{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T03:36:32Z","timestamp":1778211392533,"version":"3.51.4"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2018,1,30]],"date-time":"2018-01-30T00:00:00Z","timestamp":1517270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1007\/s10664-018-9595-8","type":"journal-article","created":{"date-parts":[[2018,1,30]],"date-time":"2018-01-30T05:08:24Z","timestamp":1517288904000},"page":"2655-2694","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":76,"title":["Studying software logging using topic models"],"prefix":"10.1007","volume":"23","author":[{"given":"Heng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tse-Hsun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiyi","family":"Shang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed E.","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,1,30]]},"reference":[{"key":"9595_CR1","unstructured":"Apache-Commons (2016) Best practices\u2014logging exceptions. https:\/\/2.zoppoz.workers.dev:443\/https\/commons.apache.org\/logging\/guide.html"},{"key":"9595_CR2","doi-asserted-by":"crossref","unstructured":"Asuncion H U, Asuncion A U, Taylor R N (2010) Software traceability with topic modeling. In: Proceedings of the 32nd international conference on software engineering. ICSE \u201910, pp 95\u2013104","DOI":"10.1145\/1806799.1806817"},{"key":"9595_CR3","doi-asserted-by":"crossref","unstructured":"Baldi PF, Lopes CV, Linstead EJ, Bajracharya SK (2008a) A theory of aspects as latent topics. In: Proceedings of the 23rd ACM SIGPLAN conference on object-oriented programming systems languages and applications. OOPSLA \u201908, pp 543\u2013562","DOI":"10.1145\/1449764.1449807"},{"key":"9595_CR4","doi-asserted-by":"crossref","unstructured":"Baldi P F, Lopes C V, Linstead E J, Bajracharya S K (2008b) A theory of aspects as latent topics. In: ACM Sigplan notices, vol 43. ACM, pp 543\u2013562","DOI":"10.1145\/1449764.1449807"},{"issue":"7","key":"9595_CR5","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1109\/TSE.2013.60","volume":"40","author":"G Bavota","year":"2014","unstructured":"Bavota G, Oliveto R, Gethers M, Poshyvanyk D, Lucia A D (2014) Methodbook: recommending move method refactorings via relational topic models. IEEE Trans Softw Eng 40(7):671\u2013694","journal-title":"IEEE Trans Softw Eng"},{"key":"9595_CR6","doi-asserted-by":"crossref","unstructured":"Binkley D, Heinz D, Lawrie D, Overfelt J (2014) Understanding LDA in source code analysis. In: Proceedings of the 22nd international conference on program comprehension, pp 26\u201336","DOI":"10.1145\/2597008.2597150"},{"key":"9595_CR7","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei D M, Ng A Y, Jordan M I (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993\u20131022","journal-title":"J Mach Learn Res"},{"issue":"3","key":"9595_CR8","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1080\/00031305.1994.10476059","volume":"48","author":"J Bring","year":"1994","unstructured":"Bring J (1994) How to standardize regression coefficients. Am Stat 48(3):209\u2013213","journal-title":"Am Stat"},{"key":"9595_CR9","first-page":"467","volume":"18","author":"PF Brown","year":"1992","unstructured":"Brown P F, deSouza P V, Mercer R L, Pietra V J D, Lai J C (1992) Class-based n-gram models of natural language. Comput Linguist 18:467\u2013479","journal-title":"Comput Linguist"},{"key":"9595_CR10","first-page":"288","volume":"22","author":"J Chang","year":"2009","unstructured":"Chang J, Gerrish S, Wang C, Boyd-graber JL, Blei D M (2009) Reading tea leaves: how humans interpret topic models. Adv Neural Inf Process Syst 22:288\u2013296","journal-title":"Adv Neural Inf Process Syst"},{"key":"9595_CR11","doi-asserted-by":"crossref","unstructured":"Chen B, Jiang Z M (2017) Characterizing and detecting anti-patterns in the logging code. In: Proceedings of the 39th international conference on software engineering. ICSE \u201917, pp 71\u201381","DOI":"10.1109\/ICSE.2017.15"},{"key":"9595_CR12","doi-asserted-by":"crossref","unstructured":"Chen T-H, Thomas S W, Nagappan M, Hassan A (2012) Explaining software defects using topic models. In: Proceedings of the 9th working conference on mining software repositories. MSR \u201912, pp 189\u2013 198","DOI":"10.1109\/MSR.2012.6224280"},{"key":"9595_CR13","doi-asserted-by":"crossref","unstructured":"Chen T-H, Shang W, Hassan A E, Nasser M, Flora P (2016a) Cacheoptimizer: helping developers configure caching frameworks for hibernate-based database-centric web applications. In: Proceedings of the 24th ACM SIGSOFT international symposium on foundations of software engineering. FSE \u201916, pp 666\u2013 677","DOI":"10.1145\/2950290.2950303"},{"key":"9595_CR14","doi-asserted-by":"crossref","unstructured":"Chen T-H, Thomas S W, Hassan A E (2016b) A survey on the use of topic models when mining software repositories. Empir Softw Eng 21(5):1843\u20131919","DOI":"10.1007\/s10664-015-9402-8"},{"key":"9595_CR15","doi-asserted-by":"crossref","unstructured":"Chen T-H, Syer M D, Shang W, Jiang Z M, Hassan A E, Nasser M, Flora P (2017a) Analytics-driven load testing: an industrial experience report on load testing of large-scale systems. In: Proceedings of the 39th international conference on software engineering: software engineering in practice track. ICSE-SEIP \u201917, pp 243\u2013252","DOI":"10.1109\/ICSE-SEIP.2017.26"},{"key":"9595_CR16","doi-asserted-by":"crossref","unstructured":"Chen T-H, Shang W, Nagappan M, Hassan A E, Thomas S W (2017b) Topic-based software defect explanation. J Syst Softw 129:79\u2013106","DOI":"10.1016\/j.jss.2016.05.015"},{"issue":"1","key":"9595_CR17","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s10664-008-9095-3","volume":"14","author":"B Cleary","year":"2008","unstructured":"Cleary B, Exton C, Buckley J, English M (2008) An empirical analysis of information retrieval based concept location techniques in software comprehension. Empir Softw Eng 14(1):93\u2013130","journal-title":"Empir Softw Eng"},{"key":"9595_CR18","unstructured":"Cohen I, Goldszmidt M, Kelly T, Symons J, Chase J S (2004) Correlating instrumentation data to system states: a building block for automated diagnosis and control. In: Proceedings of the 6th conference on symposium on opearting systems design & implementation, pp 16\u201316"},{"key":"9595_CR19","doi-asserted-by":"crossref","unstructured":"De Lucia A, Di Penta M, Oliveto R, Panichella A, Panichella S (2012) Using IR methods for labeling source code artifacts: is it worthwhile? In: Proceedings of the 20th international conference on program comprehension. ICPC \u201912, pp 193\u2013202","DOI":"10.1109\/ICPC.2012.6240488"},{"issue":"5","key":"9595_CR20","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1007\/s10664-013-9285-5","volume":"19","author":"A De Lucia","year":"2014","unstructured":"De Lucia A, Di Penta M, Oliveto R, Panichella A, Panichella S (2014) Labeling source code with information retrieval methods: an empirical study. Empir Softw Eng 19(5):1383\u20131420","journal-title":"Empir Softw Eng"},{"issue":"1","key":"9595_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i01","volume":"33","author":"J Friedman","year":"2010","unstructured":"Friedman J, Hastie T, Tibshirani R (2010) Regularization paths for generalized linear models via coordinate descent. J Stat Softw 33(1):1\u201322","journal-title":"J Stat Softw"},{"key":"9595_CR22","doi-asserted-by":"crossref","unstructured":"Fu Q, Zhu J, Hu W, Lou J-G, Ding R, Lin Q, Zhang D, Xie T (2014) Where do developers log? An empirical study on logging practices in industry. In: Companion proceedings of the 36th international conference on software engineering. ICSE Companion \u201914, pp 24\u201333","DOI":"10.1145\/2591062.2591175"},{"key":"9595_CR23","doi-asserted-by":"crossref","unstructured":"Goshtasby A A (2012) Similarity and dissimilarity measures. In: Image registration: principles, tools and methods. Springer London, London, pp 7\u201366","DOI":"10.1007\/978-1-4471-2458-0_2"},{"issue":"4","key":"9595_CR24","first-page":"391","volume":"33","author":"RA Groeneveld","year":"1984","unstructured":"Groeneveld R A, Meeden G (1984) Measuring Skewness and Kurtosis. J R Stat Soc D (Stat) 33(4):391\u2013399","journal-title":"J R Stat Soc D (Stat)"},{"key":"9595_CR25","doi-asserted-by":"crossref","unstructured":"Hall D, Jurafsky D, Manning C D (2008) Studying the history of ideas using topic models. In: Proceedings of the 2008 conference on empirical methods in natural language processing. EMNLP \u201908, pp 363\u2013371. Association for Computational Linguistics","DOI":"10.3115\/1613715.1613763"},{"key":"9595_CR26","doi-asserted-by":"crossref","unstructured":"Hindle A, Bird C, Zimmermann T, Nagappan N (2014) Do topics make sense to managers and developers? Empir Softw Eng","DOI":"10.1007\/s10664-014-9312-1"},{"key":"9595_CR27","doi-asserted-by":"crossref","unstructured":"Hu J, Sun X, Lo D, Li B (2015) Modeling the evolution of development topics using dynamic topic models. In: Proceedings of the 22nd IEEE international conference on software analysis, evolution, and reengineering. SANER\u201915, pp 3\u201312","DOI":"10.1109\/SANER.2015.7081810"},{"key":"9595_CR28","volume-title":"R in action","author":"R Kabacoff","year":"2011","unstructured":"Kabacoff R (2011) R in action. Manning Publications Co., Greenwich"},{"key":"9595_CR29","doi-asserted-by":"crossref","unstructured":"Kabinna S, Bezemer C-P, Hassan A E, Shang W (2016) Examining the stability of logging statements. In: Proceedings of the 23rd IEEE international conference on software analysis, evolution, and reengineering. SANER \u201916","DOI":"10.1109\/SANER.2016.29"},{"key":"9595_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6849-3","volume-title":"Applied predictive modeling","author":"M Kuhn","year":"2013","unstructured":"Kuhn M, Johnson K (2013) Applied predictive modeling. Springer, Berlin"},{"key":"9595_CR31","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.infsof.2006.10.017","volume":"49","author":"A Kuhn","year":"2007","unstructured":"Kuhn A, Ducasse S, G\u00edrba T (2007) Semantic clustering: identifying topics in source code. Inf Softw Technol 49:230\u2013243","journal-title":"Inf Softw Technol"},{"key":"9595_CR32","doi-asserted-by":"crossref","unstructured":"Lal S, Sureka A (2016) Logopt: static feature extraction from source code for automated catch block logging prediction. In: Proceedings of the 9th India software engineering conference. ISEC \u201916, pp 151\u2013 155","DOI":"10.1145\/2856636.2856637"},{"key":"9595_CR33","doi-asserted-by":"crossref","unstructured":"Li H, Shang W, Zou Y, Hassan AE (2017a) Towards just-in-time suggestions for log changes. Empir Softw Eng 22(4):1831\u20131865","DOI":"10.1007\/s10664-016-9467-z"},{"key":"9595_CR34","doi-asserted-by":"crossref","unstructured":"Li H, Shang W, Hassan AE (2017b) Which log level should developers choose for a new logging statement? Empir Softw Eng 22(4):1684\u20131716","DOI":"10.1007\/s10664-016-9456-2"},{"key":"9595_CR35","doi-asserted-by":"crossref","unstructured":"Linstead E, Lopes C, Baldi P (2008) An application of latent Dirichlet allocation to analyzing software evolution. In: Proceedings of seventh international conference on machine learning and applications. ICMLA \u201912, pp 813\u2013818","DOI":"10.1109\/ICMLA.2008.47"},{"key":"9595_CR36","doi-asserted-by":"crossref","unstructured":"Liu Y, Poshyvanyk D, Ferenc R, Gyimothy T, Chrisochoides N (2009a) Modeling class cohesion as mixtures of latent topics. In: Proceedings of the 25th international conference on software maintenance. ICSE \u201909, pp 233\u2013242","DOI":"10.1109\/ICSM.2009.5306318"},{"key":"9595_CR37","doi-asserted-by":"crossref","unstructured":"Liu Y, Poshyvanyk D, Ferenc R, Gyimothy T, Chrisochoides N (2009b) Modeling class cohesion as mixtures of latent topics. In: Proceedings of the 25th IEEE international conference on software maintenance. ICSM \u201909, pp 233\u2013242","DOI":"10.1109\/ICSM.2009.5306318"},{"issue":"2","key":"9595_CR38","doi-asserted-by":"crossref","first-page":"545","DOI":"10.11144\/Javeriana.upsy10-2.cdcp","volume":"10","author":"G Macbeth","year":"2011","unstructured":"Macbeth G, Razumiejczyk E, Ledesma R D (2011) Cliff\u2019s delta calculator: a non-parametric effect size program for two groups of observations. Univ Psychol 10 (2):545\u2013555","journal-title":"Univ Psychol"},{"key":"9595_CR39","doi-asserted-by":"crossref","unstructured":"Mariani L, Pastore F (2008) Automated identification of failure causes in system logs. In: Proceedings of the 2008 19th international symposium on software reliability engineering, pp 117\u2013126","DOI":"10.1109\/ISSRE.2008.48"},{"issue":"10","key":"9595_CR40","doi-asserted-by":"publisher","first-page":"2570","DOI":"10.1021\/ci300338w","volume":"52","author":"TM Martin","year":"2012","unstructured":"Martin T M, Harten P, Young D M, Muratov E N, Golbraikh A, Zhu H, Tropsha A (2012) Does rational selection of training and test sets improve the outcome of qsar modeling? J Chem Inf Model 52(10):2570\u20132578","journal-title":"J Chem Inf Model"},{"key":"9595_CR41","doi-asserted-by":"crossref","unstructured":"Maskeri G, Sarkar S, Heafield K (2008) Mining business topics in source code using latent Dirichlet allocation. In: Proceedings of the 1st India software engineering conference, pp 113\u2013120","DOI":"10.1145\/1342211.1342234"},{"issue":"4","key":"9595_CR42","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1109\/TSE.1976.233837","volume":"SE-2","author":"TJ McCabe","year":"1976","unstructured":"McCabe TJ (1976) A complexity measure. IEEE Trans Softw Eng SE-2(4):308\u2013320","journal-title":"IEEE Trans Softw Eng"},{"key":"9595_CR43","unstructured":"McCallum AK (2002) Mallet: a machine learning for language toolkit"},{"key":"9595_CR44","unstructured":"Microsoft-MSDN (2016) Logging an exception. https:\/\/2.zoppoz.workers.dev:443\/https\/msdn.microsoft.com\/en-us\/library\/ff664711(v=pandp.50).aspx"},{"key":"9595_CR45","doi-asserted-by":"crossref","unstructured":"Misra H, Capp\u00e9 O, Yvon F (2008) Using lda to detect semantically incoherent documents. In: Proceedings of the 12th conference on computational natural language learning. CoNLL \u201908. Association for Computational Linguistics, pp 41\u201348","DOI":"10.3115\/1596324.1596332"},{"key":"9595_CR46","doi-asserted-by":"crossref","unstructured":"Nguyen T T, Nguyen T N, Phuong T M (2011) Topic-based defect prediction. In: Proceedings of the 33rd international conference on software engineering. ICSE \u201911, pp 932\u2013935","DOI":"10.1145\/1985793.1985950"},{"issue":"2","key":"9595_CR47","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1145\/2076450.2076466","volume":"55","author":"A Oliner","year":"2012","unstructured":"Oliner A, Ganapathi A, Xu W (2012) Advances and challenges in log analysis. Commun ACM 55(2):55\u201361","journal-title":"Commun ACM"},{"key":"9595_CR48","doi-asserted-by":"crossref","unstructured":"Panichella A, Dit B, Oliveto R, Di Penta M, Poshyvanyk D, De Lucia A (2013) How to effectively use topic models for software engineering tasks? An approach based on genetic algorithms. In: Proceedings of the 2013 international conference on software engineering. ICSE \u201913, pp 522\u2013531","DOI":"10.1109\/ICSE.2013.6606598"},{"key":"9595_CR49","doi-asserted-by":"crossref","unstructured":"Panichella A, Dit B, Oliveto R, Di Penta M, Poshyvanyk D, De Lucia A (2016) Parameterizing and assembling ir-based solutions for se tasks using genetic algorithms. In: Proceedings of the 23rd IEEE international conference on software analysis, evolution, and reengineering. SANER \u201916","DOI":"10.1109\/SANER.2016.97"},{"key":"9595_CR50","doi-asserted-by":"crossref","unstructured":"Pecchia A, Cinque M, Carrozza G, Cotroneo D (2015) Industry practices and event logging: assessment of a critical software development process. In: Proceedings of the 37th international conference on software engineering. ICSE \u201915, pp 169\u2013178","DOI":"10.1109\/ICSE.2015.145"},{"issue":"6","key":"9595_CR51","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1109\/TSE.2007.1016","volume":"33","author":"D Poshyvanyk","year":"2007","unstructured":"Poshyvanyk D, Gueheneuc Y, Marcus A, Antoniol G, Rajlich V (2007) Feature location using probabilistic ranking of methods based on execution scenarios and information retrieval. IEEE Trans Softw Eng 33(6):420\u2013432","journal-title":"IEEE Trans Softw Eng"},{"key":"9595_CR52","doi-asserted-by":"crossref","unstructured":"Rao S, Kak A (2011) Retrieval from software libraries for bug localization: a comparative study of generic and composite text models. In: Proceeding of the 8th working conference on mining software repositories. MSR \u201911, pp 43\u201352","DOI":"10.1145\/1985441.1985451"},{"key":"9595_CR53","unstructured":"Romano J, Kromrey J D, Coraggio J, Skowronek J (2006) Appropriate statistics for ordinal level data: should we really be using t-test and cohen\u2019sd for evaluating group differences on the nsse and other surveys. In: Annual meeting of the Florida association of institutional research, pp 1\u201333"},{"issue":"1","key":"9595_CR54","first-page":"3","volume":"26","author":"W Shang","year":"2014","unstructured":"Shang W, Jiang Z M, Adams B, Hassan A E, Godfrey M W, Nasser M, Flora P (2014) An exploratory study of the evolution of communicated information about the execution of large software systems. J Softw: Evol Process 26(1):3\u201326","journal-title":"J Softw: Evol Process"},{"issue":"1","key":"9595_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10664-013-9274-8","volume":"20","author":"W Shang","year":"2015","unstructured":"Shang W, Nagappan M, Hassan AE (2015) Studying the relationship between logging characteristics and the code quality of platform software. Empir Softw Eng 20 (1):1\u201327","journal-title":"Empir Softw Eng"},{"issue":"5","key":"9595_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v039.i05","volume":"39","author":"N Simon","year":"2011","unstructured":"Simon N, Friedman J, Hastie T, Tibshirani R (2011) Regularization paths for cox\u2019s proportional hazards model via coordinate descent. J Stat Softw 39(5):1\u201313","journal-title":"J Stat Softw"},{"key":"9595_CR57","unstructured":"Steyvers M, Griffiths T (2007) Probabilistic topic models. In: Handbook of latent semantic analysis, vol 427(7), pp 424\u2013440"},{"key":"9595_CR58","doi-asserted-by":"crossref","unstructured":"Sun X, Li B, Leung H, Li B, Li Y (2015a) Msr4sm: using topic models to effectively mining software repositories for software maintenance tasks. Inf Softw Technol 66:1\u201312","DOI":"10.1016\/j.infsof.2015.05.003"},{"key":"9595_CR59","doi-asserted-by":"crossref","unstructured":"Sun X, Li B, Li Y, Chen Y (2015b) What information in software historical repositories do we need to support software maintenance tasks? An approach based on topic model. In: Computer and information science. Springer International Publishing, Cham, pp 27\u201337","DOI":"10.1007\/978-3-319-10509-3_3"},{"key":"9595_CR60","doi-asserted-by":"crossref","unstructured":"Sun X, Liu X, Li B, Duan Y, Yang H, Hu J (2016) Exploring topic models in software engineering data analysis: a survey. In: Proceedings of the 17th IEEE\/ACIS international conference on software engineering, artificial intelligence, networking and parallel\/distributed computing. SNPD\u2019, vol. 16, pp 357\u2013362","DOI":"10.1109\/SNPD.2016.7515925"},{"key":"9595_CR61","volume-title":"Statistics at Square One","author":"TDV Swinscow","year":"2002","unstructured":"Swinscow TDV, Campbell MJ et al (2002) Statistics at Square One. BMJ, London"},{"key":"9595_CR62","doi-asserted-by":"crossref","unstructured":"Syer MD, Jiang Z M, Nagappan M, Hassan A E, Nasser M, Flora P (2013) Leveraging performance counters and execution logs to diagnose memory-related performance issues. In: Proceedings of the 29th IEEE international conference on software maintenance. ICSM 13\u2019, pp 110\u2013119","DOI":"10.1109\/ICSM.2013.22"},{"key":"9595_CR63","unstructured":"Thomas SW (2012) A lightweight source code preprocesser. https:\/\/2.zoppoz.workers.dev:443\/https\/github.com\/doofuslarge\/lscp"},{"key":"9595_CR64","doi-asserted-by":"crossref","unstructured":"Thomas S, Adams B, Hassan A E, Blostein D (2010) Validating the use of topic models for software evolution. In: Proceedings of the 10th international working conference on source code analysis and manipulation. SCAM \u201910, pp 55\u201364","DOI":"10.1109\/SCAM.2010.13"},{"key":"9595_CR65","doi-asserted-by":"crossref","unstructured":"Thomas S W, Adams B, Hassan A E, Blostein D (2011) Modeling the evolution of topics in source code histories. In: Proceedings of the 8th working conference on mining software repositories, pp 173\u2013182","DOI":"10.1145\/1985441.1985467"},{"key":"9595_CR66","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/j.scico.2012.08.003","volume":"80","author":"SW Thomas","year":"2014","unstructured":"Thomas S W, Adams B, Hassan A E, Blostein D (2014) Studying software evolution using topic models. Sci Comput Program 80:457\u2013479","journal-title":"Sci Comput Program"},{"key":"9595_CR67","doi-asserted-by":"crossref","unstructured":"Tian K, Revelle M, Poshyvanyk D (2009) Using latent Dirichlet allocation for automatic categorization of software. In: Proceedings of the 6th international working conference on mining software repositories. MSR \u201909, pp 163\u2013166","DOI":"10.1109\/MSR.2009.5069496"},{"issue":"1","key":"9595_CR68","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"58","author":"R Tibshirani","year":"1996","unstructured":"Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Series B (Methodological) 58(1):267\u2013288","journal-title":"J R Stat Soc Series B (Methodological)"},{"key":"9595_CR69","unstructured":"Wallach H M, Mimno D M, McCallum A (2009) Rethinking lda: why priors matter. In: Advances in neural information processing systems. NIPS \u201909, pp 1973\u20131981"},{"key":"9595_CR70","volume-title":"Data mining: practical machine learning tools and techniques","author":"IH Witten","year":"2005","unstructured":"Witten I H, Frank E (2005) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, San Mateo"},{"key":"9595_CR71","doi-asserted-by":"crossref","unstructured":"Xu W, Huang L, Fox A, Patterson D, Jordan M I (2009) Detecting large-scale system problems by mining console logs. In: Proceedings of the ACM SIGOPS 22nd symposium on operating systems principles. SOSP \u201909, pp 117\u2013132","DOI":"10.1145\/1629575.1629587"},{"issue":"1","key":"9595_CR72","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1145\/1735970.1736038","volume":"38","author":"D Yuan","year":"2010","unstructured":"Yuan D, Mai H, Xiong W, Tan L, Zhou Y, Pasupathy S (2010) Sherlog: error diagnosis by connecting clues from run-time logs. SIGARCH Comput Architect News 38(1):143\u2013154","journal-title":"SIGARCH Comput Architect News"},{"key":"9595_CR73","doi-asserted-by":"crossref","unstructured":"Yuan D, Zheng J, Park S, Zhou Y, Savage S (2011) Improving software diagnosability via log enhancement. In: Proceedings of the sixteenth international conference on architectural support for programming languages and operating systems. ASPLOS \u201911, pp 3\u201314","DOI":"10.1145\/1950365.1950369"},{"key":"9595_CR74","unstructured":"Yuan D, Park S, Huang P, Liu Y, Lee M M, Tang X, Zhou Y, Savage S (2012a) Be conservative: enhancing failure diagnosis with proactive logging. In: Proceedings of the 10th USENIX conference on operating systems design and implementation. OSDI\u201912, pp 293\u2013306"},{"key":"9595_CR75","doi-asserted-by":"crossref","unstructured":"Yuan D, Park S, Zhou Y (2012b) Characterizing logging practices in open-source software. In: Proceedings of the 34th international conference on software engineering. ICSE \u201912, pp 102\u2013112","DOI":"10.1109\/ICSE.2012.6227202"},{"key":"9595_CR76","unstructured":"Yuan D, Luo Y, Zhuang X, Rodrigues G R, Zhao X, Zhang Y, Jain P U, Stumm M (2014) Simple testing can prevent most critical failures: an analysis of production failures in distributed data-intensive systems. In: Proceedings of the 11th USENIX conference on operating systems design and implementation. OSDI\u201914, pp 249\u2013265"},{"key":"9595_CR77","doi-asserted-by":"crossref","unstructured":"Zeng L, Xiao Y, Chen H (2015) Linux auditing: overhead and adaptation. In: Proceedings of 2015 IEEE international conference on communications. ICC \u201915, pp 7168\u20137173","DOI":"10.1109\/ICC.2015.7249470"},{"key":"9595_CR78","doi-asserted-by":"crossref","unstructured":"Zhang S, Cohen I, Symons J, Fox A (2005) Ensembles of models for automated diagnosis of system performance problems. In: Proceedings of the 2005 international conference on dependable systems and networks. DSN \u201905, pp 644\u2013653","DOI":"10.1109\/DSN.2005.44"},{"key":"9595_CR79","doi-asserted-by":"crossref","unstructured":"Zhu J, He P, Fu Q, Zhang H, Lyu M R, Zhang D (2015) Learning to log: helping developers make informed logging decisions. In: Proceedings of the 37th international conference on software engineering, vol 1. ICSE \u201915, pp 415\u2013425","DOI":"10.1109\/ICSE.2015.60"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/link.springer.com\/article\/10.1007\/s10664-018-9595-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/link.springer.com\/content\/pdf\/10.1007\/s10664-018-9595-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/link.springer.com\/content\/pdf\/10.1007\/s10664-018-9595-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T20:16:12Z","timestamp":1719778572000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/link.springer.com\/10.1007\/s10664-018-9595-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1,30]]},"references-count":79,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2018,10]]}},"alternative-id":["9595"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/s10664-018-9595-8","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1,30]]},"assertion":[{"value":"30 January 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}