{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T12:00:23Z","timestamp":1780401623710,"version":"3.54.1"},"reference-count":90,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s10664-022-10133-6","type":"journal-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T10:03:56Z","timestamp":1650881036000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Revisiting reopened bugs in open source software systems"],"prefix":"10.1007","volume":"27","author":[{"given":"Ankur","family":"Tagra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3921-1724","authenticated-orcid":false,"given":"Haoxiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gopi Krishnan","family":"Rajbahadur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed E.","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,4,25]]},"reference":[{"key":"10133_CR1","unstructured":"Agrawal A, Fu W, Chen D, Shen X, Menzies T (2019) How to\u201d dodge\u201d complex software analytics. IEEE Transactions on Software Engineering (TSE\u201919), pp 1\u201313"},{"key":"10133_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal A, Menzies T (2018) Is\u201d better data\u201d better than\u201d better data miners\u201d?. In: 2018 IEEE\/ACM 40th International Conference on Software Engineering (ICSE\u201918). IEEE, pp 1050\u20131061","DOI":"10.1145\/3180155.3180197"},{"issue":"4","key":"10133_CR3","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1007\/s10664-012-9239-3","volume":"19","author":"J Al Dallal","year":"2014","unstructured":"Al Dallal J, Morasca S (2014) Predicting object-oriented class reuse-proneness using internal quality attributes. Empir Softw Eng (EMSE\u201914) 19(4):775\u2013821","journal-title":"Empir Softw Eng (EMSE\u201914)"},{"issue":"10","key":"10133_CR4","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1093\/bioinformatics\/btq134","volume":"26","author":"A Altmann","year":"2010","unstructured":"Altmann A, Tolo\u015fi L, Sander O, Lengauer T (2010) Permutation importance: a corrected feature importance measure. Bioinformatics 26(10):1340\u20131347","journal-title":"Bioinformatics"},{"key":"10133_CR5","doi-asserted-by":"crossref","unstructured":"Anvik J, Hiew L, Murphy GC (2006) Who should fix this bug?. In: Proceedings of the 28th international conference on Software engineering (ICSE\u201906), pp 361\u2013370","DOI":"10.1145\/1134285.1134336"},{"key":"10133_CR6","unstructured":"Arellano AV (2019) Epidemiological disease surveillance using public media text mining. North Carolina State University"},{"issue":"4","key":"10133_CR7","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1162\/coli.07-034-R2","volume":"34","author":"R Artstein","year":"2008","unstructured":"Artstein R, Poesio M (2008) Inter-coder agreement for computational linguistics. Comput Linguist 34(4):555\u2013596","journal-title":"Comput Linguist"},{"issue":"1","key":"10133_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12874-018-0606-7","volume":"18","author":"DT Beckler","year":"2018","unstructured":"Beckler DT, Thumser ZC, Schofield JS, Marasco PD (2018) Reliability in evaluator-based tests: using simulation-constructed models to determine contextually relevant agreement thresholds. BMC Med Res Methodol 18(1):1\u201312","journal-title":"BMC Med Res Methodol"},{"issue":"3","key":"10133_CR9","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1007\/s10664-012-9224-x","volume":"19","author":"LR Biggers","year":"2014","unstructured":"Biggers LR, Bocovich C, Capshaw R, Eddy BP, Etzkorn LH, Kraft NA (2014) Configuring latent dirichlet allocation based feature location. Empir Softw Eng (EMSE\u201914) 19(3):465\u2013500","journal-title":"Empir Softw Eng (EMSE\u201914)"},{"key":"10133_CR10","doi-asserted-by":"crossref","unstructured":"Bortis G, Van Der Hoek A (2013) Porchlight: A tag-based approach to bug triaging. In: 2013 35th International Conference on Software Engineering (ICSE). IEEE, pp 342\u2013351","DOI":"10.1109\/ICSE.2013.6606580"},{"key":"10133_CR11","unstructured":"Boslaugh S (2012) Statistics in a nutshell: A desktop quick reference. O\u2019Reilly Media, Inc."},{"key":"10133_CR12","doi-asserted-by":"crossref","unstructured":"Caglayan B, Misirli AT, Miranskyy A, Turhan B, Bener A (2012) Factors characterizing reopened issues: a case study. In: Proceedings of the 8th International Conference on Predictive Models in Software Engineering, pp 1\u201310","DOI":"10.1145\/2365324.2365327"},{"issue":"8-10","key":"10133_CR13","doi-asserted-by":"publisher","first-page":"1477","DOI":"10.1007\/s10994-018-5724-2","volume":"107","author":"P Cerda","year":"2018","unstructured":"Cerda P, Varoquaux G, K\u00e9gl B (2018) Similarity encoding for learning with dirty categorical variables. Mach Learn 107(8-10):1477\u20131494","journal-title":"Mach Learn"},{"issue":"2","key":"10133_CR14","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1080\/19401493.2018.1498538","volume":"12","author":"D Chakraborty","year":"2019","unstructured":"Chakraborty D, Elzarka H (2019) Advanced machine learning techniques for building performance simulation: a comparative analysis. J Build Perform Simul 12(2):193\u2013207","journal-title":"J Build Perform Simul"},{"key":"10133_CR15","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321\u2013357","journal-title":"J Artif Intell Res"},{"key":"10133_CR16","doi-asserted-by":"crossref","unstructured":"Chen D, Fu W, Krishna R, Menzies T (2018) Applications of psychological science for actionable analytics. In: Proceedings of the 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp 456\u2013467","DOI":"10.1145\/3236024.3236050"},{"issue":"1","key":"10133_CR17","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/s10664-014-9347-3","volume":"21","author":"A Corazza","year":"2016","unstructured":"Corazza A, Di Martino S, Maggio V, Scanniello G (2016) Weighing lexical information for software clustering in the context of architecture recovery. Empir Softw Eng (EMSE\u201916) 21(1):72\u2013103","journal-title":"Empir Softw Eng (EMSE\u201916)"},{"issue":"1","key":"10133_CR18","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/BF00988593","volume":"13","author":"JM Corbin","year":"1990","unstructured":"Corbin JM, Strauss A (1990) Grounded theory research: Procedures, canons, and evaluative criteria. Qualitative Sociol 13(1):3\u201321","journal-title":"Qualitative Sociol"},{"issue":"2","key":"10133_CR19","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/s10664-017-9548-7","volume":"23","author":"DA da Costa","year":"2018","unstructured":"da Costa DA, McIntosh S, Treude C, Kulesza U, Hassan AE (2018) The impact of rapid release cycles on the integration delay of fixed issues. Empir Softw Eng (EMSE\u201918) 23(2):835\u2013904","journal-title":"Empir Softw Eng (EMSE\u201918)"},{"key":"10133_CR20","doi-asserted-by":"crossref","unstructured":"Denny M, Spirling A (2017) Text preprocessing for unsupervised learning: Why it matters, when it misleads, and what to do about it. When It Misleads, and What to Do about It (September 27, 2017)","DOI":"10.2139\/ssrn.2849145"},{"key":"10133_CR21","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.infsof.2016.04.017","volume":"76","author":"W Fu","year":"2016","unstructured":"Fu W, Menzies T, Shen X (2016) Tuning for software analytics: Is it really necessary?. Inf Softw Technol 76:135\u2013146","journal-title":"Inf Softw Technol"},{"key":"10133_CR22","doi-asserted-by":"crossref","unstructured":"Ghotra B, McIntosh S, Hassan AE (2015) Revisiting the impact of classification techniques on the performance of defect prediction models. In: 2015 IEEE\/ACM 37th IEEE International Conference on Software Engineering (ICSE\u201915), vol 1. IEEE, pp 789\u2013800","DOI":"10.1109\/ICSE.2015.91"},{"key":"10133_CR23","doi-asserted-by":"crossref","unstructured":"Ghotra B, McIntosh S, Hassan AE (2017) A large-scale study of the impact of feature selection techniques on defect classification models. In: 2017 IEEE\/ACM 14th International Conference on Mining Software Repositories (MSR\u201917). IEEE, pp 146\u2013157","DOI":"10.1109\/MSR.2017.18"},{"key":"10133_CR24","doi-asserted-by":"crossref","unstructured":"Guo PJ, Zimmermann T, Nagappan N, Murphy B (2010) Characterizing and predicting which bugs get fixed: an empirical study of microsoft windows. In: Proceedings of the 32nd ACM\/IEEE International Conference on Software Engineering (ICSE\u201910)-Volume 1, pp 495\u2013504","DOI":"10.1145\/1806799.1806871"},{"key":"10133_CR25","doi-asserted-by":"crossref","unstructured":"Guo PJ, Zimmermann T, Nagappan N, Murphy B (2011) \u201dnot my bug!\u201d and other reasons for software bug report reassignments. In: Proceedings of the ACM 2011 conference on Computer supported cooperative work, pp 395\u2013404","DOI":"10.1145\/1958824.1958887"},{"key":"10133_CR26","unstructured":"Hardeniya N, Perkins J, Chopra D, Joshi N, Mathur I (2016) Natural language processing: python and nltk. Packt Publishing Ltd"},{"issue":"1","key":"10133_CR27","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1080\/19312450709336664","volume":"1","author":"AF Hayes","year":"2007","unstructured":"Hayes AF, Krippendorff K (2007) Answering the call for a standard reliability measure for coding data. Commun Methods Measur 1(1):77\u201389","journal-title":"Commun Methods Measur"},{"key":"10133_CR28","doi-asserted-by":"crossref","unstructured":"He H, Ma Y (2013) Imbalanced learning: foundations, algorithms, and applications. Wiley","DOI":"10.1002\/9781118646106"},{"key":"10133_CR29","unstructured":"H\u00e9bert A (2020) Estimation of road accident risk with machine learning. Ph.D. Thesis, Concordia University"},{"issue":"2","key":"10133_CR30","first-page":"58","volume":"1","author":"I Hemalatha","year":"2012","unstructured":"Hemalatha I, Varma GP Saradhi, Govardhan A (2012) Preprocessing the informal text for efficient sentiment analysis. Int J Emerging Trends Technol Comput Sci (IJETTCS) 1(2):58\u201361","journal-title":"Int J Emerging Trends Technol Comput Sci (IJETTCS)"},{"key":"10133_CR31","doi-asserted-by":"crossref","unstructured":"Herzig K, Nagappan N (2015) Empirically detecting false test alarms using association rules. In: 2015 IEEE\/ACM 37th IEEE International Conference on Software Engineering (ICSE\u201915), vol 2. IEEE, pp 39\u201348","DOI":"10.1109\/ICSE.2015.133"},{"key":"10133_CR32","doi-asserted-by":"crossref","unstructured":"Jalbert N, Weimer W (2008) Automated duplicate detection for bug tracking systems. In: 2008 IEEE International Conference on Dependable Systems and Networks With FTCS and DCC (DSN). IEEE, pp 52\u201361","DOI":"10.1109\/DSN.2008.4630070"},{"key":"10133_CR33","unstructured":"Jiarpakdee J, Tantithamthavorn C, Hassan AE (2019) The impact of correlated metrics on the interpretation of defect models. IEEE Transactions on Software Engineering (TSE\u201919)"},{"key":"10133_CR34","doi-asserted-by":"crossref","unstructured":"Jiarpakdee J, Tantithamthavorn C, Treude C (2018) Autospearman: Automatically mitigating correlated software metrics for interpreting defect models. In: 2018 IEEE International Conference on Software Maintenance and Evolution (ICSME\u201918). IEEE Computer Society, pp 92\u2013103","DOI":"10.1109\/ICSME.2018.00018"},{"issue":"5","key":"10133_CR35","doi-asserted-by":"publisher","first-page":"3590","DOI":"10.1007\/s10664-020-09848-1","volume":"25","author":"J Jiarpakdee","year":"2020","unstructured":"Jiarpakdee J, Tantithamthavorn C, Treude C (2020) The impact of automated feature selection techniques on the interpretation of defect models. Empir Softw Eng (EMSE\u201920) 25(5):3590\u20133638","journal-title":"Empir Softw Eng (EMSE\u201920)"},{"issue":"1","key":"10133_CR36","first-page":"7","volume":"5","author":"S Kannan","year":"2014","unstructured":"Kannan S, Gurusamy V (2014) Preprocessing techniques for text mining. Int J Comput Sci Commun Netw 5(1):7\u201316","journal-title":"Int J Comput Sci Commun Netw"},{"issue":"4","key":"10133_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2382577.2382579","volume":"6","author":"S Kaufman","year":"2012","unstructured":"Kaufman S, Rosset S, Perlich C, Stitelman O (2012) Leakage in data mining: Formulation, detection, and avoidance. ACM Trans Knowl Discov Data (TKDD\u201912) 6(4):1\u201321","journal-title":"ACM Trans Knowl Discov Data (TKDD\u201912)"},{"issue":"5","key":"10133_CR38","doi-asserted-by":"publisher","first-page":"3396","DOI":"10.1007\/s10664-020-09840-9","volume":"25","author":"D Lee","year":"2020","unstructured":"Lee D, Rajbahadur GK, Lin D, Sayagh M, Bezemer C-P, Hassan AE (2020) An empirical study of the characteristics of popular minecraft mods. Empir Softw Eng (EMSE\u201920) 25(5):3396\u20133429","journal-title":"Empir Softw Eng (EMSE\u201920)"},{"issue":"4","key":"10133_CR39","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1109\/TSE.2008.35","volume":"34","author":"S Lessmann","year":"2008","unstructured":"Lessmann S, Baesens B, Mues C, Pietsch S (2008) Benchmarking classification models for software defect prediction: A proposed framework and novel findings. IEEE Trans Softw Eng (TSE\u201908) 34(4):485\u2013496","journal-title":"IEEE Trans Softw Eng (TSE\u201908)"},{"key":"10133_CR40","unstructured":"Li H, Shang W, Adams B, Sayagh M, Hassan AE (2020) A qualitative study of the benefits and costs of logging from developers\u2019 perspectives. IEEE Transactions on Software Engineering (TSE\u201920)"},{"issue":"3","key":"10133_CR41","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/3236386.3241340","volume":"16","author":"ZC Lipton","year":"2018","unstructured":"Lipton ZC (2018) The mythos of model interpretability. Queue 16(3):31\u201357","journal-title":"Queue"},{"issue":"6","key":"10133_CR42","doi-asserted-by":"publisher","first-page":"2806","DOI":"10.1007\/s10664-016-9488-7","volume":"22","author":"R Malhotra","year":"2017","unstructured":"Malhotra R, Khanna M (2017) An empirical study for software change prediction using imbalanced data. Empir Softw Eng (EMSE\u201917) 22(6):2806\u20132851","journal-title":"Empir Softw Eng (EMSE\u201917)"},{"issue":"5","key":"10133_CR43","doi-asserted-by":"publisher","first-page":"2146","DOI":"10.1007\/s10664-015-9381-9","volume":"21","author":"S McIntosh","year":"2016","unstructured":"McIntosh S, Kamei Y, Adams B, Hassan AE (2016) An empirical study of the impact of modern code review practices on software quality. Empir Softw Eng (EMSE\u201916) 21(5):2146\u20132189","journal-title":"Empir Softw Eng (EMSE\u201916)"},{"issue":"5","key":"10133_CR44","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1109\/TSE.2011.84","volume":"38","author":"C McMillan","year":"2011","unstructured":"McMillan C, Grechanik M, Poshyvanyk D, Fu C, Xie Q (2011) Exemplar: A source code search engine for finding highly relevant applications. IEEE Trans Softw Eng (TSE\u201911) 38(5):1069\u20131087","journal-title":"IEEE Trans Softw Eng (TSE\u201911)"},{"key":"10133_CR45","doi-asserted-by":"crossref","unstructured":"M\u00e9ndez JR, Iglesias EL, Fdez-Riverola F, D\u00edaz F, Corchado JM (2005) Tokenising, stemming and stopword removal on anti-spam filtering domain. In: Conference of the Spanish Association for Artificial Intelligence. Springer, pp 449\u2013458","DOI":"10.1007\/11881216_47"},{"key":"10133_CR46","unstructured":"Meyer TA, Whateley B (2004) Spambayes: Effective open-source, bayesian based, email classification system.. In: CEAS. Citeseer"},{"key":"10133_CR47","doi-asserted-by":"crossref","unstructured":"Mi Q, Keung J (2016) An empirical analysis of reopened bugs based on open source projects. In: Proceedings of the 20th International Conference on Evaluation and Assessment in Software Engineering, pp 1\u201310","DOI":"10.1145\/2915970.2915986"},{"key":"10133_CR48","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.infsof.2018.03.006","volume":"99","author":"Q Mi","year":"2018","unstructured":"Mi Q, Keung J, Huo Y, Mensah S (2018) Not all bug reopens are negative: A case study on eclipse bug reports. Inf Softw Technol 99:93\u201397","journal-title":"Inf Softw Technol"},{"issue":"5","key":"10133_CR49","doi-asserted-by":"publisher","first-page":"3977","DOI":"10.1007\/s10664-020-09861-4","volume":"25","author":"S Morasca","year":"2020","unstructured":"Morasca S, Lavazza L (2020) On the assessment of software defect prediction models via ROC curves. Empir Softw Eng (EMSE\u201920) 25(5):3977\u20134019","journal-title":"Empir Softw Eng (EMSE\u201920)"},{"key":"10133_CR50","unstructured":"Murphy G, Cubranic D (2004) Automatic bug triage using text categorization. In: Proceedings of the Sixteenth International Conference on Software Engineering & Knowledge Engineering. Citeseer, pp 1\u20136"},{"issue":"5","key":"10133_CR51","doi-asserted-by":"publisher","first-page":"4315","DOI":"10.1007\/s10664-020-09871-2","volume":"25","author":"AS Nyamawe","year":"2020","unstructured":"Nyamawe AS, Liu H, Niu N, Umer Q, Niu Z (2020) Feature requests-based recommendation of software refactorings. Empir Softw Eng (EMSE\u201920) 25(5):4315\u20134347","journal-title":"Empir Softw Eng (EMSE\u201920)"},{"key":"10133_CR52","doi-asserted-by":"crossref","unstructured":"Rajbahadur GK, Wang S, Ansaldi G, Kamei Y, Hassan AE (2021) The impact of feature importance methods on the interpretation of defect classifiers. IEEE Transactions on Software Engineering (TSE\u201921)","DOI":"10.1109\/TSE.2021.3056941"},{"key":"10133_CR53","doi-asserted-by":"crossref","unstructured":"Rajbahadur GK, Wang S, Kamei Y, Hassan AE (2017) The impact of using regression models to build defect classifiers. In: 2017 IEEE\/ACM 14th International Conference on Mining Software Repositories (MSR\u201917). IEEE, pp 135\u2013145","DOI":"10.1109\/MSR.2017.4"},{"key":"10133_CR54","unstructured":"Rajbahadur GK, Wang S, Kamei Y, Hassan AE (2019) Impact of discretization noise of the dependent variable on machine learning classifiers in software engineering. IEEE Trans Softw Eng (TSE\u201919):1\u201318"},{"issue":"12","key":"10133_CR55","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1109\/TSE.2017.2755005","volume":"44","author":"MS Rakha","year":"2017","unstructured":"Rakha M S, Bezemer C-P, Hassan AE (2017) Revisiting the performance evaluation of automated approaches for the retrieval of duplicate issue reports. IEEE Trans Softw Eng (TSE\u201917) 44(12):1245\u20131268","journal-title":"IEEE Trans Softw Eng (TSE\u201917)"},{"issue":"2","key":"10133_CR56","doi-asserted-by":"publisher","first-page":"1294","DOI":"10.1007\/s10664-019-09781-y","volume":"25","author":"G Rodr\u00edguez-P\u00e9rez","year":"2020","unstructured":"Rodr\u00edguez-P\u00e9rez G, Robles G, Serebrenik A, Zaidman A, Germ\u00e1n DM, Gonzalez-Barahona JM (2020) How bugs are born: a model to identify how bugs are introduced in software components. Empir Softw Eng (EMSE\u201920) 25(2):1294\u20131340","journal-title":"Empir Softw Eng (EMSE\u201920)"},{"key":"10133_CR57","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1016\/j.infsof.2015.03.002","volume":"65","author":"RK Saha","year":"2015","unstructured":"Saha RK, Khurshid S, Perry DE (2015) Understanding the triaging and fixing processes of long lived bugs. Inf Softw Technol 65:114\u2013128","journal-title":"Inf Softw Technol"},{"key":"10133_CR58","unstructured":"Scikit-learn (2020) Tuning the hyper-parameters of an estimator. https:\/\/scikit-learn.org\/stable\/modules\/grid_search.html#grid-search, [Online; accessed 08-June-2020]"},{"key":"10133_CR59","doi-asserted-by":"crossref","unstructured":"Scoccia GL, Autili M (2020) Web frameworks for desktop apps: an exploratory study. In: Proceedings of the 14th ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM\u201920), pp 1\u20136","DOI":"10.1145\/3382494.3422171"},{"key":"10133_CR60","doi-asserted-by":"crossref","unstructured":"Shihab E, Ihara A, Kamei Y, Ibrahim WM, Ohira M, Adams B, Hassan AE, Matsumoto K- (2010) Predicting re-opened bugs: A case study on the eclipse project. In: 2010 17th Working Conference on Reverse Engineering. IEEE, pp 249\u2013258","DOI":"10.1109\/WCRE.2010.36"},{"issue":"5","key":"10133_CR61","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1007\/s10664-012-9228-6","volume":"18","author":"E Shihab","year":"2013","unstructured":"Shihab E, Ihara A, Kamei Y, Ibrahim WM, Ohira M, Adams B, Hassan AE, Matsumoto Ki (2013) Studying re-opened bugs in open source software. Empir Softw Eng (EMSE\u201913) 18(5):1005\u20131042","journal-title":"Empir Softw Eng (EMSE\u201913)"},{"key":"10133_CR62","doi-asserted-by":"crossref","unstructured":"Somasundaram K, Murphy GC (2012) Automatic categorization of bug reports using latent dirichlet allocation. In: Proceedings of the 5th India software engineering conference, pp 125\u2013130","DOI":"10.1145\/2134254.2134276"},{"issue":"1-2","key":"10133_CR63","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s10044-005-0256-3","volume":"8","author":"F Song","year":"2005","unstructured":"Song F, Liu S, Yang J (2005) A comparative study on text representation schemes in text categorization. Pattern analysis and applications 8(1-2):199\u2013209","journal-title":"Pattern analysis and applications"},{"issue":"11","key":"10133_CR64","first-page":"49","volume":"47","author":"V Srividhya","year":"2010","unstructured":"Srividhya V, Anitha R (2010) Evaluating preprocessing techniques in text categorization. Int J Comput Sci Appl 47(11):49\u201351","journal-title":"Int J Comput Sci Appl"},{"key":"10133_CR65","doi-asserted-by":"crossref","unstructured":"Stolberg S (2009) Enabling agile testing through continuous integration. In: 2009 agile conference. IEEE, pp 369\u2013374","DOI":"10.1109\/AGILE.2009.16"},{"key":"10133_CR66","unstructured":"Tantithamthavorn C, Hassan AE, Matsumoto K (2018) The impact of class rebalancing techniques on the performance and interpretation of defect prediction models. IEEE Transactions on Software Engineering (TSE\u201918)"},{"key":"10133_CR67","doi-asserted-by":"crossref","unstructured":"Tantithamthavorn C, McIntosh S, Hassan AE, Matsumoto K (2016) Automated parameter optimization of classification techniques for defect prediction models. In: Proceedings of the 38th International Conference on Software Engineering (ICSE\u201916), pp 321\u2013332","DOI":"10.1145\/2884781.2884857"},{"issue":"1","key":"10133_CR68","first-page":"1","volume":"43","author":"C Tantithamthavorn","year":"2016","unstructured":"Tantithamthavorn C, McIntosh S, Hassan AE, Matsumoto K (2016) An empirical comparison of model validation techniques for defect prediction models. IEEE Trans Softw Eng (TSE\u201916) 43(1):1\u201318","journal-title":"IEEE Trans Softw Eng (TSE\u201916)"},{"key":"10133_CR69","doi-asserted-by":"crossref","unstructured":"Tian Y, Sun C, Lo D (2012) Improved duplicate bug report identification. In: 2012 16th European Conference on Software Maintenance and Reengineering. IEEE, pp 385\u2013390","DOI":"10.1109\/CSMR.2012.48"},{"key":"10133_CR70","doi-asserted-by":"crossref","unstructured":"Tian Y, Wijedasa D, Lo D, Le Goues C (2016) Learning to rank for bug report assignee recommendation. In: 2016 IEEE 24th International Conference on Program Comprehension (ICPC\u201916). IEEE, pp 1\u201310","DOI":"10.1109\/ICPC.2016.7503715"},{"key":"10133_CR71","doi-asserted-by":"crossref","unstructured":"Tu F, Zhu J, Zheng Q, Zhou M (2018) Be careful of when: an empirical study on time-related misuse of issue tracking data. In: Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp 307\u2013318","DOI":"10.1145\/3236024.3236054"},{"key":"10133_CR72","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.eswa.2018.12.033","volume":"122","author":"H Turabieh","year":"2019","unstructured":"Turabieh H, Mafarja M, Li X (2019) Iterated feature selection algorithms with layered recurrent neural network for software fault prediction. Expert Syst Appl 122:27\u201342","journal-title":"Expert Syst Appl"},{"issue":"1","key":"10133_CR73","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.ipm.2013.08.006","volume":"50","author":"AK Uysal","year":"2014","unstructured":"Uysal AK, Gunal S (2014) The impact of preprocessing on text classification. Inf Process Manag 50(1):104\u2013112","journal-title":"Inf Process Manag"},{"issue":"2","key":"10133_CR74","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1007\/s10664-019-09750-5","volume":"25","author":"C Vassallo","year":"2020","unstructured":"Vassallo C, Panichella S, Palomba F, Proksch S, Gall HC, Zaidman A (2020) How developers engage with static analysis tools in different contexts. Empir Softw Eng (EMSE\u201920) 25(2):1419\u20131457","journal-title":"Empir Softw Eng (EMSE\u201920)"},{"key":"10133_CR75","doi-asserted-by":"crossref","unstructured":"Vieira R, da Silva A, Rocha L, Gomes JP (2019) From reports to bug-fix commits: A 10 years dataset of bug-fixing activity from 55 apache\u2019s open source projects. In: Proceedings of the Fifteenth International Conference on Predictive Models and Data Analytics in Software Engineering, pp 80\u201389","DOI":"10.1145\/3345629.3345639"},{"issue":"2","key":"10133_CR76","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1638\/2019-0219","volume":"51","author":"JK Webb","year":"2020","unstructured":"Webb JK, Keller KA, Welle K, Allender MC (2020) Evaluation of the inter-and intraindividual agreement of a pododermatitis scoring model in greater flamingos (phoenicopterus roseus). J Zoo Wildlife Med 51(2):379\u2013384","journal-title":"J Zoo Wildlife Med"},{"issue":"3","key":"10133_CR77","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/TSE.2016.2576454","volume":"43","author":"X Xia","year":"2016","unstructured":"Xia X, Lo D, Ding Y, Al-Kofahi JM, Nguyen TN, Wang X (2016) Improving automated bug triaging with specialized topic model. IEEE Trans Softw Eng (TSE\u201916) 43(3):272\u2013297","journal-title":"IEEE Trans Softw Eng (TSE\u201916)"},{"issue":"1","key":"10133_CR78","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/s10515-014-0162-2","volume":"22","author":"X Xia","year":"2015","unstructured":"Xia X, Lo D, Shihab E, Wang X, Zhou B (2015) Automatic, high accuracy prediction of reopened bugs. Autom Softw Eng (ASE\u201915) 22(1):75\u2013109","journal-title":"Autom Softw Eng (ASE\u201915)"},{"key":"10133_CR79","doi-asserted-by":"crossref","unstructured":"Xia X, Lo D, Wang X, Yang X, Li S, Sun J (2013) A comparative study of supervised learning algorithms for re-opened bug prediction. In: 2013 17th European Conference on Software Maintenance and Reengineering. IEEE, pp 331\u2013334","DOI":"10.1109\/CSMR.2013.43"},{"key":"10133_CR80","doi-asserted-by":"crossref","unstructured":"Xia X, Lo D, Wang X, Zhou B (2013) Accurate developer recommendation for bug resolution. In: 2013 20th Working Conference on Reverse Engineering (WCRE). IEEE, pp 72\u201381","DOI":"10.1109\/WCRE.2013.6671282"},{"key":"10133_CR81","doi-asserted-by":"crossref","unstructured":"Xia X, Lo D, Wen M, Shihab E, Zhou B (2014) An empirical study of bug report field reassignment. In: 2014 Software Evolution Week-IEEE Conference on Software Maintenance, Reengineering, and Reverse Engineering (CSMR-WCRE\u201914). IEEE, pp 174\u2013183","DOI":"10.1109\/CSMR-WCRE.2014.6747167"},{"issue":"1","key":"10133_CR82","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1109\/TKDE.2014.2324590","volume":"27","author":"J Xuan","year":"2014","unstructured":"Xuan J, Jiang H, Hu Y, Ren Z, Zou W, Luo Z, Wu X (2014) Towards effective bug triage with software data reduction techniques. IEEE Trans Knowl Data Eng 27(1):264\u2013280","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"10133_CR83","doi-asserted-by":"crossref","unstructured":"Xuan J, Jiang H, Ren Z, Zou W (2012) Developer prioritization in bug repositories. In: 2012 34th International Conference on Software Engineering (ICSE\u201912). IEEE, pp 25\u201335","DOI":"10.1109\/ICSE.2012.6227209"},{"key":"10133_CR84","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.infsof.2019.03.014","volume":"112","author":"A Yadav","year":"2019","unstructured":"Yadav A, Singh SK, Suri JS (2019) Ranking of software developers based on expertise score for bug triaging. Inf Softw Technol 112:1\u201317","journal-title":"Inf Softw Technol"},{"key":"10133_CR85","doi-asserted-by":"crossref","unstructured":"Yatish S, Jiarpakdee J, Thongtanunam P, Tantithamthavorn C (2019) Mining software defects: should we consider affected releases?. In: IEEE\/ACM 41st International Conference on Software Engineering (ICSE\u201919). IEEE, pp 654\u2013665","DOI":"10.1109\/ICSE.2019.00075"},{"key":"10133_CR86","doi-asserted-by":"crossref","unstructured":"Zeng Y, Jiang K, Chen J (2019) Automatic seismic salt interpretation with deep convolutional neural networks. In: Proceedings of the 3rd International Conference on Information System and Data Mining, pp 16\u201320","DOI":"10.1145\/3325917.3325926"},{"key":"10133_CR87","unstructured":"Zhang H, Wang S, Chen T-H, Hassan AE (2020) Are comments on stack overflow well organized for easy retrieval by developers? ACM Trans Softw Eng Methodol (TOSEM\u201920) 29"},{"key":"10133_CR88","unstructured":"Zhang H, Wang S, Chen T-H, Zou Y, Hassan AE (2019) An empirical study of obsolete answers on Stack Overflow. IEEE Transactions on Software Engineering (TSE\u201919)"},{"key":"10133_CR89","unstructured":"Zheng A, Casari A (2018) Feature engineering for machine learning: principles and techniques for data scientists. O\u2019Reilly Media, Inc."},{"key":"10133_CR90","doi-asserted-by":"crossref","unstructured":"Zimmermann T, Nagappan N, Guo PJ, Murphy B (2012) Characterizing and predicting which bugs get reopened. In: 2012 34th International Conference on Software Engineering (ICSE\u201912). IEEE, pp 1074\u20131083","DOI":"10.1109\/ICSE.2012.6227112"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-022-10133-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-022-10133-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-022-10133-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,9]],"date-time":"2022-06-09T21:05:06Z","timestamp":1654808706000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-022-10133-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":90,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["10133"],"URL":"https:\/\/doi.org\/10.1007\/s10664-022-10133-6","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"16 February 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}],"article-number":"92"}}