synthetic minority oversampling technique (SMOTE) in addressing the class imbalance issue, observing improvements of up to 6.6% in accuracy for GNN+LSTM models in severely imbalanced datasets. Our findings provide practical insights for selecting appropriate model architectures and metric combinations in SFP while highlighting the importance of carefully considering feature interactions and class imbalance mitigation strategies.<\/jats:p>","DOI":"10.1002\/cpe.70472","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T11:03:27Z","timestamp":1764759807000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep Learning Architectures for Software Fault Prediction: The Impact of Error\u2010Type Metrics and Class Imbalance"],"prefix":"10.1002","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9341-2033","authenticated-orcid":false,"given":"Khoa","family":"Phung","sequence":"first","affiliation":[{"name":"School of Computing and Creative Technologies University of the West of England  Bristol UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehmet E.","family":"Aydin","sequence":"additional","affiliation":[{"name":"School of Computing and Creative Technologies University of the West of England  Bristol UK"},{"name":"Department of Industrial Engineering Istanbul Commerce University  Istanbul Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Ogunshile","sequence":"additional","affiliation":[{"name":"School of Computing and Creative Technologies University of the West of England  Bristol UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-06862-6_11"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10371-6"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.067"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3144598"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2925313"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-0189-0_18"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-sen.2019.0260"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2270"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.35882\/jeeemi.v6i3.453"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICOEI.2017.8300883"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3262411"},{"key":"e_1_2_10_13_1","first-page":"167","volume-title":"International Symposium on Intelligent and Distributed Computing","author":"Phung K.","year":"2024"},{"key":"e_1_2_10_14_1","volume-title":"The Practical Implementation of Software Metrics","author":"Goodman P.","year":"1993"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/32.979986"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1201\/b17461"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/32.295895"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.303623"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2013.6606589"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-017-9563-5"},{"key":"e_1_2_10_21_1","first-page":"19","volume-title":"2017 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","author":"Karim S.","year":"2017"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CONISOFT52520.2021.00032"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33826-7_25"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/2401496"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/QRS.2015.14"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-018-1696-z"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSA52907.2021.00025"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/RAISE.2019.00016"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-024-10495-z"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/fi11120246"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2024.3356515"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2018.11.005"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05459-1"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2024.109232"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2019.00017"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/smr.2330"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2020.3040191"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2021.111108"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/e24101373"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/QRS51102.2020.00055"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04277-5_76"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2878425"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2821768"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/6230953"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2915970.2916007"},{"key":"e_1_2_10_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2013.11"},{"key":"e_1_2_10_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06659-3"},{"key":"e_1_2_10_51_1","first-page":"384","volume-title":"ICSOFT","author":"Ardimento P.","year":"2020"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2020.110691"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11219-024-09704-1"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8840389"},{"key":"e_1_2_10_55_1","first-page":"6105","volume-title":"International Conference on Machine Learning","author":"Tan M.","year":"2019"},{"key":"e_1_2_10_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21606-5"},{"key":"e_1_2_10_57_1","unstructured":"S.Ioffe \u201cBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift \u201d arXiv preprint arXiv:1502.031672015."},{"issue":"1","key":"e_1_2_10_58_1","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks From Overfitting","volume":"15","author":"Srivastava N.","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_10_59_1","unstructured":"S.Mastromichalakis \u201cAlrelu: A Different Approach on Leaky Relu Activation Function to Improve Neural Networks Performance \u201d arXiv preprint arXiv:2012.07564 (2020)."},{"key":"e_1_2_10_60_1","unstructured":"P.Veli\u010dkovi\u0107 G.Cucurull A.Casanova A.Romero P.Lio andY.Bengio \u201cGraph Attention Networks \u201d arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_2_10_61_1","article-title":"Gla\u2010Sdp: A Graph Neural Network and Lstm Based Software Defect Prediction Method With Attention Mechanism","volume":"209","author":"Meng Y.","year":"2025","journal-title":"Journal of Systems and Software"},{"key":"e_1_2_10_62_1","unstructured":"K.Xu W.Hu J.Leskovec andS.Jegelka \u201cHow Powerful Are Graph Neural Networks? \u201d arXiv preprint arXiv:1810.00826 (2018)."},{"key":"e_1_2_10_63_1","unstructured":"D. P.KingmaandJ.Ba \u201cAdam: A Method for Stochastic Optimization \u201d arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_10_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2018.8624183"},{"key":"e_1_2_10_65_1","unstructured":"S.Ruder \u201cAn Overview of Gradient Descent Optimization Algorithms \u201d arXiv preprint arXiv:1609.04747 (2016)."},{"key":"e_1_2_10_66_1","unstructured":"D.MastersandC.Luschi \u201cRevisiting Small Batch Training for Deep Neural Networks \u201d arXiv preprint arXiv:1804.07612 (2018)."},{"key":"e_1_2_10_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_3"},{"key":"e_1_2_10_68_1","unstructured":"A.Labach H.Salehinejad andS.Valaee \u201cSurvey of Dropout Methods for Deep Neural Networks \u201d arXiv preprint arXiv:1904.13310 (2019)."},{"key":"e_1_2_10_69_1","volume-title":"Deep Learning","author":"Goodfellow I.","year":"2016"},{"key":"e_1_2_10_70_1","first-page":"2825","article-title":"Scikit\u2010Learn: Machine Learning in Python","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_10_71_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"e_1_2_10_72_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01588-5"},{"key":"e_1_2_10_73_1","first-page":"1137","volume-title":"A Study of Cross\u2010Validation and Bootstrap for Accuracy Estimation and Model Selection","author":"Kohavi R.","year":"1995"},{"key":"e_1_2_10_74_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"e_1_2_10_75_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57077-4_10"},{"key":"e_1_2_10_76_1","unstructured":"M.FeyandJ. E.Lenssen \u201cFast Graph Representation Learning With Pytorch Geometric \u201d arXiv preprint arXiv:1903.02428 (2019)."},{"key":"e_1_2_10_77_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-33383-0_5"},{"issue":"1","key":"e_1_2_10_78_1","first-page":"559","article-title":"Imbalanced\u2010Learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning","volume":"18","author":"Lema\u00eetre G.","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_10_79_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43725-0_4"},{"key":"e_1_2_10_80_1","first-page":"8","volume-title":"Yeo\u2010Johnson Power Transformations. Department of Applied Statistics","author":"Weisberg S.","year":"2001"},{"key":"e_1_2_10_81_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10260-022-00640-7"},{"key":"e_1_2_10_82_1","first-page":"878","volume-title":"Advances in Intelligent Computing, 2005","author":"Han H.","year":"2005"},{"key":"e_1_2_10_83_1","first-page":"1322","volume-title":"2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","author":"He H.","year":"2008"},{"key":"e_1_2_10_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007735"},{"key":"e_1_2_10_85_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11192"},{"key":"e_1_2_10_86_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_2_10_87_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16788-7"},{"key":"e_1_2_10_88_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218194018500237"},{"key":"e_1_2_10_89_1","volume-title":"AIP Conference Proceedings","author":"Tamanna","year":"2022"},{"key":"e_1_2_10_90_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177731944"},{"key":"e_1_2_10_91_1","first-page":"1","article-title":"Statistical Comparisons of Classifiers Over Multiple Data Sets","volume":"7","author":"Dem\u0161ar J.","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_10_92_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2007.02.015"},{"key":"e_1_2_10_93_1","first-page":"1157","article-title":"An Introduction to Variable and Feature Selection","volume":"3","author":"Guyon I.","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_10_94_1","doi-asserted-by":"publisher","DOI":"10.51219\/JAIMLD\/srija-saha\/249"},{"key":"e_1_2_10_95_1","volume-title":"Distribution\u2010Free Multiple Comparisons","author":"Nemenyi P. B.","year":"1963"},{"key":"e_1_2_10_96_1","doi-asserted-by":"publisher","DOI":"10.1145\/3212695"},{"key":"e_1_2_10_97_1","unstructured":"Z.Chen J.Xu C.Alippi et al. \u201cGraph Neural Network\u2010Based Fault Diagnosis: A Review \u201d arXiv preprint arXiv:2111.08185 (2021)."},{"key":"e_1_2_10_98_1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587"},{"key":"e_1_2_10_99_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00863"},{"key":"e_1_2_10_100_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.paid.2016.06.069"},{"key":"e_1_2_10_101_1","doi-asserted-by":"publisher","DOI":"10.22237\/jmasm\/1257035100"},{"key":"e_1_2_10_102_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00026"},{"key":"e_1_2_10_103_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600-0587.2012.07348.x"},{"key":"e_1_2_10_104_1","doi-asserted-by":"publisher","DOI":"10.4172\/2161-1165.1000227"},{"key":"e_1_2_10_105_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.1998.738486"},{"key":"e_1_2_10_106_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym12071147"},{"key":"e_1_2_10_107_1","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/5585130"},{"key":"e_1_2_10_108_1","volume-title":"Applied Regression Analysis and Generalized Linear Models","author":"Fox J.","year":"2015"},{"key":"e_1_2_10_109_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2015.0202"},{"key":"e_1_2_10_110_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0087357"},{"key":"e_1_2_10_111_1","doi-asserted-by":"crossref","unstructured":"Y.Shi Z.Huang S.Feng H.Zhong W.Wang andY.Sun \u201cMasked Label Prediction: Unified Message Passing Model for Semi\u2010Supervised Classification \u201d arXiv preprint arXiv:2009.03509 (2020).","DOI":"10.24963\/ijcai.2021\/214"},{"key":"e_1_2_10_112_1","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.2019.1583913"},{"key":"e_1_2_10_113_1","first-page":"1","article-title":"Cross\u2010Validation for Imbalanced Datasets: Avoiding Overoptimistic and Overfitting Approaches","volume":"2018","author":"Santos M. S.","year":"2018","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"e_1_2_10_114_1","doi-asserted-by":"publisher","DOI":"10.1145\/2907070"},{"key":"e_1_2_10_115_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-012-0295-5"},{"key":"e_1_2_10_116_1","first-page":"1","article-title":"A Practical Guide for Using Statistical Tests to Assess Randomized Algorithms in Software Engineering","author":"Arcuri A.","year":"2011","journal-title":"Proceedings of the 33rd International Conference on Software Engineering"},{"key":"e_1_2_10_117_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-008-9060-1"},{"key":"e_1_2_10_118_1","volume-title":"Attention Is All You Need","author":"Vaswani A.","year":"2017"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T04:49:32Z","timestamp":1768193372000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70472"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":117,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/cpe.70472"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70472","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"assertion":[{"value":"2024-12-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70472"}}