{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T22:48:28Z","timestamp":1762642108143,"version":"3.37.3"},"reference-count":105,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,8,7]],"date-time":"2018-08-07T00:00:00Z","timestamp":1533600000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Scientific Independence of young Researchers","award":["EmoQuest"],"award-info":[{"award-number":["EmoQuest"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1007\/s10664-018-9642-5","type":"journal-article","created":{"date-parts":[[2018,8,6]],"date-time":"2018-08-06T19:58:22Z","timestamp":1533585502000},"page":"854-901","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["An empirical assessment of best-answer prediction models in technical Q&A sites"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2654-1588","authenticated-orcid":false,"given":"Fabio","family":"Calefato","sequence":"first","affiliation":[]},{"given":"Filippo","family":"Lanubile","sequence":"additional","affiliation":[]},{"given":"Nicole","family":"Novielli","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,7]]},"reference":[{"issue":"2","key":"9642_CR1","first-page":"53","volume":"34","author":"R Abdalkareem","year":"2017","unstructured":"Abdalkareem R, Shihab E, Rilling J (2017) What do developers use the crowd for? A Study Using Stack Overflow IEEE Software 34(2):53\u201360","journal-title":"A Study Using Stack Overflow IEEE Software"},{"key":"9642_CR2","doi-asserted-by":"publisher","unstructured":"L.A. Adamic, J. Zhang, E. Bakshy, M.S. Ackerman, Knowledge sharing and yahoo answers, in Proceeding of the 17th international Conf. On world wide web \u2013 WWW \u201808 (ACM, 2008). \n                    https:\/\/doi.org\/10.1145\/1367497.1367587","DOI":"10.1145\/1367497.1367587"},{"issue":"7","key":"9642_CR3","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1016\/s0031-3203(98)00154-x","volume":"32","author":"NM Adams","year":"1999","unstructured":"Adams NM, Hand DJ (1999) Comparing classifiers when the misallocation costs are uncertain. Pattern Recogn 32(7):1139\u20131147. \n                    https:\/\/doi.org\/10.1016\/s0031-3203(98)00154-x","journal-title":"Pattern Recogn"},{"key":"9642_CR4","doi-asserted-by":"publisher","unstructured":"A. Anderson, D. Huttenlocher, J. Kleinberg, J. Leskovec, Discovering value from community activity on focused question answering sites, in Proc. of the 18th ACM SIGKDD Int\u2019l Conf. On knowledge discovery and data mining \u2013 KDD \u201812 (ACM, 2012). \n                    https:\/\/doi.org\/10.1145\/2339530.2339665","DOI":"10.1145\/2339530.2339665"},{"issue":"1","key":"9642_CR5","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.jss.2009.06.055","volume":"83","author":"E Arisholm","year":"2010","unstructured":"Arisholm E, Briand LC, Johannessen EB (2010) A systematic and comprehensive investigation of methods to build and evaluate fault prediction models. J Syst Softw 83(1):2\u201317. \n                    https:\/\/doi.org\/10.1016\/j.jss.2009.06.055","journal-title":"J Syst Softw"},{"key":"9642_CR6","doi-asserted-by":"crossref","unstructured":"M. Asaduzzaman, A.S Mashiyat, C.K. Roy, K.A. Schneider (2013). Answering questions about unanswered questions of Stack Overflow, In Proc. of the 10th IEEE Working Conf. on Mining Software Repositories (MSR 2013), pp. 97\u2013100","DOI":"10.1109\/MSR.2013.6624015"},{"key":"9642_CR7","doi-asserted-by":"publisher","unstructured":"K. Bajaj, K. Pattabiraman, A. Mesbah, Mining questions asked by web developers, in Proc. of the 11th working Conf. On mining software repositories \u2013 MSR 2014 (ACM, 2014). \n                    https:\/\/doi.org\/10.1145\/2597073.2597083","DOI":"10.1145\/2597073.2597083"},{"issue":"3","key":"9642_CR8","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/s10664-012-9231-y","volume":"19","author":"A Barua","year":"2012","unstructured":"Barua A, Thomas SW, Hassan AE (2012) What are developers talking about? An analysis of topics and trends in Stack Overflow Empirical Software Engineering 19(3):619\u2013654. \n                    https:\/\/doi.org\/10.1007\/s10664-012-9231-y","journal-title":"An analysis of topics and trends in Stack Overflow Empirical Software Engineering"},{"issue":"1","key":"9642_CR9","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. The Journal of Machine Learning Research 13(1):281\u2013305","journal-title":"The Journal of Machine Learning Research"},{"key":"9642_CR10","first-page":"993","volume":"3","author":"D Blei","year":"2003","unstructured":"Blei D, Ng A, Jordan M (2003) Latent Dirichlet allocation. The Journal of Machine Learning Research 3:993\u20131022","journal-title":"The Journal of Machine Learning Research"},{"key":"9642_CR11","unstructured":"L.C. Borges, D.F. Ferreira. Power and type I errors rate of Scott-Knott, Tukey and Student-Newman-Keuls tests under normal and no-normal distributions of the residues. Rev. Mat. Estat., Sao Paulo, 211: 67\u201383 (2003)"},{"key":"9642_CR12","doi-asserted-by":"publisher","unstructured":"A. Bosu, C.S. Corley, D. Heaton, D. Chatterji, J.C. Carver, N.A. Kraft, Building reputation in StackOverflow: an empirical investigation, in 2013 10th working Conf. On mining software repositories (MSR) (IEEE, 2013). \n                    https:\/\/doi.org\/10.1109\/msr.2013.6624013","DOI":"10.1109\/msr.2013.6624013"},{"key":"9642_CR13","doi-asserted-by":"publisher","unstructured":"G. Burel, Y. He, H. Alani, Automatic Identification of Best Answers in Online Enquiry Communities, in Lecture Notes in Computer Science (Springer, 2012), pp. 514\u2013529. \n                    https:\/\/doi.org\/10.1007\/978-3-642-30284-841","DOI":"10.1007\/978-3-642-30284-841"},{"key":"9642_CR14","unstructured":"Cai Y, Chakravarthy S (2011) Predicting answer quality in q\/a social networks: using temporal features, technical report, technical report. University of Texas at Arlington"},{"key":"9642_CR15","doi-asserted-by":"publisher","unstructured":"F. Calefato, F. Lanubile, M.C. Marasciulo, N. Novielli, Mining successful answers in stack overflow, in 2015 IEEE\/ACM 12th working Conf. On mining software repositories (IEEE, 2015). \n                    https:\/\/doi.org\/10.1109\/msr.2015.56","DOI":"10.1109\/msr.2015.56"},{"key":"9642_CR16","doi-asserted-by":"publisher","unstructured":"Calefato F, Lanubile F, Novielli N (2016) Moving to stack overflow: best-answer prediction in legacy developer forums. In: Proc. 10th Int\u2019l Symposium on Empirical Softw. Eng. And Measurement (ESEM\u201916), Ciudad Real, 8\u20139 Sept. 2016. \n                    https:\/\/doi.org\/10.1145\/2961111.2962585","DOI":"10.1145\/2961111.2962585"},{"key":"9642_CR17","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.infsof.2017.10.009","volume":"94","author":"F Calefato","year":"2018","unstructured":"Calefato F, Lanubile F, Novielli N (2018) How to ask for technical help? Evidence-based guidelines for writing questions on stack overflow. Inf Softw Technol 94:186\u2013207. \n                    https:\/\/doi.org\/10.1016\/j.infsof.2017.10.009","journal-title":"Inf Softw Technol"},{"issue":"4","key":"9642_CR18","doi-asserted-by":"publisher","first-page":"7346","DOI":"10.1016\/j.eswa.2008.10.027","volume":"36","author":"C Catal","year":"2009","unstructured":"Catal C, Diri B (2009) A systematic review of software fault prediction studies. Expert Syst Appl 36(4):7346\u20137354. \n                    https:\/\/doi.org\/10.1016\/j.eswa.2008.10.027","journal-title":"Expert Syst Appl"},{"key":"9642_CR19","volume-title":"Statistical power analysis for the behavioral sciences","author":"J Cohen","year":"1988","unstructured":"Cohen J (1988) Statistical power analysis for the behavioral sciences, 2nd edn. Erlbaum, Hillsdale, NJ","edition":"2"},{"key":"9642_CR20","unstructured":"WJ Conover (1999) Practical nonparametric statistics (3rd ed). Wiley"},{"issue":"4\u20135","key":"9642_CR21","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s10664-011-9173-9","volume":"17","author":"M D\u2019Ambros","year":"2012","unstructured":"D\u2019Ambros M, Lanza M, Robbes R (2012) Evaluating defect prediction approaches: a benchmark and an extensive comparison. Empir Softw Eng 17(4\u20135):531\u2013577. \n                    https:\/\/doi.org\/10.1007\/s10664-011-9173-9","journal-title":"Empir Softw Eng"},{"key":"9642_CR22","doi-asserted-by":"publisher","unstructured":"J. Davis, M. Goadrich, The relationship between precision-recall and ROC curves, in proceedings of the 23rd international conference on machine learning \u2013 ICML \u201806 (ACM 2006). \n                    https:\/\/doi.org\/10.1145\/1143844.1143874","DOI":"10.1145\/1143844.1143874"},{"key":"9642_CR23","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837\u2013845","journal-title":"Biometrics"},{"key":"9642_CR24","first-page":"1","volume":"7","author":"J Demsar","year":"2006","unstructured":"Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. The Journal of Machine Learning Research 7:1\u201330","journal-title":"The Journal of Machine Learning Research"},{"key":"9642_CR25","doi-asserted-by":"publisher","unstructured":"G. Denaro, M. Pezz\u00e8, An empirical evaluation of fault-proneness models, in Software Engineering, 2002. ICSE 2002. Proceedings of the 24rd international conference on, 2002, pp. 241\u2013251. \n                    https:\/\/doi.org\/10.1145\/581368.581371","DOI":"10.1145\/581368.581371"},{"issue":"1","key":"9642_CR26","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s10994-006-8199-5","volume":"65","author":"C Drummond","year":"2006","unstructured":"Drummond C, Holte RC (2006) Cost curves: an improved method for visualizing classifier performance. Mach Learn 65(1):95\u2013130. \n                    https:\/\/doi.org\/10.1007\/s10994-006-8199-5","journal-title":"Mach Learn"},{"key":"9642_CR27","doi-asserted-by":"crossref","unstructured":"M. Duijn, A. Ku\u010dera, and A. Bacchelli (2015) Quality questions need quality code: classifying code fragments on stack overflow. In Proceedings of the 12th Working Conference on Mining Software Repositories (MSR '15), pp 410\u2013413","DOI":"10.1109\/MSR.2015.51"},{"key":"9642_CR28","unstructured":"C. Elkan. The foundations of cost-sensitive learning. In Proceedings of the 17th international joint conference on Artificial intelligence - IJCAI'01 (Morgan Kaufmann, 2001), Vol. 2, pp. 973\u2212978 (2001)"},{"issue":"8","key":"9642_CR29","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T (2006) An introduction to roc analysis. Pattern Recogn Lett 27(8):861\u2013874","journal-title":"Pattern Recogn Lett"},{"issue":"5","key":"9642_CR30","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1109\/32.815326","volume":"25","author":"NE Fenton","year":"1999","unstructured":"Fenton NE, Neil M (1999) A critique of software defect prediction models. IEEE Trans Softw Eng 25(5):675\u2013689. \n                    https:\/\/doi.org\/10.1109\/32.815326","journal-title":"IEEE Trans Softw Eng"},{"key":"9642_CR31","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":"9642_CR32","doi-asserted-by":"crossref","unstructured":"B. Ghotra, S. McIntosh, A.E. Hassan, Revisiting the Impact of Classification Techniques on the Performance of Defect Prediction Models, in Proc. of the International Conference on Software Engineering (ICSE), 2015, pp. 789\u2013800","DOI":"10.1109\/ICSE.2015.91"},{"key":"9642_CR33","doi-asserted-by":"publisher","unstructured":"G. Gkotsis, K. Stepanyan, C. Pedrinaci, J. Domingue, M. Liakata, It\u2019s all in the content, in Proc. of the 2014 ACM Conf. On web science \u2013 WebSci \u201814 (ACM, 2014). \n                    https:\/\/doi.org\/10.1145\/2615569.2615681","DOI":"10.1145\/2615569.2615681"},{"issue":"1","key":"9642_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/106.00000001","volume":"1","author":"G Gkotsis","year":"2015","unstructured":"Gkotsis G, Liakata M, Pedrinaci C, Stepanyan K, Domingue J (2015) ACQUA: automated community-based question answering through the discretisation of shallow linguistic features. Journal of Web Science 1(1):1\u201315. \n                    https:\/\/doi.org\/10.1561\/106.00000001","journal-title":"Journal of Web Science"},{"key":"9642_CR35","volume-title":"Correlation-based feature selection for machine learning","author":"MA Hall","year":"1999","unstructured":"Hall MA (1999) Correlation-based feature selection for machine learning. University of Waikato, PhD Dissertation"},{"issue":"6","key":"9642_CR36","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/TSE.2011.103","volume":"38","author":"T Hall","year":"2012","unstructured":"Hall T, Beecham S, Bowes D, Gray D, Counsell S (2012) A systematic literature review on fault prediction performance in software engineering. IEEE Trans Softw Eng 38(6):1276\u20131304. \n                    https:\/\/doi.org\/10.1109\/TSE.2011.103","journal-title":"IEEE Trans Softw Eng"},{"key":"9642_CR37","doi-asserted-by":"publisher","unstructured":"K. Hart, A. Sarma, Perceptions of answer quality in an online technical question and answer forum, in Proc. of 7th Int\u2019l workshop on coop. And human aspects of Softw. Eng. \u2013 CHASE\u201914 (ACM, 2014). \n                    https:\/\/doi.org\/10.1145\/2593702.2593703","DOI":"10.1145\/2593702.2593703"},{"key":"9642_CR38","unstructured":"T.J. Hastie, R.J. Tibshirani, J.H. Friedman, The elements of statistical learning: data mining, inference, and prediction. Springer series in statistics (Springer, New York, 2009). Autres impressions: 2011 (corr.), 2013 (7e corr.). ISBN 978-0-387-84857-0"},{"issue":"9","key":"9642_CR39","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans on Knowl and Data Eng 21(9):1263\u20131284. \n                    https:\/\/doi.org\/10.1109\/TKDE.2008.239","journal-title":"IEEE Trans on Knowl and Data Eng"},{"key":"9642_CR40","unstructured":"Hosseini S, Turhan B, Gunarathna D (2017) A systematic literature review and Meta-analysis on cross project defect prediction. IEEE Trans Softw Eng"},{"issue":"3","key":"9642_CR41","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1109\/TKDE.2005.50","volume":"17","author":"J Huang","year":"2005","unstructured":"Huang J, Ling CX (2005) Using AUC and accuracy in evaluating learning algorithms. IEEE Trans on Knowl and Data Eng 17(3):299\u2013310. \n                    https:\/\/doi.org\/10.1109\/TKDE.2005.50","journal-title":"IEEE Trans on Knowl and Data Eng"},{"key":"9642_CR42","volume-title":"Forecasting: principles and practice","author":"RJ Hyndman","year":"2017","unstructured":"Hyndman RJ, Athanasopoulos G (2017) Forecasting: principles and practice, 2nd edn \n                    http:\/\/otexts.org\/fpp2","edition":"2"},{"issue":"5","key":"9642_CR43","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3233\/IDA-2002-6504","volume":"6","author":"N Japkowicz","year":"2002","unstructured":"Japkowicz N, Stephen S (2002) The class imbalance problem: a systematic study. Intelligent data analysis 6(5):429\u2013449","journal-title":"Intelligent data analysis"},{"issue":"5","key":"9642_CR44","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/s10664-008-9079-3","volume":"13","author":"Y Jiang","year":"2008","unstructured":"Jiang Y, Cukic B, Ma Y (2008a) Techniques for evaluating fault prediction models. Empir Softw Eng 13(5):561\u2013595. \n                    https:\/\/doi.org\/10.1007\/s10664-008-9079-3","journal-title":"Empir Softw Eng"},{"key":"9642_CR45","doi-asserted-by":"crossref","unstructured":"Y. Jiang, B. Cukic, T. Menzies, Can data transformation help in the detection of fault-prone modules?, in Proceedings of the 2008 workshop on Defects in large software systems, ACM, 2008b, pp. 16\u201320","DOI":"10.1145\/1390817.1390822"},{"issue":"7","key":"9642_CR46","first-page":"13","volume":"1","author":"AG Karegowda","year":"2010","unstructured":"Karegowda AG, Jayaram MA, Manjunath AS (2010) Feature subset selection problem using wrapper approach in supervised learning. Int J Comput Appl 1(7):13\u201317","journal-title":"Int J Comput Appl"},{"key":"9642_CR47","doi-asserted-by":"crossref","unstructured":"J. Kincaid, R.J. Fishburne, R. Rogers, B. Chissom, Derivation of new readability formulas (Automated Readability Index, Fog Count and Flesch Reading Ease Formula) for Navy enlisted personnel. Research Branch Report 8(75) (1975)","DOI":"10.21236\/ADA006655"},{"issue":"5","key":"9642_CR48","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1109\/TSE.2007.1001","volume":"33","author":"BA Kitchenham","year":"2007","unstructured":"Kitchenham BA, Mendes E, Travassos GH (2007) Cross versus within-company cost estimation studies: a systematic review. IEEE Trans Softw Eng 33(5):316\u2013329. \n                    https:\/\/doi.org\/10.1109\/TSE.2007.1001","journal-title":"IEEE Trans Softw Eng"},{"issue":"2","key":"9642_CR49","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1109\/TSE.2011.27","volume":"38","author":"E Kocaguneli","year":"2012","unstructured":"Kocaguneli E, Menzies T, Bener AB, Keung JW (2012) Exploiting the essential assumptions of analogy-based effort estimation. Software Engineering, IEEE Transactions on 38(2):425\u2013438","journal-title":"Software Engineering, IEEE Transactions on"},{"key":"9642_CR50","doi-asserted-by":"publisher","unstructured":"M. Kuhn, Building predictive models in r using the caret package. Journal of Statistical Software 28(1), 1\u201326 (2008). \n                    https:\/\/doi.org\/10.18637\/jss.v028.i05","DOI":"10.18637\/jss.v028.i05"},{"issue":"11","key":"9642_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v036.i11","volume":"36","author":"MB Kursa","year":"2010","unstructured":"Kursa MB, Rudnicki WR (2010) Feature selection with the Boruta package. J Stat Softw 36(11):1\u201313","journal-title":"J Stat Softw"},{"key":"9642_CR52","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/j.infsof.2014.07.005","volume":"58","author":"IH Laradji","year":"2015","unstructured":"Laradji IH, Alshayeb M, Ghouti L (2015) Software defect prediction using ensemble learning on selected features. Inf Softw Technol 58:388\u2013402. \n                    https:\/\/doi.org\/10.1016\/j.infsof.2014.07.005","journal-title":"Inf Softw Technol"},{"key":"9642_CR53","unstructured":"C. Lemnaru, R. Potolea (2011). Imbalanced Classification Problems: Systematic Study, Issues and Best Practices. In: Zhang R., Zhang J., Zhang Z., Filipe J., Cordeiro J. (eds) Enterprise Information Systems. ICEIS 2011. Lecture notes in business information processing, vol 102. Springer, Berlin, Heidelberg"},{"issue":"4","key":"9642_CR54","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 34(4):485\u2013496. \n                    https:\/\/doi.org\/10.1109\/TSE.2008.35","journal-title":"IEEE Trans Softw Eng"},{"key":"9642_CR55","doi-asserted-by":"publisher","unstructured":"Y. Liu, A. An, X. Huang, Advances in Knowledge discovery and data mining: 10th PacificAsia conference, PAKDD 2006, Singapore, April 9\u201312, 2006. Proceedings, in boosting prediction accuracy on imbalanced datasets with SVM ensembles, ed. by W.-K. Ng, M. Kitsuregawa, J. Li, K. Chang (Springer, Berlin, Heidelberg, 2006), pp. 107\u2013118. ISBN 978-3-540-33207-7. \n                    https:\/\/doi.org\/10.1007\/1173113915","DOI":"10.1007\/1173113915"},{"key":"9642_CR56","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.ins.2013.07.007","volume":"250","author":"V Lopez","year":"2013","unstructured":"Lopez V, Fernandez A, Garc\u0131a S, Palade V, Herrera F (2013) An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics. Inf Sci 250:113\u2013141. \n                    https:\/\/doi.org\/10.1016\/j.ins.2013.07.007","journal-title":"Inf Sci"},{"key":"9642_CR57","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1016\/j.asoc.2014.11.023","volume":"27","author":"R Malhotra","year":"2015","unstructured":"Malhotra R (2015) A systematic review of machine learning techniques for software fault prediction. Appl Soft Comput 27:504\u2013518. \n                    https:\/\/doi.org\/10.1016\/j.asoc.2014.11.023","journal-title":"Appl Soft Comput"},{"key":"9642_CR58","doi-asserted-by":"publisher","unstructured":"R. Malhotra, M. Khanna. An empirical study for software change prediction using imbalanced data Empir Software Eng, 22: 2806 (2017) \n                    https:\/\/doi.org\/10.1007\/s10664-016-9488-7","DOI":"10.1007\/s10664-016-9488-7"},{"key":"9642_CR59","doi-asserted-by":"publisher","unstructured":"Mamykina L, Manoim B, Mittal M, Hripcsak G, Hartmann B (2011) Design lessons from the fastest Q&A site in the west. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI\u201911). ACM, New York, pp 2857\u20132866. \n                    https:\/\/doi.org\/10.1145\/1978942.1979366","DOI":"10.1145\/1978942.1979366"},{"key":"9642_CR60","doi-asserted-by":"crossref","unstructured":"C.D. Manning, P. Raghavan H. Sch\u00fctze, Introduction to information retrieval, Cambridge University press. 2008","DOI":"10.1017\/CBO9780511809071"},{"key":"9642_CR61","doi-asserted-by":"publisher","unstructured":"T. Mende, R. Koschke, Revisiting the Evaluation of Defect Prediction Models, in Proceedings of the 5th International Conference on Predictor Models in Software Engineering. PROMISE \u201809 (ACM, New York, NY, USA, 2009), pp. 7\u20131710. ISBN 978-1-60558-634-2. \n                    https:\/\/doi.org\/10.1145\/1540438.1540448","DOI":"10.1145\/1540438.1540448"},{"key":"9642_CR62","doi-asserted-by":"crossref","unstructured":"T. Menzies, How not to do it: anti-patterns for data science in software engineering, in Proceedings of the 38th International Conference on Software Engineering Companion, ACM, 2016, pp. 887\u2013887","DOI":"10.1145\/2889160.2891047"},{"issue":"1","key":"9642_CR63","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10664-011-9193-5","volume":"17","author":"T Menzies","year":"2012","unstructured":"Menzies T, Shepperd M (2012) Special issue on repeatable results in software engineering prediction. Empir Softw Eng 17(1):1\u201317","journal-title":"Empir Softw Eng"},{"issue":"1","key":"9642_CR64","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/TSE.2007.10","volume":"33","author":"T Menzies","year":"2007","unstructured":"Menzies T, Greenwald J, Frank A (2007) Data mining static code attributes to learn defect predictors. IEEE Trans Softw Eng 33(1):2\u201313. \n                    https:\/\/doi.org\/10.1109\/TSE.2007.10","journal-title":"IEEE Trans Softw Eng"},{"issue":"4","key":"9642_CR65","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s10515-010-0069-5","volume":"17","author":"T Menzies","year":"2010","unstructured":"Menzies T, Milton Z, Turhan B, Cukic B, Jiang Y, Bener A (2010) Defect prediction from static code features: current results, limitations, new approaches. Autom Softw Eng 17(4):375\u2013407. \n                    https:\/\/doi.org\/10.1007\/s10515-010-0069-5","journal-title":"Autom Softw Eng"},{"key":"9642_CR66","doi-asserted-by":"publisher","unstructured":"J. Nam and S. Kim. Heterogeneous defect prediction. In Proc. of the 10th Joint Meeting on Foundations of Software Engineering - ESEC\/FSE\u201915 (ACM, 2015), 2015, pp. 508\u2013519. \n                    https:\/\/doi.org\/10.1145\/2786805.2786814","DOI":"10.1145\/2786805.2786814"},{"issue":"6","key":"9642_CR67","doi-asserted-by":"publisher","first-page":"1186","DOI":"10.1109\/TKDE.2017.2669982","volume":"29","author":"L Nie","year":"2017","unstructured":"Nie L, Wei X, Zhang D, Wang X, Gao Z, Yang Y (2017) Data-driven answer selection in community QA systems. IEEE Trans Knowl Data Eng 29(6):1186\u20131198","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"9642_CR68","volume-title":"Crowd documentation: exploring the coverage and the dynamics of api discussions on stack overflow","author":"C Parnin","year":"2012","unstructured":"Parnin C, Treude C, Grammel L (2012) Crowd documentation: exploring the coverage and the dynamics of api discussions on stack overflow. Technical report, Georgia Institute of Technology"},{"key":"9642_CR69","doi-asserted-by":"crossref","unstructured":"F. Peters, T. Menzies, A. Marcus. 2013. Better cross company defect prediction. In proceedings of the 10th working conference on mining software repositories (MSR '13). IEEE press, Piscataway, NJ, USA, 409-418","DOI":"10.1109\/MSR.2013.6624057"},{"key":"9642_CR70","doi-asserted-by":"publisher","unstructured":"E. Pitler, A. Nenkova, Revisiting readability, in Proc. of the Conf. On empirical methods in natural language processing \u2013 EMNLP \u201808 (ACL, 2008). \n                    https:\/\/doi.org\/10.3115\/1613715.1613742","DOI":"10.3115\/1613715.1613742"},{"issue":"3","key":"9642_CR71","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MCAS.2006.1688199","volume":"6","author":"R Polikar","year":"2006","unstructured":"Polikar R (2006) Ensemble based systems in decision making. Circuits and Systems Magazine, IEEE 6(3):21\u201345. \n                    https:\/\/doi.org\/10.1109\/MCAS.2006.1688199","journal-title":"Circuits and Systems Magazine, IEEE"},{"key":"9642_CR72","doi-asserted-by":"publisher","unstructured":"L. Ponzanelli, A. Mocci, A. Bacchelli, M. Lanza, D. Fullerton, Improving low quality stack overflow post detection, in 2014 IEEE Int\u2019l Conf. On software maintenance and evolution (IEEE, 2014). \n                    https:\/\/doi.org\/10.1109\/icsme.2014.90","DOI":"10.1109\/icsme.2014.90"},{"key":"9642_CR73","unstructured":"F.J. Provost, T. Fawcett, Analysis and visualization of classifier performance: comparison under imprecise class and cost distributions., in KDD, vol. 97, 1997, pp. 43\u201348"},{"key":"9642_CR74","unstructured":"F.J. Provost, T. Fawcett, R. Kohavi, The case against accuracy estimation for comparing induction algorithms., in ICML, vol. 98, 1998, pp. 445\u2013453"},{"key":"9642_CR75","doi-asserted-by":"publisher","unstructured":"F. Rahman, D. Posnett, P. Devanbu. 2012. Recalling the \u201cimprecision\u201d of cross-project defect prediction. In proc. 20th Int\u2019l symposium on the foundations of software engineering (FSE \u201812), \n                    https:\/\/doi.org\/10.1145\/2393596.2393669","DOI":"10.1145\/2393596.2393669"},{"issue":"3","key":"9642_CR76","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.2307\/2533581","volume":"53","author":"TJ Ringrose","year":"1997","unstructured":"Ringrose TJ, Hand DJ (1997) Construction and Assessment of Classification Rules Biometrics 53(3):1181. \n                    https:\/\/doi.org\/10.2307\/2533581","journal-title":"Construction and Assessment of Classification Rules Biometrics"},{"key":"9642_CR77","doi-asserted-by":"crossref","unstructured":"X Robin, N Turck, A Hainard, N Tiberti, F Lisacek, J-C Sanchez, M. M\u00fcller (2011). pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics, 12:77 (2011)","DOI":"10.1186\/1471-2105-12-77"},{"key":"9642_CR78","unstructured":"P.K. Roy, Z. Ahmad, J. P. Singh, .M.A. Ali Alryalat, N.P. Rana, Y. K Dwivedi (2017). Finding and ranking high-quality answers in community question answering sites. Global Journal of Flexible Systems Management, pp 1\u201316"},{"issue":"19","key":"9642_CR79","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.1093\/bioinformatics\/btm344","volume":"23","author":"Y Saeys","year":"2007","unstructured":"Saeys Y, Inza I, Larra\u00f1aga P (2007) A review of feature selection techniques in bioinformatics. Bioinformatics 23(19):2507\u20132517","journal-title":"Bioinformatics"},{"key":"9642_CR80","doi-asserted-by":"publisher","unstructured":"S. Scalabrino, M. Linares-V\u00e1squez, D. Poshyvanyk and R. Oliveto. Improving code readability models with textual features. In proceedings of the IEEE 24th international conference on program comprehension (ICPC\u201916), Austin, TX, 2016, pp. 1\u201310. \n                    https:\/\/doi.org\/10.1109\/ICPC.2016.7503707","DOI":"10.1109\/ICPC.2016.7503707"},{"issue":"3","key":"9642_CR81","doi-asserted-by":"publisher","first-page":"507","DOI":"10.2307\/2529204","volume":"30","author":"AJ Scott","year":"1974","unstructured":"Scott AJ, Knott M (1974) A cluster analysis method for grouping means in the analysis of variance. Biometrics 30(3):507\u2013512","journal-title":"Biometrics"},{"key":"9642_CR82","unstructured":"C. Shah, Building a parsimonious model for identifying best answers using interaction history in community Q&A, in Proceedings of the 78th ASIS&T Annual Meeting: Information Science with Impact: Research in and for the Community, American Society for Information Science, 2015, p. 51"},{"key":"9642_CR83","doi-asserted-by":"publisher","unstructured":"C. Shah, J. Pomerantz, Evaluating and predicting answer quality in community QA, in Proceeding of the 33rd Int\u2019l ACM SIGIR Conf. On research and development in information retrieval \u2013 SIGIR \u201810 (ACM, 2010). \n                    https:\/\/doi.org\/10.1145\/1835449.1835518","DOI":"10.1145\/1835449.1835518"},{"key":"9642_CR84","unstructured":"M. Shaw (2016) Progress Toward an Engineering Discipline of Software. ICSE 2016 Keynote"},{"key":"9642_CR85","doi-asserted-by":"publisher","unstructured":"M. Squire, Should we move to stack overflow? Measuring the utility of social Media for Developer Support, in Proceedings of the 2015 IEEE\/ACM 37th IEEE Int\u2019l Conf. On software engineering (IEEE, 2015). \n                    https:\/\/doi.org\/10.1109\/icse.2015.150","DOI":"10.1109\/icse.2015.150"},{"key":"9642_CR86","doi-asserted-by":"crossref","unstructured":"C. Tantithamthavorn, S. McIntosh, A.E. Hassan, K. Matsumoto, Automated parameter optimization of classification techniques for defect prediction models, in Proc. of the international conference on software engineering (ICSE), 2016","DOI":"10.1145\/2884781.2884857"},{"issue":"1","key":"9642_CR87","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TSE.2016.2584050","volume":"43","author":"C Tantithamthavorn","year":"2017","unstructured":"Tantithamthavorn C, McIntosh S, Hassan AE, Matsumoto K (2017) An empirical comparison of model validation techniques for defect prediction models. IEEE Trans Softw Eng 43(1):1\u201318. \n                    https:\/\/doi.org\/10.1109\/TSE.2016.2584050","journal-title":"IEEE Trans Softw Eng"},{"key":"9642_CR88","unstructured":"Q. Tian, P. Zhang, B. Li, Towards Predicting the Best Answers in Community-based Question-Answering Services., in Proc. of the 7th Int\u2019l Conf. on Weblogs and Social Media \u2013 ICWSM \u201813, ed. by E. Kiciman, N.B. Ellison, B. Hogan, P. Resnick, I. Soboroff (The AAAI Press, 2013). ISBN 978-1-57735-610-3"},{"key":"9642_CR89","doi-asserted-by":"crossref","unstructured":"A. Tosun, A. Bener, Reducing false alarms in software defect prediction by decision threshold optimization, in Proceedings of the 2009 3rd International Symposium on Empirical Software Engineering and Measurement, IEEE Computer Society, 2009, pp. 477\u2013480","DOI":"10.1109\/ESEM.2009.5316006"},{"key":"9642_CR90","doi-asserted-by":"publisher","unstructured":"C. Treude, O. Barzilay, M.-A. Storey, How do programmers ask and answer questions on the web?, in Proceeding of the 33rd Int\u2019l Conf. On software engineering \u2013 ICSE \u201811 (ACM, 2011). \n                    https:\/\/doi.org\/10.1145\/1985793.1985907","DOI":"10.1145\/1985793.1985907"},{"issue":"1\u20132","key":"9642_CR91","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/s10664-011-9182-8","volume":"17","author":"B Turhan","year":"2012","unstructured":"Turhan B (2012) On the dataset shift problem in software engineering prediction models. Empir Softw Eng 17(1\u20132):62\u201374","journal-title":"Empir Softw Eng"},{"key":"9642_CR92","doi-asserted-by":"publisher","unstructured":"B. Turhan, T. Menzies, A.B. Bener, J. Di Stefano. 2009. On the relative value of cross-company and within-company data for defect prediction. Empirical Softw. Eng. 14, 5 (October 2009), 540\u2013578. \n                    https:\/\/doi.org\/10.1007\/s10664-008-9103-7","DOI":"10.1007\/s10664-008-9103-7"},{"key":"9642_CR93","doi-asserted-by":"publisher","unstructured":"B. Turhan, A. Tosun and A. Bener, Empirical Evaluation of Mixed-Project Defect Prediction Models, 37th EUROMICRO Conference on Software Engineering and Advanced Applications, 2011, pp. 396\u2013403. \n                    https:\/\/doi.org\/10.1109\/SEAA.2011.59","DOI":"10.1109\/SEAA.2011.59"},{"key":"9642_CR94","doi-asserted-by":"publisher","unstructured":"B. Vasilescu, A. Serebrenik, P. Devanbu, V. Filkov, How Social Q&A Sites Are Changing Knowledge Sharing in Open Source Software Communities, in Proc. of the 17th ACM Conf. on Computer Supported Cooperative Work. CSCW \u201814 (ACM, New York, NY, USA, 2014), pp. 342\u2013354. ISBN 978-1-4503-2540-0. \n                    https:\/\/doi.org\/10.1145\/2531602.2531659","DOI":"10.1145\/2531602.2531659"},{"issue":"1","key":"9642_CR95","first-page":"1","volume":"1","author":"RS Wahono","year":"2015","unstructured":"Wahono RS (2015) A systematic literature review of software defect prediction: research trends, datasets, methods and frameworks. Journal of Software Engineering 1(1):1\u201316","journal-title":"Journal of Software Engineering"},{"key":"9642_CR96","doi-asserted-by":"publisher","unstructured":"Wang S, Chen TH, Hassan AE (2017) Understanding the factors for fast answers in technical Q&a websites. Empir Software Eng, pp:1\u201342. \n                    https:\/\/doi.org\/10.1007\/s10664-017-9558-5","DOI":"10.1007\/s10664-017-9558-5"},{"key":"9642_CR97","unstructured":"X. Xia, D. Lo, D. Correa, A. Sureka, E. Shihab (2016) It takes two to tango: deleted stack overflow question prediction with text and Meta features, IEEE 40th annual computer software and applications conference (COMPSAC\u201916), Atlanta, GE, USA, pp.73\u201382"},{"key":"9642_CR98","doi-asserted-by":"crossref","unstructured":"B. Xu, Z. Xing, X. Xia, D. Lo, Q. Wang, S. Li (2016a). Domain-specific cross-language relevant question retrieval. In Proc. of 13th Int\u2019l Conf. on Mining Software Repositories (MSR\u201916), Austin, TX, USA, pp. 413\u2013424","DOI":"10.1145\/2901739.2901746"},{"key":"9642_CR99","doi-asserted-by":"crossref","unstructured":"B. Xu, D. Ye, Z. Xing, X. Xia, G. Chen, S. Li (2016b). Predicting semantically linkable knowledge in developer online forums via convolutional neural network. In proc of 31st IEEE\/ACM international conference on automated software engineering (ASE\u201916), Singapore, pp. 51\u201362","DOI":"10.1145\/2970276.2970357"},{"key":"9642_CR100","doi-asserted-by":"crossref","unstructured":"B. Xu, Z. Xing, X. Xia, D. Lo (2017). AnswerBot: Automated Generation of Answer Summary to Developers' Technical Questions, In Proc. of 32nd IEEE\/ACM Int\u2019l Conf. on Automated Software Engineering (ASE\u201917), Urbana-Champaign, IL, USA, 706\u2013716","DOI":"10.1109\/ASE.2017.8115681"},{"key":"9642_CR101","doi-asserted-by":"publisher","unstructured":"Y. Yang, X. Liu, A Re-examination of Text Categorization Methods, in Proceedings of the 22Nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR \u201899 (ACM, New York, NY, USA, 1999), pp. 42\u201349. ISBN 1-58113-096-1. \n                    https:\/\/doi.org\/10.1145\/312624.312647","DOI":"10.1145\/312624.312647"},{"issue":"9","key":"9642_CR102","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1109\/TSE.2007.70706","volume":"33","author":"H Zhang","year":"2007","unstructured":"Zhang H, Zhang X (2007) Comments on \u201cdata mining static code attributes to learn defect predictors\u201d. IEEE Trans Softw Eng 33(9):635\u2013637. \n                    https:\/\/doi.org\/10.1109\/TSE.2007.70706","journal-title":"IEEE Trans Softw Eng"},{"key":"9642_CR103","doi-asserted-by":"publisher","unstructured":"F. Zhang, A. Mockus, I. Keivanloo, Y. Zou. Towards building a universal defect prediction model with rank transformed predictors. Empir Softw Eng, 21, 5 (Oct. 2016), 2107\u20132145. \n                    https:\/\/doi.org\/10.1007\/s10664-015-9396-2","DOI":"10.1007\/s10664-015-9396-2"},{"key":"9642_CR104","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1016\/j.neucom.2016.12.097","volume":"269","author":"W Zheng","year":"2017","unstructured":"Zheng W, Li M (2017) The best answer prediction by exploiting heterogeneous data on software development Q&a forum. Neurocomputing 269:212\u2013219. \n                    https:\/\/doi.org\/10.1016\/j.neucom.2016.12.097","journal-title":"Neurocomputing"},{"key":"9642_CR105","doi-asserted-by":"publisher","unstructured":"T. Zimmermann, N. Nagappan, H. Gall, E. Giger, B. Murphy. 2009. Cross-project defect prediction: a large scale experiment on data vs. domain vs. process. In proc, of 7th joint meeting of the European software engineering Conf. And ACM SIGSOFT symposium on the foundations of software engineering (ESEC\/FSE '09). ACM, New York, NY, USA, 91-100. \n                    https:\/\/doi.org\/10.1145\/1595696.1595713","DOI":"10.1145\/1595696.1595713"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-018-9642-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10664-018-9642-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-018-9642-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,21]],"date-time":"2019-12-21T16:07:32Z","timestamp":1576944452000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10664-018-9642-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,7]]},"references-count":105,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["9642"],"URL":"https:\/\/doi.org\/10.1007\/s10664-018-9642-5","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"type":"print","value":"1382-3256"},{"type":"electronic","value":"1573-7616"}],"subject":[],"published":{"date-parts":[[2018,8,7]]},"assertion":[{"value":"7 August 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}