{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T18:46:21Z","timestamp":1758048381646,"version":"3.44.0"},"reference-count":178,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T00:00:00Z","timestamp":1753228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T00:00:00Z","timestamp":1753228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s10664-025-10692-4","type":"journal-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T12:39:53Z","timestamp":1753274393000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comprehensive predictive analytics for collaborators\u2019 answers, code quality, and dropout: stack overflow case study"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6975-2890","authenticated-orcid":false,"given":"Elijah","family":"Zolduoarrati","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sherlock A.","family":"Licorish","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nigel","family":"Stanger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,23]]},"reference":[{"doi-asserted-by":"publisher","unstructured":"Abida A, Majdoul R, Zegrari M (2024) The electric vehicle requested energy predictions using machine learning algorithms for the demand side management. In: El Fadil H, Zhang W (eds) Automatic control and emerging technologies. Automatic control and emerging technologies, pp 608\u2013617. https:\/\/doi.org\/10.1007\/978-981-97-0126-1_54","key":"10692_CR1","DOI":"10.1007\/978-981-97-0126-1_54"},{"doi-asserted-by":"publisher","unstructured":"Adaji I, Vassileva J (2015) Predicting churn of expert respondents in social networks using data mining techniques: a case study of stack overflow. In: 2015 IEEE 14th international conference on machine learning and applications (ICMLA), pp 182\u2013189. https:\/\/doi.org\/10.1109\/ICMLA.2015.120","key":"10692_CR2","DOI":"10.1109\/ICMLA.2015.120"},{"doi-asserted-by":"publisher","unstructured":"Adoma AF, Henry NM, Chen W (2020) Comparative analyses of bert, roberta, distilbert, and xlnet for text-based emotion recognition. In: 2020 17th international computer conference on wavelet active media technology and information processing (ICCWAMTIP), pp 117\u2013121. https:\/\/doi.org\/10.1109\/ICCWAMTIP51612.2020.9317379","key":"10692_CR3","DOI":"10.1109\/ICCWAMTIP51612.2020.9317379"},{"doi-asserted-by":"publisher","unstructured":"Ahasanuzzaman M, Asaduzzaman M, Roy CK, Schneider KA (2016) Mining duplicate questions in stack overflow. In: Proceedings of the 13th international conference on mining software repositories, pp 402\u2013412. https:\/\/doi.org\/10.1145\/2901739.2901770","key":"10692_CR4","DOI":"10.1145\/2901739.2901770"},{"doi-asserted-by":"publisher","unstructured":"Ahasanuzzaman M, Asaduzzaman M, Roy CK, Schneider KA (2018) Classifying stack overflow posts on API issues. In: 2018 IEEE 25th international conference on software analysis, evolution and reengineering (SANER), pp 244\u2013254. https:\/\/doi.org\/10.1109\/SANER.2018.8330213","key":"10692_CR5","DOI":"10.1109\/SANER.2018.8330213"},{"doi-asserted-by":"publisher","unstructured":"Akiba T, Sano S, Yanase T, Ohta T, Koyama M (2019) Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp 2623\u20132631. https:\/\/doi.org\/10.1145\/3292500.3330701","key":"10692_CR6","DOI":"10.1145\/3292500.3330701"},{"issue":"429","key":"10692_CR7","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1080\/01621459.1995.10476499","volume":"90","author":"MG Akritas","year":"1995","unstructured":"Akritas MG, Murphy SA, Lavalley MP (1995) The Theil-Sen estimator with doubly censored data and applications to astronomy. J Am Stat Assoc 90(429):170\u2013177. https:\/\/doi.org\/10.1080\/01621459.1995.10476499","journal-title":"J Am Stat Assoc"},{"doi-asserted-by":"publisher","unstructured":"Alharthi H, Outioua D, Baysal O (2016) Predicting questions' scores on stack overflow. In: 2016 IEEE\/ACM 3rd international workshop on crowdsourcing in software engineering (CSI-SE), pp 1\u20137. https:\/\/doi.org\/10.1145\/2897659.2897661","key":"10692_CR8","DOI":"10.1145\/2897659.2897661"},{"doi-asserted-by":"publisher","unstructured":"Alonso H, Costa PD, Fernando J (2025) Over-sampling methods for mixed data in imbalanced problems. Commun Stat - Simul Comput 1\u201323. https:\/\/doi.org\/10.1080\/03610918.2024.2447451","key":"10692_CR9","DOI":"10.1080\/03610918.2024.2447451"},{"doi-asserted-by":"publisher","unstructured":"Anderson A, Huttenlocher D, Kleinberg J, Leskovec J (2012) Discovering value from community activity on focused question answering sites: a case study of stack overflow. In: Proceedings of the 18th ACM SIGKDD international conference on knowledge discovery and data mining, pp 850\u2013858. https:\/\/doi.org\/10.1145\/2339530.2339665","key":"10692_CR10","DOI":"10.1145\/2339530.2339665"},{"unstructured":"Anghel AS, Papandreou N, Parnell T, De Palma A, Pozidis H (2018) Benchmarking and optimization of gradient boosting decision tree algorithms. Annu Conf Neural Inf Process Syst. Retrieved 22 February, 2024, from http:\/\/learningsys.org\/nips18\/assets\/papers\/68CameraReadySubmissionboosting_paper_mlsys_neurips_2018_cr.pdf","key":"10692_CR11"},{"unstructured":"Ansary N, Adib QAR, Reasat T, Sushmit AS, Humayun AI, Mehnaz S,..., Sadeque F (2024) Unicode normalization and grapheme parsing of indic languages. In: Calzolari N et al (eds) Proceedings of the 2024 joint international conference on computational linguistics, language resources and evaluation (LREC-COLING 2024). 17019\u201317030. Retrieved 24 May, 2024, from https:\/\/aclanthology.org\/2024.lrec-main.1479","key":"10692_CR12"},{"doi-asserted-by":"publisher","unstructured":"Arunachalaeshwaran VR, Mahdi HF, Choudhury T, Sarkar T, Bhuyan BP (2022) Freshness classification of hog plum fruit using deep learning.In: 2022 international congress on human-computer interaction, optimization and robotic applications (HORA), pp 1\u20136. https:\/\/doi.org\/10.1109\/HORA55278.2022.9799897","key":"10692_CR13","DOI":"10.1109\/HORA55278.2022.9799897"},{"doi-asserted-by":"publisher","unstructured":"Asaduzzaman M, Mashiyat AS, Roy CK, Schneider KA (2013) Answering questions about unanswered questions of stack overflow. In: 2013 10th working conference on mining software repositories (MSR), pp 97\u2013100. https:\/\/doi.org\/10.1109\/MSR.2013.6624015","key":"10692_CR14","DOI":"10.1109\/MSR.2013.6624015"},{"issue":"6","key":"10692_CR15","doi-asserted-by":"publisher","first-page":"3360","DOI":"10.1080\/10494820.2021.1928235","volume":"31","author":"A Asselman","year":"2023","unstructured":"Asselman A, Khaldi M, Aammou S (2023) Enhancing the prediction of student performance based on the machine learning XGBoost algorithm. Interact Learn Environ 31(6):3360\u20133379. https:\/\/doi.org\/10.1080\/10494820.2021.1928235","journal-title":"Interact Learn Environ"},{"unstructured":"Baltadzhieva A, Chrupa\u0142a G (2015) Predicting the quality of questions on Stackoverflow. In Mitkov R et al (eds) Proceedings of the international conference recent advances in natural language processing, pp 32\u201340. Retrieved 6 March, 2024, from https:\/\/aclanthology.org\/R15-1005","key":"10692_CR16"},{"doi-asserted-by":"publisher","unstructured":"Barazandeh B, Razaviyayn M (2018) On the behavior of the expectation-maximization algorithm for mixture models. In: 2018 IEEE global conference on signal and information processing (GlobalSIP), pp 61\u201365. https:\/\/doi.org\/10.1109\/GlobalSIP.2018.8646506","key":"10692_CR17","DOI":"10.1109\/GlobalSIP.2018.8646506"},{"issue":"3","key":"10692_CR18","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/s10664-012-9231-y","volume":"19","author":"A Barua","year":"2014","unstructured":"Barua A, Thomas SW, Hassan AE (2014) What are developers talking about? An analysis of topics and trends in stack overflow. Empir Softw Eng 19(3):619\u2013654. https:\/\/doi.org\/10.1007\/s10664-012-9231-y","journal-title":"Empir Softw Eng"},{"issue":"12","key":"10692_CR19","doi-asserted-by":"publisher","first-page":"7305","DOI":"10.1007\/s10115-024-02214-3","volume":"66","author":"H Bashiri","year":"2024","unstructured":"Bashiri H, Naderi H (2024) Comprehensive review and comparative analysis of transformer models in sentiment analysis. Knowl Inf Syst 66(12):7305\u20137361. https:\/\/doi.org\/10.1007\/s10115-024-02214-3","journal-title":"Knowl Inf Syst"},{"key":"10692_CR20","doi-asserted-by":"publisher","first-page":"106917","DOI":"10.1016\/j.csda.2020.106917","volume":"145","author":"A Bedoui","year":"2020","unstructured":"Bedoui A, Lazar NA (2020) Bayesian empirical likelihood for ridge and lasso regressions. Comput Stat Data Anal 145:106917. https:\/\/doi.org\/10.1016\/j.csda.2020.106917","journal-title":"Comput Stat Data Anal"},{"key":"10692_CR21","doi-asserted-by":"publisher","first-page":"147306","DOI":"10.1109\/ACCESS.2021.3124268","volume":"9","author":"A Benayas","year":"2021","unstructured":"Benayas A, Hashempour R, Rumble D, Jameel S, Amorim RCD (2021) Unified transformer multi-task learning for intent classification with entity recognition. IEEE Access 9:147306\u2013147314. https:\/\/doi.org\/10.1109\/ACCESS.2021.3124268","journal-title":"IEEE Access"},{"issue":"2","key":"10692_CR22","doi-asserted-by":"publisher","first-page":"025003","DOI":"10.1088\/2632-2153\/abc9fd","volume":"2","author":"M Benoit","year":"2021","unstructured":"Benoit M, Amodeo J, Combettes S, Khaled I, Roux A, Lam J (2021) Measuring transferability issues in machine-learning force fields: the example of gold\u2013iron interactions with linearized potentials. Mach Learn: Sci Technol 2(2):025003. https:\/\/doi.org\/10.1088\/2632-2153\/abc9fd","journal-title":"Mach Learn: Sci Technol"},{"issue":"3","key":"10692_CR23","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1186\/s12911-016-0318-z","volume":"16","author":"L Beretta","year":"2016","unstructured":"Beretta L, Santaniello A (2016) Nearest neighbor imputation algorithms: a critical evaluation. BMC Med Inform Decis Mak 16(3):74. https:\/\/doi.org\/10.1186\/s12911-016-0318-z","journal-title":"BMC Med Inform Decis Mak"},{"doi-asserted-by":"publisher","unstructured":"Bhowmick S, Saha A (2023) Enhancing the performance of kNN for glass identification dataset using inverse distance weight, ReliefF ranking and SMOTE. AIP Conf Proc 2754(1). https:\/\/doi.org\/10.1063\/5.0161083","key":"10692_CR24","DOI":"10.1063\/5.0161083"},{"doi-asserted-by":"publisher","unstructured":"Biswas E, Karabulut ME, Pollock L, Vijay-Shanker K (2020) Achieving reliable sentiment analysis in the software engineering domain using BERT. In: 2020 IEEE international conference on software maintenance and evolution (ICSME), pp 162\u2013173. https:\/\/doi.org\/10.1109\/ICSME46990.2020.00025","key":"10692_CR25","DOI":"10.1109\/ICSME46990.2020.00025"},{"doi-asserted-by":"publisher","unstructured":"Bowen D, Murphy B, Cai W, Khachaturov D, Gleave A, Pelrine K (2024) Scaling laws for data poisoning in llms. Preprint at https:\/\/arxiv.org\/abs\/2408.02946. https:\/\/doi.org\/10.48550\/arXiv.2408.02946","key":"10692_CR26","DOI":"10.48550\/arXiv.2408.02946"},{"issue":"4","key":"10692_CR27","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/3529318","volume":"32","author":"HB Braiek","year":"2023","unstructured":"Braiek HB, Khomh F (2023) Testing feedforward neural networks training programs. ACM Trans Softw Eng Methodol 32(4):105. https:\/\/doi.org\/10.1145\/3529318. (Article)","journal-title":"ACM Trans Softw Eng Methodol"},{"doi-asserted-by":"publisher","unstructured":"Broughel J, Thierer AD (2019) Technological innovation and economic growth: a brief report on the evidence. Mercatus Res Paper. https:\/\/doi.org\/10.2139\/ssrn.3346495","key":"10692_CR28","DOI":"10.2139\/ssrn.3346495"},{"doi-asserted-by":"publisher","unstructured":"Cabello-Solorzano K, Ortigosa de Araujo I, Pe\u00f1a M, Correia L, J. Tall\u00f3n-Ballesteros A (2023) The impact of\u00a0data normalization on\u00a0the\u00a0accuracy of\u00a0machine learning algorithms: a comparative analysis. In: 18th international conference on soft computing models in industrial and environmental applications (SOCO 2023), pp 344\u2013353. https:\/\/doi.org\/10.1007\/978-3-031-42536-3_33","key":"10692_CR29","DOI":"10.1007\/978-3-031-42536-3_33"},{"issue":"3","key":"10692_CR30","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1093\/biomet\/68.3.609","volume":"68","author":"RJ Carroll","year":"1981","unstructured":"Carroll RJ, Ruppert D (1981) On prediction and the power transformation family. Biometrika 68(3):609\u2013615. https:\/\/doi.org\/10.1093\/biomet\/68.3.609","journal-title":"Biometrika"},{"issue":"6","key":"10692_CR31","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1007\/s00500-013-1131-6","volume":"18","author":"V Ceperic","year":"2014","unstructured":"Ceperic V, Gielen G, Baric A (2014) Sparse E-tube support vector regression by active learning. Soft Comput 18(6):1113\u20131126. https:\/\/doi.org\/10.1007\/s00500-013-1131-6","journal-title":"Soft Comput"},{"doi-asserted-by":"publisher","unstructured":"Cerchiello P, Nicola G, Ronnqvist S, Sarlin P (2018) Deep learning bank distress from news and numerical financial data. arXiv Mach Learn. https:\/\/doi.org\/10.48550\/arXiv.1706.09627","key":"10692_CR32","DOI":"10.48550\/arXiv.1706.09627"},{"issue":"6","key":"10692_CR33","doi-asserted-by":"publisher","first-page":"2999","DOI":"10.1016\/j.rse.2008.02.011","volume":"112","author":"JC-W Chan","year":"2008","unstructured":"Chan JC-W, Paelinckx D (2008) Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery. Remote Sens Environ 112(6):2999\u20133011. https:\/\/doi.org\/10.1016\/j.rse.2008.02.011","journal-title":"Remote Sens Environ"},{"doi-asserted-by":"publisher","unstructured":"Chen Y, Hemlani A, Zheng S (2022) A comparison of supervised classification methods for classifying biological cell types. In: Proceedings of the 2021 5th international conference on computational biology and bioinformatics, pp 23\u201329. https:\/\/doi.org\/10.1145\/3512452.3512456","key":"10692_CR34","DOI":"10.1145\/3512452.3512456"},{"doi-asserted-by":"publisher","unstructured":"Chen J, Wu P, Li J, Xu L (2023) More robust and better: automatic traffic incident detection based on XGBoost. In: Advances in traffic transportation and civil architecture. Boca Raton, FL: CRC Press, pp 267\u2013274. https:\/\/doi.org\/10.1201\/9781003402220-31","key":"10692_CR35","DOI":"10.1201\/9781003402220-31"},{"issue":"7","key":"10692_CR36","doi-asserted-by":"publisher","first-page":"1605","DOI":"10.1016\/j.neucom.2008.09.002","volume":"72","author":"T Chen","year":"2009","unstructured":"Chen T, Ren J (2009) Bagging for Gaussian process regression. Neurocomputing 72(7):1605\u20131610. https:\/\/doi.org\/10.1016\/j.neucom.2008.09.002","journal-title":"Neurocomputing"},{"doi-asserted-by":"publisher","unstructured":"Choetkiertikul M, Avery D, Dam HK, Tran T, Ghose A (2015) Who will answer my question on stack overflow?. In: 2015 24th Australasian software engineering conference, pp 155\u2013164. https:\/\/doi.org\/10.1109\/ASWEC.2015.28","key":"10692_CR37","DOI":"10.1109\/ASWEC.2015.28"},{"issue":"28","key":"10692_CR38","doi-asserted-by":"publisher","first-page":"41225","DOI":"10.1007\/s11042-022-12330-3","volume":"81","author":"R Chowdhury","year":"2022","unstructured":"Chowdhury R, Sen S, Roy A, Saha B (2022) An optimal feature based network intrusion detection system using bagging ensemble method for real-time traffic analysis. Multimed Tools Appl 81(28):41225\u201341247. https:\/\/doi.org\/10.1007\/s11042-022-12330-3","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"10692_CR39","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1007\/s10115-013-0665-3","volume":"36","author":"D Cook","year":"2013","unstructured":"Cook D, Feuz KD, Krishnan NC (2013) Transfer learning for activity recognition: a survey. Knowl Inf Syst 36(3):537\u2013556. https:\/\/doi.org\/10.1007\/s10115-013-0665-3","journal-title":"Knowl Inf Syst"},{"doi-asserted-by":"publisher","unstructured":"Correa D, Sureka A (2013) Fit or unfit: analysis and prediction of 'closed questions' on stack overflow. In: Proceedings of the first ACM conference on online social networks, pp 201\u2013212. https:\/\/doi.org\/10.1145\/2512938.2512954","key":"10692_CR40","DOI":"10.1145\/2512938.2512954"},{"issue":"3","key":"10692_CR41","doi-asserted-by":"publisher","first-page":"189","DOI":"10.14358\/PERS.82.3.189","volume":"82","author":"JW Coulston","year":"2016","unstructured":"Coulston JW, Blinn CE, Thomas VA, Wynne RH (2016) Approximating prediction uncertainty for random forest regression models. Photogramm Eng Remote Sens 82(3):189\u2013197. https:\/\/doi.org\/10.14358\/PERS.82.3.189","journal-title":"Photogramm Eng Remote Sens"},{"doi-asserted-by":"publisher","unstructured":"Cuzzocrea A, Francis SL, Gaber MM (2013) An information-theoretic approach for setting the optimal number of decision trees in random forests. In: 2013 IEEE international conference on systems, man, and cybernetics, pp 1013\u20131019. https:\/\/doi.org\/10.1109\/SMC.2013.177","key":"10692_CR42","DOI":"10.1109\/SMC.2013.177"},{"issue":"5","key":"10692_CR43","doi-asserted-by":"publisher","first-page":"2158","DOI":"10.3390\/app11052158","volume":"11","author":"FK Dankar","year":"2021","unstructured":"Dankar FK, Ibrahim M (2021) Fake it till you make it: guidelines for effective synthetic data generation. Appl Sci 11(5):2158. https:\/\/doi.org\/10.3390\/app11052158","journal-title":"Appl Sci"},{"issue":"15","key":"10692_CR44","doi-asserted-by":"publisher","first-page":"3354","DOI":"10.3390\/electronics12153354","volume":"12","author":"I de Zarz\u00e0","year":"2023","unstructured":"de Zarz\u00e0 I, de Curt\u00f2 J, Hern\u00e1ndez-Orallo E, Calafate CT (2023) Cascading and ensemble techniques in deep learning. Electronics 12(15):3354. https:\/\/doi.org\/10.3390\/electronics12153354","journal-title":"Electronics"},{"doi-asserted-by":"publisher","unstructured":"Duijn M, Kucera A, Bacchelli A (2015) Quality questions need quality code: classifying code fragments on stack overflow. In: 2015 IEEE\/ACM 12th working conference on mining software repositories, pp 410\u2013413. https:\/\/doi.org\/10.1109\/MSR.2015.51","key":"10692_CR45","DOI":"10.1109\/MSR.2015.51"},{"unstructured":"Eberhard O, Zesch T (2021) Effects of layer freezing on transferring a speech recognition system to under-resourced languages. In Evang K et al (eds) Proceedings of the 17th conference on natural language processing (KONVENS 2021), pp 208\u2013212. Retrieved 22 April, 2024, from https:\/\/aclanthology.org\/2021.konvens-1.19","key":"10692_CR46"},{"unstructured":"Fazeli A (2024) Machine learning-based automated vulnerability classification in c\/c++ software: the future of automated software vulnerability classification. (Student thesis). Retrieved 13 November, 2024, from https:\/\/urn.kb.se\/resolve?urn=urn:nbn:se:liu:diva-204019","key":"10692_CR47"},{"issue":"2","key":"10692_CR48","doi-asserted-by":"publisher","first-page":"105","DOI":"10.3969\/j.issn.1002-0829.2014.02.009","volume":"26","author":"C Feng","year":"2014","unstructured":"Feng C, Wang H, Lu N, Chen T, He H, Lu Y, Tu XM (2014) Log-transformation and its implications for data analysis. Shanghai Arch Psychiatry 26(2):105\u2013109. https:\/\/doi.org\/10.3969\/j.issn.1002-0829.2014.02.009","journal-title":"Shanghai Arch Psychiatry"},{"doi-asserted-by":"publisher","unstructured":"Feng Z, Guo D, Tang D, Duan N, Feng X, Gong M,..., Zhou M (2020) CodeBERT: a pre-trained model for programming and natural languages. In: Cohn T et al (eds) Findings of the association for computational linguistics: EMNLP 2020. Findings of the association for computational linguistics: EMNLP 2020, pp 1536\u20131547. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.139","key":"10692_CR49","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"doi-asserted-by":"publisher","unstructured":"Fink GA (2014) n-Gram models. In: Markov models for pattern recognition: from theory to applications. London: Springer London, pp 107\u2013127. https:\/\/doi.org\/10.1007\/978-1-4471-6308-4_6","key":"10692_CR50","DOI":"10.1007\/978-1-4471-6308-4_6"},{"doi-asserted-by":"publisher","unstructured":"Gama E, Cort\u00e9s M, Paixao M, Damasceno A (2023) Machine learning for the identification and classification of technical debt types on stackoverflow discussions. An do III Work Bras Engenharia Softw Inteligente 25\u201330. https:\/\/doi.org\/10.5753\/ise.2023.235840","key":"10692_CR51","DOI":"10.5753\/ise.2023.235840"},{"doi-asserted-by":"publisher","unstructured":"Ge J, Li H, Wang H, Dong H, Liu H, Wang W,..., Zhang H (2019) Aeromagnetic compensation algorithm robust to outliers of magnetic sensor based on huber loss method. IEEE Sensors J 19(14):5499\u20135505. https:\/\/doi.org\/10.1109\/JSEN.2019.2907398","key":"10692_CR52","DOI":"10.1109\/JSEN.2019.2907398"},{"key":"10692_CR53","doi-asserted-by":"publisher","first-page":"122511","DOI":"10.1016\/j.molliq.2023.122511","volume":"387","author":"M Ghazwani","year":"2023","unstructured":"Ghazwani M, Begum Y (2023) Machine learning aided drug development: assessing improvement of drug efficiency by correlation of solubility in supercritical solvent for nanomedicine preparation. J Mol Liq 387:122511. https:\/\/doi.org\/10.1016\/j.molliq.2023.122511","journal-title":"J Mol Liq"},{"doi-asserted-by":"publisher","unstructured":"Gonz\u00e1lez-Briones A, Hern\u00e1ndez G, Pinto T, Vale Z, Corchado JM (2019) A review of the main machine learning methods for predicting residential energy consumption. In: 2019 16th international conference on the European energy market (EEM), pp 1\u20136. https:\/\/doi.org\/10.1109\/EEM.2019.8916406","key":"10692_CR54","DOI":"10.1109\/EEM.2019.8916406"},{"doi-asserted-by":"publisher","unstructured":"Gumus M, Kiran MS (2017) Crude oil price forecasting using XGBoost. In: 2017 international conference on computer science and engineering (UBMK), pp 1100\u20131103. https:\/\/doi.org\/10.1109\/UBMK.2017.8093500","key":"10692_CR55","DOI":"10.1109\/UBMK.2017.8093500"},{"issue":"2","key":"10692_CR56","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1002\/gepi.21608","volume":"36","author":"RT Guy","year":"2012","unstructured":"Guy RT, Santago P, Langefeld CD (2012) Bootstrap aggregating of alternating decision trees to detect sets of SNPs that associate with disease. Genet Epidemiol 36(2):99\u2013106. https:\/\/doi.org\/10.1002\/gepi.21608","journal-title":"Genet Epidemiol"},{"issue":"1.2","key":"10692_CR57","doi-asserted-by":"publisher","first-page":"35","DOI":"10.2152\/jmi.66.35","volume":"66","author":"A Haga","year":"2019","unstructured":"Haga A, Takahashi W, Aoki S, Nawa K, Yamashita H, Abe O, Nakagawa K (2019) Standardization of imaging features for radiomics analysis. J Med Investig 66(1.2):35\u201337. https:\/\/doi.org\/10.2152\/jmi.66.35","journal-title":"J Med Investig"},{"doi-asserted-by":"publisher","unstructured":"He J, Xu B, Yang Z, Han D, Yang C, Lo D (2022) PTM4Tag: sharpening tag recommendation of stack overflow posts with pre-trained models. In: Proceedings of the 30th IEEE\/ACM international conference on program comprehension, pp 1\u201311. https:\/\/doi.org\/10.1145\/3524610.3527897","key":"10692_CR58","DOI":"10.1145\/3524610.3527897"},{"doi-asserted-by":"publisher","unstructured":"He J, Zhou X, Xu B, Zhang T, Kim K, Yang Z,..., Lo D (2024) Representation learning for stack overflow posts: how far are we?. ACM Trans Softw Eng Methodol 33(3): 69. https:\/\/doi.org\/10.1145\/3635711 (Article)","key":"10692_CR59","DOI":"10.1145\/3635711"},{"doi-asserted-by":"publisher","unstructured":"Helsel DR, Hirsch RM, Ryberg KR, Archfield SA, Gilroy EJ (2020) Statistical methods in water resources (Report No. 4-A3). https:\/\/doi.org\/10.3133\/tm4A3","key":"10692_CR60","DOI":"10.3133\/tm4A3"},{"doi-asserted-by":"publisher","unstructured":"Heyburn R, Bond RR, Black M, Mulvenna M, Wallace J, Rankin D, Cleland B (2018) Machine learning using synthetic and real data: similarity of evaluation metrics for different healthcare datasets and for different algorithms. In: Data science and knowledge engineering for sensing decision support: proceedings of the 13th international FLINS conference (FLINS 2018), pp 1281\u20131291. https:\/\/doi.org\/10.1142\/9789813273238_0160","key":"10692_CR61","DOI":"10.1142\/9789813273238_0160"},{"key":"10692_CR62","doi-asserted-by":"publisher","first-page":"100421","DOI":"10.1016\/j.envc.2021.100421","volume":"6","author":"B Ibrahim","year":"2022","unstructured":"Ibrahim B, Majeed F, Ewusi A, Ahenkorah I (2022) Residual geochemical gold grade prediction using extreme gradient boosting. Environ Challenges 6:100421. https:\/\/doi.org\/10.1016\/j.envc.2021.100421","journal-title":"Environ Challenges"},{"issue":"1","key":"10692_CR63","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1057\/s41599-024-03239-3","volume":"11","author":"M Jang","year":"2024","unstructured":"Jang M, Kim S (2024) Key traits of top answerers on Korean social Q&A platforms: insights into user performance and entrepreneurial potential. Humanit Soc Sci Commun 11(1):744. https:\/\/doi.org\/10.1057\/s41599-024-03239-3","journal-title":"Humanit Soc Sci Commun"},{"issue":"2","key":"10692_CR64","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1109\/TFUZZ.2011.2174997","volume":"20","author":"CF Juang","year":"2012","unstructured":"Juang CF, Hsieh CD (2012) A fuzzy system constructed by rule generation and iterative linear SVR for antecedent and consequent parameter optimization. IEEE Trans Fuzzy Syst 20(2):372\u2013384. https:\/\/doi.org\/10.1109\/TFUZZ.2011.2174997","journal-title":"IEEE Trans Fuzzy Syst"},{"doi-asserted-by":"publisher","unstructured":"Kabir S, Udo-Imeh DN, Kou B, Zhang T (2024) Is stack overflow obsolete? an empirical study of the characteristics of ChatGPT answers to stack overflow questions. In: Proceedings of the CHI conference on human factors in computing systems, p 935. https:\/\/doi.org\/10.1145\/3613904.3642596 (Article)","key":"10692_CR65","DOI":"10.1145\/3613904.3642596"},{"key":"10692_CR66","doi-asserted-by":"publisher","first-page":"100832","DOI":"10.1016\/j.uclim.2021.100832","volume":"37","author":"A Kashki","year":"2021","unstructured":"Kashki A, Karami M, Zandi R, Roki Z (2021) Evaluation of the effect of geographical parameters on the formation of the land surface temperature by applying OLS and GWR, a case study Shiraz City, Iran. Urban Clim 37:100832. https:\/\/doi.org\/10.1016\/j.uclim.2021.100832","journal-title":"Urban Clim"},{"issue":"6","key":"10692_CR67","doi-asserted-by":"publisher","first-page":"1014","DOI":"10.1016\/S0029-7844(98)00537-7","volume":"93","author":"KS Khan","year":"1999","unstructured":"Khan KS, Chien PFW, Dwarakanath LS (1999) Logistic regression models in obstetrics and gynecology literature. Obstet Gynecol 93(6):1014\u20131020. https:\/\/doi.org\/10.1016\/S0029-7844(98)00537-7","journal-title":"Obstet Gynecol"},{"doi-asserted-by":"publisher","unstructured":"Khurana U, Samulowitz H, Turaga D (2018) Feature engineering for predictive modeling using reinforcement learning. Proc AAAI Conf Artif Intell 32(1). https:\/\/doi.org\/10.1609\/aaai.v32i1.11678","key":"10692_CR68","DOI":"10.1609\/aaai.v32i1.11678"},{"doi-asserted-by":"publisher","unstructured":"Kloberdanz E, Kloberdanz KG, Le W (2022) DeepStability: a study of unstable numerical methods and their solutions in deep learning. In: Proceedings of the 44th international conference on software engineering, pp 586\u2013597. https:\/\/doi.org\/10.1145\/3510003.3510095","key":"10692_CR69","DOI":"10.1145\/3510003.3510095"},{"doi-asserted-by":"publisher","unstructured":"Lartey B, Homaifar A, Girma A, Karimoddini A, Opoku D (2021) XGBoost: a tree-based approach for traffic volume prediction. In: 2021 IEEE international conference on systems, man, and cybernetics (SMC), pp 1280\u20131286. https:\/\/doi.org\/10.1109\/SMC52423.2021.9658959","key":"10692_CR70","DOI":"10.1109\/SMC52423.2021.9658959"},{"doi-asserted-by":"publisher","unstructured":"Lewkowycz A (2021) How to decay your learning rate. arXiv Mach Learn. https:\/\/doi.org\/10.48550\/arXiv.2103.12682","key":"10692_CR71","DOI":"10.48550\/arXiv.2103.12682"},{"issue":"2","key":"10692_CR72","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/S1876-3804(12)60041-X","volume":"39","author":"X Li","year":"2012","unstructured":"Li X, Zhou J, Li H, Zhang S, Chen Y (2012) Computational intelligent methods for predicting complex ithologies and multiphase fluids. Pet Explor Dev 39(2):261\u2013267. https:\/\/doi.org\/10.1016\/S1876-3804(12)60041-X","journal-title":"Pet Explor Dev"},{"doi-asserted-by":"publisher","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D,..., Stoyanov V (2019). RoBERTa: a robustly optimized BERT pretraining approach. arXiv Comput Lang. https:\/\/doi.org\/10.48550\/arXiv.1907.11692","key":"10692_CR73","DOI":"10.48550\/arXiv.1907.11692"},{"doi-asserted-by":"publisher","unstructured":"Liu J, Xia CS, Wang Y, Zhang L (2023) Is your code generated by ChatGPT really correct? rigorous evaluation of large language models for code generation. In: Proceedings of the 37th international conference on neural information processing systems, p 943. https:\/\/doi.org\/10.5555\/3666122.3667065 (Article)","key":"10692_CR74","DOI":"10.5555\/3666122.3667065"},{"doi-asserted-by":"publisher","unstructured":"Llugsi R, Yacoubi SE, Fontaine A, Lupera P (2021) Comparison between Adam, AdaMax and Adam W optimizers to implement a weather forecast based on neural networks for the Andean city of Quito. In: 2021 IEEE fifth ecuador technical chapters meeting (ETCM), pp 1\u20136. https:\/\/doi.org\/10.1109\/ETCM53643.2021.9590681","key":"10692_CR75","DOI":"10.1109\/ETCM53643.2021.9590681"},{"doi-asserted-by":"publisher","unstructured":"Luong K, Hadi M, Thung F, Fard F, Lo D (2021) Facos: finding api relevant contents on stack overflow with semantic and syntactic analysis. Preprint at https:\/\/arxiv.org\/abs\/2111.07238. https:\/\/doi.org\/10.48550\/arXiv.2111.07238","key":"10692_CR76","DOI":"10.48550\/arXiv.2111.07238"},{"doi-asserted-by":"publisher","unstructured":"Lutz B (2009) Linguistic challenges in global software development: lessons learned in an international SW development division. In: 2009 fourth IEEE international conference on global software engineering, pp 249-253. https:\/\/doi.org\/10.1109\/ICGSE.2009.33","key":"10692_CR77","DOI":"10.1109\/ICGSE.2009.33"},{"unstructured":"Lynnerup NA, Nolling L, Hasle R, Hallam J (2020) A survey on reproducibility by evaluating deep reinforcement learning algorithms on real-world robots. In: Proceedings of the conference on robot learning, pp 466\u2013489. Retrieved 4 April, 2024, from https:\/\/proceedings.mlr.press\/v100\/lynnerup20a.html","key":"10692_CR78"},{"unstructured":"Mahbub M, Manjur N, Alam M, Vassileva J (2021) Analysis of factors influencing user contribution and predicting involvement of users on stack overflow. Educ Data Min. Retrieved 6 June, 2024, from https:\/\/educationaldatamining.org\/EDM2021\/virtual\/static\/pdf\/EDM21_paper_95.pdf","key":"10692_CR79"},{"key":"10692_CR80","doi-asserted-by":"publisher","first-page":"103767","DOI":"10.1016\/j.csite.2023.103767","volume":"53","author":"MAA Majrashi","year":"2024","unstructured":"Majrashi MAA, Abdullah Alamoudi J, Alrashidi A, Algarni MA, Alshehri S (2024) Nonsteroidal anti-inflammatory drug solubility optimization through green chemistry solvent: artificial intelligence technique. Case Stud Thermal Eng 53:103767. https:\/\/doi.org\/10.1016\/j.csite.2023.103767","journal-title":"Case Stud Thermal Eng"},{"issue":"2","key":"10692_CR81","doi-asserted-by":"publisher","first-page":"49","DOI":"10.25007\/ajnu.v12n2a1532","volume":"12","author":"HS Malallah","year":"2023","unstructured":"Malallah HS, Abdulrazzaq MB (2023) Web-based agricultural management products for marketing system: survey. Acad J Nawroz Univ 12(2):49\u201362. https:\/\/doi.org\/10.25007\/ajnu.v12n2a1532","journal-title":"Acad J Nawroz Univ"},{"doi-asserted-by":"publisher","unstructured":"Mashhadi E, Hemmati H (2021) Applying CodeBERT for automated program repair of java simple bugs. In: 2021 IEEE\/ACM 18th international conference on mining software repositories (MSR), pp 505\u2013509. https:\/\/doi.org\/10.1109\/MSR52588.2021.00063","key":"10692_CR82","DOI":"10.1109\/MSR52588.2021.00063"},{"issue":"1","key":"10692_CR83","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/s13278-018-0512-3","volume":"8","author":"SA Matei","year":"2018","unstructured":"Matei SA, Abu Jabal A, Bertino E (2018) Social-collaborative determinants of content quality in online knowledge production systems: comparing wikipedia and stack overflow. Soc Netw Anal Min 8(1):36. https:\/\/doi.org\/10.1007\/s13278-018-0512-3","journal-title":"Soc Netw Anal Min"},{"key":"10692_CR84","doi-asserted-by":"publisher","first-page":"102516","DOI":"10.1016\/j.scico.2020.102516","volume":"199","author":"S Meldrum","year":"2020","unstructured":"Meldrum S, Licorish S, Owen CA, Savarimuthu BTR (2020) Understanding stack overflow code quality: a recommendation of caution. Sci Comput Program 199:102516. https:\/\/doi.org\/10.1016\/j.scico.2020.102516","journal-title":"Sci Comput Program"},{"doi-asserted-by":"publisher","unstructured":"Meldrum S, Licorish S, Savarimuthu BTR (2017) Crowdsourced knowledge on stack overflow: a systematic mapping study. In: Proceedings of the 21st international conference on evaluation and assessment in software engineering, pp 180\u2013185. https:\/\/doi.org\/10.1145\/3084226.3084267","key":"10692_CR85","DOI":"10.1145\/3084226.3084267"},{"issue":"2","key":"10692_CR86","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s40899-024-01064-9","volume":"10","author":"M Moeini","year":"2024","unstructured":"Moeini M (2024) Hyperparameter tuning of supervised bagging ensemble machine learning model using Bayesian optimization for estimating stormwater quality. Sustain Water Resour Manag 10(2):83. https:\/\/doi.org\/10.1007\/s40899-024-01064-9","journal-title":"Sustain Water Resour Manag"},{"doi-asserted-by":"publisher","unstructured":"Mondal S, Saifullah CMK, Bhattacharjee A, Rahman MM, Roy CK (2021) Early detection and guidelines to improve unanswered questions on stack overflow. In: Proceedings of the 14th innovations in software engineering conference (formerly known as India Software Engineering Conference). 9. https:\/\/doi.org\/10.1145\/3452383.3452392 (Article)","key":"10692_CR87","DOI":"10.1145\/3452383.3452392"},{"doi-asserted-by":"publisher","unstructured":"Morrison P, Murphy-Hill E (2013) Is programming knowledge related to age? an exploration of stack overflow. In: Proceedings of the 10th working conference on mining software repositories, pp 69\u201372. https:\/\/doi.org\/10.5555\/2487085.2487102","key":"10692_CR88","DOI":"10.5555\/2487085.2487102"},{"issue":"13","key":"10692_CR89","doi-asserted-by":"publisher","first-page":"10468","DOI":"10.1007\/s12144-022-03307-4","volume":"42","author":"S Mustafa","year":"2023","unstructured":"Mustafa S, Zhang W, Naveed MM (2023) What motivates online community contributors to contribute consistently? A case study on Stackoverflow netizens. Curr Psychol 42(13):10468\u201310481. https:\/\/doi.org\/10.1007\/s12144-022-03307-4","journal-title":"Curr Psychol"},{"unstructured":"Naing L, Winn T, Rusli B (2006) Practical issues in calculating the sample size for prevalence studies. Arch Orofac Sci 1:9\u201314. Retrieved 3 March, 2023, from https:\/\/aos.usm.my\/docs\/Vol_1\/09_14_ayub.pdf","key":"10692_CR90"},{"key":"10692_CR91","doi-asserted-by":"publisher","first-page":"111524","DOI":"10.1016\/j.jss.2022.111524","volume":"195","author":"IG Ndukwe","year":"2023","unstructured":"Ndukwe IG, Licorish S, Tahir A, MacDonell SG (2023) How have views on software quality differed over time? Research and practice viewpoints. J Syst Softw 195:111524. https:\/\/doi.org\/10.1016\/j.jss.2022.111524","journal-title":"J Syst Softw"},{"doi-asserted-by":"publisher","unstructured":"Nguyen TG, Le-Cong T, Kang HJ, Widyasari R, Yang C, Zhao Z,..., Lo D (2023) Multi-granularity detector for vulnerability fixes. IEEE Trans Softw Eng 49(8):4035\u20134057. https:\/\/doi.org\/10.1109\/TSE.2023.3281275","key":"10692_CR92","DOI":"10.1109\/TSE.2023.3281275"},{"doi-asserted-by":"publisher","unstructured":"Nugraha PZES, Sunarya IMG, Maysanjaya IMD (2023) Binary semantic segmentation of dolphin on UAV image using U-Net. In: 2023 international seminar on intelligent technology and its applications (ISITIA), pp 728\u2013733. https:\/\/doi.org\/10.1109\/ISITIA59021.2023.10221152","key":"10692_CR93","DOI":"10.1109\/ISITIA59021.2023.10221152"},{"doi-asserted-by":"publisher","unstructured":"\u00d6hman J, Verlinden S, Ekgren A, Gyllensten AC, Isbister T, Gogoulou E,..., Sahlgren M (2023) The nordic pile: a 1.2TB nordic dataset for language modeling. arXiv Comput Lang. https:\/\/doi.org\/10.48550\/arXiv.2303.17183","key":"10692_CR94","DOI":"10.48550\/arXiv.2303.17183"},{"doi-asserted-by":"publisher","unstructured":"Olatinwo SO, Demmans CE (2024) Predicting tags for learner questions on stack overflow. Int J Artif Intell Educ. https:\/\/doi.org\/10.1007\/s40593-024-00441-x","key":"10692_CR95","DOI":"10.1007\/s40593-024-00441-x"},{"doi-asserted-by":"publisher","unstructured":"Omondiagbe OP, Licorish S, MacDonell SG (2019) Features that predict the acceptability of java and javascript answers on stack overflow. In: Proceedings of the 23rd international conference on evaluation and assessment in software engineering, pp 101\u2013110. https:\/\/doi.org\/10.1145\/3319008.3319024","key":"10692_CR96","DOI":"10.1145\/3319008.3319024"},{"doi-asserted-by":"publisher","unstructured":"Omondiagbe OP, Licorish S, MacDonell SG (2022) Evaluating simple and complex models\u2019 performance when predicting accepted answers on stack overflow. In: 2022 48th euromicro conference on software engineering and advanced applications (SEAA), pp 29\u201338. https:\/\/doi.org\/10.1109\/SEAA56994.2022.00014","key":"10692_CR97","DOI":"10.1109\/SEAA56994.2022.00014"},{"issue":"4","key":"10692_CR98","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1007\/s12108-023-09607-x","volume":"55","author":"T Osborne","year":"2024","unstructured":"Osborne T, Nivala M, Seredko A, Hillman T (2024) Gaming expertise metrics: a sociological examination of online knowledge creation platforms. Am Sociol 55(4):338\u2013360. https:\/\/doi.org\/10.1007\/s12108-023-09607-x","journal-title":"Am Sociol"},{"doi-asserted-by":"publisher","unstructured":"Ozili PK (2023) The acceptable r-square in empirical modelling for social science research. In: Saliya CA (ed) Social research methodology and publishing results: a guide to non-native english speakers. Hershey, PA, USA: IGI Global, pp 134\u2013143. https:\/\/doi.org\/10.4018\/978-1-6684-6859-3.ch009","key":"10692_CR99","DOI":"10.4018\/978-1-6684-6859-3.ch009"},{"doi-asserted-by":"publisher","unstructured":"Pal OK (2021) Skin disease classification: a comparative analysis of K-Nearest Neighbors (KNN) and random forest algorithm. In: 2021 international conference on electronics, communications and information technology (ICECIT), pp 1\u20135. https:\/\/doi.org\/10.1109\/ICECIT54077.2021.9641120","key":"10692_CR100","DOI":"10.1109\/ICECIT54077.2021.9641120"},{"key":"10692_CR101","doi-asserted-by":"publisher","first-page":"102157","DOI":"10.1016\/j.simpat.2020.102157","volume":"105","author":"M Papoutsoglou","year":"2020","unstructured":"Papoutsoglou M, Kapitsaki GM, Angelis L (2020) Modeling the effect of the badges gamification mechanism on personality traits of stack overflow users. Simul Model Pract Theory 105:102157. https:\/\/doi.org\/10.1016\/j.simpat.2020.102157","journal-title":"Simul Model Pract Theory"},{"issue":"3","key":"10692_CR102","doi-asserted-by":"publisher","first-page":"251524592311625","DOI":"10.1177\/25152459231162559","volume":"6","author":"F Pargent","year":"2023","unstructured":"Pargent F, Schoedel R, Stachl C (2023) Best practices in supervised machine learning: a tutorial for psychologists. Adv Methods Pract Psychol Sci 6(3):25152459231162560. https:\/\/doi.org\/10.1177\/25152459231162559","journal-title":"Adv Methods Pract Psychol Sci"},{"doi-asserted-by":"publisher","unstructured":"Patle A, Chouhan DS (2013) SVM kernel functions for classification. In: 2013 international conference on advances in technology and engineering (ICATE), pp 1\u20139. https:\/\/doi.org\/10.1109\/ICAdTE.2013.6524743","key":"10692_CR103","DOI":"10.1109\/ICAdTE.2013.6524743"},{"issue":"12","key":"10692_CR104","doi-asserted-by":"publisher","first-page":"e0243030","DOI":"10.1371\/journal.pone.0243030","volume":"15","author":"TA Pham","year":"2020","unstructured":"Pham TA, Tran VQ, Vu H-LT, Ly H-B (2020) Design deep neural network architecture using a genetic algorithm for estimation of pile bearing capacity. PLoS One 15(12):e0243030. https:\/\/doi.org\/10.1371\/journal.pone.0243030","journal-title":"PLoS One"},{"doi-asserted-by":"publisher","unstructured":"Ponzanelli L, Mocci A, Bacchelli A, Lanza M, Fullerton D (2014) Improving low quality stack overflow post detection. In: 2014 IEEE international conference on software maintenance and evolution, pp 541\u2013544. https:\/\/doi.org\/10.1109\/ICSME.2014.90","key":"10692_CR105","DOI":"10.1109\/ICSME.2014.90"},{"doi-asserted-by":"publisher","unstructured":"Pudipeddi JS, Akoglu L, Tong H (2014) User churn in focused question answering sites: characterizations and prediction. In: Proceedings of the 23rd international conference on world wide web, pp 469\u2013474. https:\/\/doi.org\/10.1145\/2567948.2576965","key":"10692_CR106","DOI":"10.1145\/2567948.2576965"},{"doi-asserted-by":"publisher","unstructured":"Radabaugh HL, Bonnell J, Dietrich WD, Bramlett HM, Schwartz O, Sarkar D (2020) Development and evaluation of machine learning models for recovery prediction after treatment for traumatic brain injury. In: 2020 42nd annual international conference of the IEEE engineering in medicine & biology society (EMBC), pp 2416\u20132420. https:\/\/doi.org\/10.1109\/EMBC44109.2020.9175658","key":"10692_CR107","DOI":"10.1109\/EMBC44109.2020.9175658"},{"doi-asserted-by":"publisher","unstructured":"Rafnsson W, Giustolisi R, Kragerup M, H\u00f8yrup M (2020) Fixing vulnerabilities automatically with linters. In: Kuty\u0142owski M et al (eds) Network and system security. Network and system security, pp 224\u2013244. https:\/\/doi.org\/10.1007\/978-3-030-65745-1_13","key":"10692_CR108","DOI":"10.1007\/978-3-030-65745-1_13"},{"doi-asserted-by":"publisher","unstructured":"Raiaan MAK, Mukta MSH, Fatema K, Fahad NM, Sakib S, Mim MMJ,..., Azam S (2024) A review on large language models: architectures, applications, taxonomies, open issues and challenges. IEEE Access 12:26839\u201326874. https:\/\/doi.org\/10.1109\/ACCESS.2024.3365742","key":"10692_CR109","DOI":"10.1109\/ACCESS.2024.3365742"},{"issue":"3","key":"10692_CR110","doi-asserted-by":"publisher","first-page":"1186","DOI":"10.3390\/app12031186","volume":"12","author":"ID Raji","year":"2022","unstructured":"Raji ID, Bello-Salau H, Umoh IJ, Onumanyi AJ, Adegboye MA, Salawudeen AT (2022) Simple deterministic selection-based genetic algorithm for hyperparameter tuning of machine learning models. Appl Sci 12(3):1186. https:\/\/doi.org\/10.3390\/app12031186","journal-title":"Appl Sci"},{"doi-asserted-by":"publisher","unstructured":"Raju VNG, Lakshmi KP, Jain VM, Kalidindi A, Padma V (2020) Study the influence of normalization\/transformation process on the accuracy of supervised classification. In: 2020 third international conference on smart systems and inventive technology (ICSSIT), pp 729\u2013735. https:\/\/doi.org\/10.1109\/ICSSIT48917.2020.9214160","key":"10692_CR111","DOI":"10.1109\/ICSSIT48917.2020.9214160"},{"doi-asserted-by":"publisher","unstructured":"Raschka S (2018) Model evaluation, model selection, and algorithm selection in machine learning. Preprint at https:\/\/arxiv.org\/abs\/1811.12808. https:\/\/doi.org\/10.48550\/arXiv.1811.12808","key":"10692_CR112","DOI":"10.48550\/arXiv.1811.12808"},{"issue":"3","key":"10692_CR113","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1016\/j.ecolmodel.2005.10.003","volume":"193","author":"B Reineking","year":"2006","unstructured":"Reineking B, Schr\u00f6der B (2006) Constrain to perform: regularization of habitat models. Ecol Model 193(3):675\u2013690. https:\/\/doi.org\/10.1016\/j.ecolmodel.2005.10.003","journal-title":"Ecol Model"},{"key":"10692_CR114","doi-asserted-by":"publisher","first-page":"102722","DOI":"10.1016\/j.cpa.2024.102722","volume":"99","author":"J Roberts","year":"2024","unstructured":"Roberts J, Baker M, Andrew J (2024) Artificial intelligence and qualitative research: the promise and perils of large language model (LLM) \u2018assistance.\u2019 Crit Perspect Account 99:102722. https:\/\/doi.org\/10.1016\/j.cpa.2024.102722","journal-title":"Crit Perspect Account"},{"key":"10692_CR115","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.eswa.2016.04.032","volume":"59","author":"CA Ronao","year":"2016","unstructured":"Ronao CA, Cho S-B (2016) Human activity recognition with smartphone sensors using deep learning neural networks. Expert Syst Appl 59:235\u2013244. https:\/\/doi.org\/10.1016\/j.eswa.2016.04.032","journal-title":"Expert Syst Appl"},{"doi-asserted-by":"publisher","unstructured":"Rong G, Li K, Su Y, Tong Z, Liu X, Zhang J,..., Li T (2021) Comparison of tree-structured parzen estimator optimization in three typical neural network models for landslide susceptibility assessment. Remote Sens 13(22):4694. https:\/\/doi.org\/10.3390\/rs13224694","key":"10692_CR116","DOI":"10.3390\/rs13224694"},{"unstructured":"Sabzevari M, Su\u00e1rez A (2014) Improving the robustness of bagging with reduced sampling size. Eur (ESANN) Comput Intell Mach Learn. Retrieved 5 June, 2024, from http:\/\/www.i6doc.com\/fr\/livre\/?GCOI=28001100432440","key":"10692_CR117"},{"key":"10692_CR118","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.procs.2015.12.105","volume":"72","author":"H Sain","year":"2015","unstructured":"Sain H, Purnami SW (2015) Combine sampling support vector machine for imbalanced data classification. Procedia Comput Sci 72:59\u201366. https:\/\/doi.org\/10.1016\/j.procs.2015.12.105","journal-title":"Procedia Comput Sci"},{"issue":"1","key":"10692_CR119","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13673-019-0205-6","volume":"10","author":"J Salminen","year":"2020","unstructured":"Salminen J, Hopf M, Chowdhury SA, Jung S-G, Almerekhi H, Jansen BJ (2020) Developing an online hate classifier for multiple social media platforms. HCIS 10(1):1. https:\/\/doi.org\/10.1186\/s13673-019-0205-6","journal-title":"HCIS"},{"issue":"12","key":"10692_CR120","doi-asserted-by":"publisher","first-page":"1973","DOI":"10.3390\/rs12121973","volume":"12","author":"A Samat","year":"2020","unstructured":"Samat A, Li E, Wang W, Liu S, Lin C, Abuduwaili J (2020) Meta-XGBoost for hyperspectral image classification using extended MSER-guided morphological profiles. Remote Sens 12(12):1973. https:\/\/doi.org\/10.3390\/rs12121973","journal-title":"Remote Sens"},{"doi-asserted-by":"publisher","unstructured":"Santos J, Costa DAD, Kulesza U (2022) Investigating the impact of continuous integration practices on the productivity and quality of open-source projects. In: Proceedings of the 16th ACM \/ IEEE international symposium on empirical software engineering and measurement, pp 137\u2013147. https:\/\/doi.org\/10.1145\/3544902.3546244","key":"10692_CR121","DOI":"10.1145\/3544902.3546244"},{"issue":"5","key":"10692_CR122","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1162\/089976600300015565","volume":"12","author":"B Sch\u00f6lkopf","year":"2000","unstructured":"Sch\u00f6lkopf B, Smola AJ, Williamson RC, Bartlett PL (2000) New support vector algorithms. Neural Comput 12(5):1207\u20131245. https:\/\/doi.org\/10.1162\/089976600300015565","journal-title":"Neural Comput"},{"doi-asserted-by":"publisher","unstructured":"Schroeder DJ (2009) Spaces and places guide my behavior. PsycCRITIQUES 54(39). https:\/\/doi.org\/10.1037\/a0016823","key":"10692_CR123","DOI":"10.1037\/a0016823"},{"doi-asserted-by":"publisher","unstructured":"Shah C, Pomerantz J (2010) Evaluating and predicting answer quality in community QA. In: Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval. https:\/\/doi.org\/10.1145\/1835449.1835518","key":"10692_CR124","DOI":"10.1145\/1835449.1835518"},{"issue":"4","key":"10692_CR125","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1016\/0305-0483(96)00010-2","volume":"24","author":"M Shanker","year":"1996","unstructured":"Shanker M, Hu MY, Hung MS (1996) Effect of data standardization on neural network training. Omega 24(4):385\u2013397. https:\/\/doi.org\/10.1016\/0305-0483(96)00010-2","journal-title":"Omega"},{"issue":"2","key":"10692_CR126","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s42979-022-01537-8","volume":"4","author":"DL Shanthi","year":"2022","unstructured":"Shanthi DL, Chethan N (2022) Genetic algorithm based hyper-parameter tuning to improve the performance of machine learning models. SN Comput Sci 4(2):119. https:\/\/doi.org\/10.1007\/s42979-022-01537-8","journal-title":"SN Comput Sci"},{"doi-asserted-by":"publisher","unstructured":"Sharma R, Chen F, Fard F, Lo D (2022) An exploratory study on code attention in BERT. arXiv Softw Eng. https:\/\/doi.org\/10.48550\/arXiv.2204.10200","key":"10692_CR127","DOI":"10.48550\/arXiv.2204.10200"},{"doi-asserted-by":"publisher","unstructured":"Shashank, S., & Mahapatra, M. P. (2018). Boosting rock facies prediction: weighted ensemble of machine learning classifiers. Abu Dhabi Int Pet Exhibition Conf. https:\/\/doi.org\/10.2118\/192930-ms","key":"10692_CR128","DOI":"10.2118\/192930-ms"},{"doi-asserted-by":"publisher","unstructured":"Shen S-S, Lee H-Y (2016) Neural attention models for sequence classification: analysis and application to key term extraction and dialogue act detection. arXiv Comput Lang abs\/1604.00077. https:\/\/doi.org\/10.48550\/arXiv.1604.00077","key":"10692_CR129","DOI":"10.48550\/arXiv.1604.00077"},{"doi-asserted-by":"publisher","unstructured":"Shi, B. (2021). On the hyperparameters in stochastic gradient descent with momentum. arXiv Comput Lang. https:\/\/doi.org\/10.48550\/arXiv.2108.03947","key":"10692_CR130","DOI":"10.48550\/arXiv.2108.03947"},{"doi-asserted-by":"crossref","unstructured":"Shrestha N (2020) Detecting multicollinearity in regression analysis. Am J Appl Math Stat 8(2):39\u201342. Retrieved 28 February, 2024, from http:\/\/article.sciappliedmathematics.com\/pdf\/AJAMS-8-2-1.pdf","key":"10692_CR131","DOI":"10.12691\/ajams-8-2-1"},{"doi-asserted-by":"publisher","unstructured":"Singh P, Raman B (2024) Transformer architectures. In: Deep learning through the prism of tensors. Singapore: Springer Nature Singapore, pp 303\u2013367. https:\/\/doi.org\/10.1007\/978-981-97-8019-8_6","key":"10692_CR132","DOI":"10.1007\/978-981-97-8019-8_6"},{"doi-asserted-by":"publisher","unstructured":"Singh B, Vijayvargiya A, Kumar R (2021) Mapping model for genesis of joint trajectory using human gait dataset. In: 2021 smart technologies, communication and robotics (STCR), pp 1\u20135. https:\/\/doi.org\/10.1109\/STCR51658.2021.9589007","key":"10692_CR133","DOI":"10.1109\/STCR51658.2021.9589007"},{"doi-asserted-by":"publisher","unstructured":"Slag R, Waard MD, Bacchelli A (2015) One-day flies on stackoverflow - why the vast majority of stackoverflow users only posts once. In: 2015 IEEE\/ACM 12th working conference on mining software repositories, pp 458\u2013461. https:\/\/doi.org\/10.1109\/MSR.2015.63","key":"10692_CR134","DOI":"10.1109\/MSR.2015.63"},{"issue":"4","key":"10692_CR135","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1109\/MS.2016.34","volume":"33","author":"I Srba","year":"2016","unstructured":"Srba I, Bielikova M (2016) Why is stack overflow failing? preserving sustainability in community question answering. IEEE Softw 33(4):80\u201389. https:\/\/doi.org\/10.1109\/MS.2016.34","journal-title":"IEEE Softw"},{"issue":"3","key":"10692_CR136","doi-asserted-by":"publisher","first-page":"616","DOI":"10.3390\/biomedinformatics3030042","volume":"3","author":"E Strelcenia","year":"2023","unstructured":"Strelcenia E, Prakoonwit S (2023) Effective feature engineering and classification of breast cancer diagnosis: a comparative study. BioMedInformatics 3(3):616\u2013631. https:\/\/doi.org\/10.3390\/biomedinformatics3030042","journal-title":"BioMedInformatics"},{"doi-asserted-by":"publisher","unstructured":"Sun C, Qiu X, Xu Y, Huang X (2019) How to fine-tune bert for text classification?. In: Sun M et al (eds) Chinese computational linguistics. chinese computational linguistics, pp 194\u2013206. https:\/\/doi.org\/10.1007\/978-3-030-32381-3_16","key":"10692_CR137","DOI":"10.1007\/978-3-030-32381-3_16"},{"doi-asserted-by":"publisher","unstructured":"Sundhari SS (2011) A knowledge discovery using decision tree by Gini coefficient. In: 2011 international conference on business, engineering and industrial applications, pp 232\u2013235. https:\/\/doi.org\/10.1109\/ICBEIA.2011.5994250","key":"10692_CR138","DOI":"10.1109\/ICBEIA.2011.5994250"},{"doi-asserted-by":"publisher","unstructured":"Tabassum J, Maddela M, Xu W, Ritter A (2020) Code and named entity recognition in stackoverflow. In: Jurafsky D et al (eds) Proceedings of the 58th annual meeting of the association for computational linguistics, pp 4913\u20134926. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.443","key":"10692_CR139","DOI":"10.18653\/v1\/2020.acl-main.443"},{"issue":"3","key":"10692_CR140","doi-asserted-by":"publisher","first-page":"70","DOI":"10.3390\/computation8030070","volume":"8","author":"Y Tang","year":"2020","unstructured":"Tang Y, Chau K-Y, Li W, Wan T (2020) Forecasting economic recession through share price in the logistics industry with artificial intelligence (AI). Computation 8(3):70. https:\/\/doi.org\/10.3390\/computation8030070","journal-title":"Computation"},{"key":"10692_CR141","doi-asserted-by":"publisher","first-page":"102119","DOI":"10.1016\/j.mex.2023.102119","volume":"10","author":"D Tarwidi","year":"2023","unstructured":"Tarwidi D, Pudjaprasetya SR, Adytia D, Apri M (2023) An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beach. Methods X 10:102119. https:\/\/doi.org\/10.1016\/j.mex.2023.102119","journal-title":"Methods X"},{"issue":"1","key":"10692_CR142","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1609\/icwsm.v7i1.14457","volume":"7","author":"Q Tian","year":"2021","unstructured":"Tian Q, Zhang P, Li B (2021) Towards predicting the best answers in community-based question-answering services. Proc Int AAAI Conf Web Soc Media 7(1):725\u2013728. https:\/\/doi.org\/10.1609\/icwsm.v7i1.14457","journal-title":"Proc Int AAAI Conf Web Soc Media"},{"issue":"9","key":"10692_CR143","doi-asserted-by":"publisher","first-page":"5167","DOI":"10.1109\/TIT.2016.2590421","volume":"62","author":"M Unser","year":"2016","unstructured":"Unser M, Fageot J, Gupta H (2016) Representer theorems for sparsity-promoting L1 regularization. IEEE Trans Inf Theory 62(9):5167\u20135180. https:\/\/doi.org\/10.1109\/TIT.2016.2590421","journal-title":"IEEE Trans Inf Theory"},{"doi-asserted-by":"publisher","unstructured":"Uzair M, Jamil N (2020) Effects of hidden layers on the efficiency of neural networks. In: 2020 IEEE 23rd international multitopic conference (INMIC), pp 1\u20136. https:\/\/doi.org\/10.1109\/INMIC50486.2020.9318195","key":"10692_CR144","DOI":"10.1109\/INMIC50486.2020.9318195"},{"issue":"3","key":"10692_CR145","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1080\/13588265.2022.2075101","volume":"28","author":"D Vadhwani","year":"2023","unstructured":"Vadhwani D, Thakor D (2023) Prediction of extent of damage in vehicle during crash using improved XGBoost model. Int J Crashworthiness 28(3):299\u2013305. https:\/\/doi.org\/10.1080\/13588265.2022.2075101","journal-title":"Int J Crashworthiness"},{"doi-asserted-by":"publisher","unstructured":"Van den Broeck J, Fadnes LT (2013) Data cleaning. In: Van den Broeck J, Brestoff JR (eds) Epidemiology: principles and practical guidelines. Dordrecht: Springer Netherlands, pp 389\u2013399. https:\/\/doi.org\/10.1007\/978-94-007-5989-3_20","key":"10692_CR146","DOI":"10.1007\/978-94-007-5989-3_20"},{"doi-asserted-by":"publisher","unstructured":"van Laarhoven T (2017) L2 regularization versus batch and weight normalization. CoRR abs\/1706.05350. https:\/\/doi.org\/10.48550\/arXiv.1706.05350","key":"10692_CR147","DOI":"10.48550\/arXiv.1706.05350"},{"issue":"3","key":"10692_CR148","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1213\/ANE.0000000000001107","volume":"122","author":"T Vasilopoulos","year":"2016","unstructured":"Vasilopoulos T, Morey TE, Dhatariya K, Rice MJ (2016) Limitations of significance testing in clinical research: a review of multiple comparison corrections and effect size calculations with correlated measures. Anesth Analg 122(3):825\u2013830. https:\/\/doi.org\/10.1213\/ANE.0000000000001107","journal-title":"Anesth Analg"},{"unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN,..., Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30. Retrieved 18 April, 2025, from https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html","key":"10692_CR149"},{"issue":"3","key":"10692_CR150","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1111\/1467-8551.12431","volume":"32","author":"AR Villadsen","year":"2021","unstructured":"Villadsen AR, Wulff JN (2021) Statistical myths about log-transformed dependent variables and how to better estimate exponential models. Br J Manag 32(3):779\u2013796. https:\/\/doi.org\/10.1111\/1467-8551.12431","journal-title":"Br J Manag"},{"issue":"1","key":"10692_CR151","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.chemolab.2010.10.004","volume":"105","author":"K Wang","year":"2011","unstructured":"Wang K, Chen T, Lau R (2011) Bagging for robust non-linear multivariate calibration of spectroscopy. Chemom Intell Lab Syst 105(1):1\u20136. https:\/\/doi.org\/10.1016\/j.chemolab.2010.10.004","journal-title":"Chemom Intell Lab Syst"},{"issue":"4","key":"10692_CR152","doi-asserted-by":"publisher","first-page":"1136","DOI":"10.1109\/TCSI.2015.2395591","volume":"62","author":"Z Wang","year":"2015","unstructured":"Wang Z, Schapire RE, Verma N (2015) Error adaptive classifier boosting (EACB): leveraging data-driven training towards hardware resilience for signal inference. IEEE Trans Circuits Syst I Regul Pap 62(4):1136\u20131145. https:\/\/doi.org\/10.1109\/TCSI.2015.2395591","journal-title":"IEEE Trans Circuits Syst I Regul Pap"},{"issue":"9","key":"10692_CR153","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1109\/TSE.2018.2874470","volume":"46","author":"S Wang","year":"2020","unstructured":"Wang S, Chen TH, Hassan AE (2020b) How do users revise answers on technical Q&A websites? A case study on stack overflow. IEEE Trans Software Eng 46(9):1024\u20131038. https:\/\/doi.org\/10.1109\/TSE.2018.2874470","journal-title":"IEEE Trans Software Eng"},{"key":"10692_CR154","doi-asserted-by":"publisher","first-page":"659","DOI":"10.2147\/ndt.S349956","volume":"18","author":"R Wang","year":"2022","unstructured":"Wang R, Zhang J, Shan B, He M, Xu J (2022) XGBoost machine learning algorithm for prediction of outcome in aneurysmal subarachnoid hemorrhage. Neuropsychiatr Dis Treat 18:659\u2013667. https:\/\/doi.org\/10.2147\/ndt.S349956","journal-title":"Neuropsychiatr Dis Treat"},{"doi-asserted-by":"publisher","unstructured":"Wang Q, Wang H, Gupta C, Rao AR, Khorasgani H (2020a) A non-linear function-on-function model for regression with time series data. In: 2020 IEEE international conference on big data (Big Data), pp 232\u2013239. https:\/\/doi.org\/10.1109\/BigData50022.2020.9378087","key":"10692_CR155","DOI":"10.1109\/BigData50022.2020.9378087"},{"issue":"3","key":"10692_CR156","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1145\/2738037","volume":"24","author":"PA Whigham","year":"2015","unstructured":"Whigham PA, Owen CA, Macdonell SG (2015) A baseline model for software effort estimation. ACM Trans Softw Eng Methodol 24(3):20. https:\/\/doi.org\/10.1145\/2738037. (Article)","journal-title":"ACM Trans Softw Eng Methodol"},{"unstructured":"Wijekoon H, Merunka V (2022) Patterns of user participation and contribution in global crowdsourcing: a data mining study of stack overflow. In: 10th international conference on information and communication technologies in agriculture, food and environment, pp 143\u2013150. Retrieved 17 December, 2024, from https:\/\/ceur-ws.org\/Vol-3293\/paper30.pdf","key":"10692_CR157"},{"unstructured":"Wipf D, Nagarajan S (2007) A new view of automatic relevance determination. Adv Neural Inf Process Syst. Retrieved 25 May, 2024, from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2007\/file\/9c01802ddb981e6bcfbec0f0516b8e35-Paper.pdf","key":"10692_CR158"},{"issue":"1","key":"10692_CR159","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3390\/info14010054","volume":"14","author":"T Wongvorachan","year":"2023","unstructured":"Wongvorachan T, He S, Bulut O (2023) A comparison of undersampling, oversampling, and SMOTE methods for dealing with imbalanced classification in educational data mining. Information 14(1):54. https:\/\/doi.org\/10.3390\/info14010054","journal-title":"Information"},{"issue":"3","key":"10692_CR160","doi-asserted-by":"publisher","first-page":"172","DOI":"10.54097\/vt1qpm59","volume":"8","author":"M Xu","year":"2023","unstructured":"Xu M (2023) Quantile regression model and its application research. Acad J Sci Technol 8(3):172\u2013176. https:\/\/doi.org\/10.54097\/vt1qpm59","journal-title":"Acad J Sci Technol"},{"issue":"11","key":"10692_CR161","doi-asserted-by":"publisher","first-page":"11830","DOI":"10.1109\/TKDE.2022.3230743","volume":"35","author":"D Yang","year":"2023","unstructured":"Yang D, Qu B, Hussein R, Rosso P, Cudr\u00e9-Mauroux P, Liu J (2023) Revisiting embedding based graph analyses: hyperparameters matter! IEEE Trans Knowl Data Eng 35(11):11830\u201311845. https:\/\/doi.org\/10.1109\/TKDE.2022.3230743","journal-title":"IEEE Trans Knowl Data Eng"},{"doi-asserted-by":"publisher","unstructured":"Yang C, Xu B, Khan JY, Uddin G, Han D, Yang Z, Lo D (2022) Aspect-based API review classification: how far can pre-trained transformer model go?. In: 2022 IEEE international conference on software analysis, evolution and reengineering (SANER), pp 385\u2013395. https:\/\/doi.org\/10.1109\/SANER53432.2022.00054","key":"10692_CR162","DOI":"10.1109\/SANER53432.2022.00054"},{"doi-asserted-by":"publisher","unstructured":"Yazdaninia M, Lo D, Sami A (2021) Characterization and prediction of questions without accepted answers on stack overflow. In: 2021 IEEE\/ACM 29th international conference on program comprehension (ICPC), pp 59\u201370. https:\/\/doi.org\/10.1109\/ICPC52881.2021.00015","key":"10692_CR163","DOI":"10.1109\/ICPC52881.2021.00015"},{"issue":"1","key":"10692_CR164","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s10664-016-9430-z","volume":"22","author":"D Ye","year":"2017","unstructured":"Ye D, Xing Z, Kapre N (2017) The structure and dynamics of knowledge network in domain-specific Q&A sites: a case study of stack overflow. Empir Softw Eng 22(1):375\u2013406. https:\/\/doi.org\/10.1007\/s10664-016-9430-z","journal-title":"Empir Softw Eng"},{"doi-asserted-by":"crossref","unstructured":"Yeh A (2022) Teaching english as a foreign language in the Philippines. In: Philippine english. Routledge, pp 353\u2013362","key":"10692_CR165","DOI":"10.4324\/9780429427824-36"},{"doi-asserted-by":"publisher","unstructured":"Zahedi M, Rajapakse RN, Babar MA (2020) Mining questions asked about continuous software engineering: a case study of stack overflow. In: Proceedings of the 24th international conference on evaluation and assessment in software engineering, pp 41\u201350. https:\/\/doi.org\/10.1145\/3383219.3383224","key":"10692_CR166","DOI":"10.1145\/3383219.3383224"},{"doi-asserted-by":"publisher","unstructured":"Zhang L, Zhan C (2017) Machine learning in rock facies classification: an application of XGBoost. In: International geophysical conference, Qingdao, China, 17-20 April 2017, pp 1371-1374. https:\/\/doi.org\/10.1190\/igc2017-351","key":"10692_CR167","DOI":"10.1190\/igc2017-351"},{"doi-asserted-by":"publisher","unstructured":"Zhang F, Yu X, Keung J, Li F, Xie Z, Yang Z,..., Zhang Z (2022) Improving stack overflow question title generation with copying enhanced CodeBERT model and bi-modal information. Inf Softw Technol 148:106922. https:\/\/doi.org\/10.1016\/j.infsof.2022.106922","key":"10692_CR168","DOI":"10.1016\/j.infsof.2022.106922"},{"doi-asserted-by":"publisher","unstructured":"Zhao WX, Zhou K, Li J, Tang T, Wang X, Hou Y,..., Dong Z (2023) A survey of large language models. Preprint at https:\/\/arxiv.org\/abs\/2303.18223. https:\/\/doi.org\/10.48550\/arXiv.2303.18223","key":"10692_CR169","DOI":"10.48550\/arXiv.2303.18223"},{"issue":"7","key":"10692_CR170","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1002\/sim.7204","volume":"36","author":"J Zhou","year":"2017","unstructured":"Zhou J, Zhang J, Lu W (2017) An expectation maximization algorithm for fitting the generalized odds-rate model to interval censored data. Stat Med 36(7):1157\u20131171. https:\/\/doi.org\/10.1002\/sim.7204","journal-title":"Stat Med"},{"issue":"1","key":"10692_CR171","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s10664-019-09744-3","volume":"25","author":"J Zhou","year":"2020","unstructured":"Zhou J, Wang S, Bezemer C-P, Hassan AE (2020) Bounties on technical Q&A sites: a case study of stack overflow bounties. Empir Softw Eng 25(1):139\u2013177. https:\/\/doi.org\/10.1007\/s10664-019-09744-3","journal-title":"Empir Softw Eng"},{"doi-asserted-by":"publisher","unstructured":"Zhou X, Han D, Lo D (2021) Assessing generalizability of CodeBERT. In: 2021 IEEE international conference on software maintenance and evolution (ICSME), pp 425\u2013436. https:\/\/doi.org\/10.1109\/ICSME52107.2021.00044","key":"10692_CR172","DOI":"10.1109\/ICSME52107.2021.00044"},{"key":"10692_CR173","doi-asserted-by":"publisher","first-page":"106667","DOI":"10.1016\/j.infsof.2021.106667","volume":"139","author":"E Zolduoarrati","year":"2021","unstructured":"Zolduoarrati E, Licorish S (2021) On the value of encouraging gender tolerance and inclusiveness in software engineering communities. Inf Softw Technol 139:106667. https:\/\/doi.org\/10.1016\/j.infsof.2021.106667","journal-title":"Inf Softw Technol"},{"issue":"7","key":"10692_CR174","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3672453","volume":"33","author":"E Zolduoarrati","year":"2024","unstructured":"Zolduoarrati E, Licorish S, Stanger N (2024) Harmonising contributions: exploring diversity in software engineering through CQA mining on stack overflow. ACM Trans Softw Eng Methodol 33(7):1\u201354. https:\/\/doi.org\/10.1145\/3672453","journal-title":"ACM Trans Softw Eng Methodol"},{"doi-asserted-by":"publisher","unstructured":"Zolduoarrati E, Licorish S, Stanger N (2025a). Comprehensive predictive analytics for collaborators' answers, code quality, and dropout: stack overflow case study\u2013 replication package [Data set]. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.15330992","key":"10692_CR175","DOI":"10.5281\/zenodo.15330992"},{"doi-asserted-by":"publisher","unstructured":"Zolduoarrati E, Licorish S, Stanger N (2025b) Does location influence code quality? mining stack overflow snippets across the United States\u2013 replication package [Data set]. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.15331009","key":"10692_CR176","DOI":"10.5281\/zenodo.15331009"},{"key":"10692_CR177","doi-asserted-by":"publisher","first-page":"112374","DOI":"10.1016\/j.jss.2025.112374","volume":"223","author":"E Zolduoarrati","year":"2025","unstructured":"Zolduoarrati E, Licorish S, Stanger N (2025c) Stack overflow\u2019s hidden nuances: how does zip code define user contribution? J Syst Softw 223:112374. https:\/\/doi.org\/10.1016\/j.jss.2025.112374","journal-title":"J Syst Softw"},{"issue":"2","key":"10692_CR178","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","volume":"67","author":"H Zou","year":"2005","unstructured":"Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. J R Stat Soc Ser B Stat Methodol 67(2):301\u2013320. https:\/\/doi.org\/10.1111\/j.1467-9868.2005.00503.x","journal-title":"J R Stat Soc Ser B Stat Methodol"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10692-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-025-10692-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10692-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T08:55:40Z","timestamp":1757753740000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-025-10692-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,23]]},"references-count":178,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["10692"],"URL":"https:\/\/doi.org\/10.1007\/s10664-025-10692-4","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"type":"print","value":"1382-3256"},{"type":"electronic","value":"1573-7616"}],"subject":[],"published":{"date-parts":[[2025,7,23]]},"assertion":[{"value":"17 June 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"The researchers declare no competing financial interests or personal relationships that could have influenced the work presented in this manuscript.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Clinical trial number: not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical Trial Number"}}],"article-number":"147"}}