{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T08:25:30Z","timestamp":1769070330122,"version":"3.49.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2012,10,10]],"date-time":"2012-10-10T00:00:00Z","timestamp":1349827200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2014,6]]},"DOI":"10.1007\/s10664-012-9230-z","type":"journal-article","created":{"date-parts":[[2012,10,9]],"date-time":"2012-10-09T08:18:03Z","timestamp":1349770683000},"page":"582-618","source":"Crossref","is-referenced-by-count":73,"title":["On using machine learning to automatically classify software applications into domain categories"],"prefix":"10.1007","volume":"19","author":[{"given":"Mario","family":"Linares-V\u00e1squez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Collin","family":"McMillan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denys","family":"Poshyvanyk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Grechanik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,10,10]]},"reference":[{"key":"9230_CR1","first-page":"37","volume":"6","author":"DW Aha","year":"1991","unstructured":"Aha DW, Kibler D, Albert MK (1991) Instance-based learning algorithms. Mach Learn 6:37\u201366","journal-title":"Mach Learn"},{"key":"9230_CR2","unstructured":"Alpaydin E (2010) Introduction to machine learning, 2nd edn. The MIT Press, Cambridge, Massachusetts"},{"key":"9230_CR3","doi-asserted-by":"crossref","unstructured":"Antoniol G, Ayari K, Di Penta M, Khomh F, Gu\u00e9h\u00e9neuc Y-G (2008) Is it a bug or an enhancement?: a text-based approach to classify change requests. 18th Conference of the Centre for Advanced Studies on Collaborative Research Meeting of Minds (CASCON\u201908), Ontario, Canada, pp 304\u2013318","DOI":"10.1145\/1463788.1463819"},{"key":"9230_CR4","doi-asserted-by":"crossref","unstructured":"Anvik J, Hiew L, Murphy GC (2006) Who should fix this bug? 28th International Conference on Software Engineering (ICSE\u201906), pp 361\u2013370","DOI":"10.1145\/1134285.1134336"},{"key":"9230_CR5","doi-asserted-by":"crossref","unstructured":"Anvik J, Murphy GC (2011) Reducing the effort of bug report triage: recommenders for development-oriented decisions. ACM Transactions on Software Engineering and Methods 20(3):10:1\u201310:35","DOI":"10.1145\/2000791.2000794"},{"key":"9230_CR6","doi-asserted-by":"crossref","unstructured":"Bajracharya S, Ossher J, Lopes CV (2010) Leveraging usage similarity for effective retrieval of examples in code repositories. 18th International Symposium on the Foundations of Software Engineering (FSE\u201910)","DOI":"10.1145\/1882291.1882316"},{"key":"9230_CR7","doi-asserted-by":"crossref","unstructured":"Bruno M, Canfora G, Di Penta M, Scognamiglio R (2005) An approach to support web service classification and annotation. IEEE International Conference on e-Technology, e-Commerce and e-Services (EEE\u201905), pp 138\u2013143","DOI":"10.1109\/EEE.2005.31"},{"key":"9230_CR8","doi-asserted-by":"crossref","unstructured":"Bugde S, Nagappan N, Rajamani S, Ramalingam G (2008) Global software servicing: observational experiences at Microsoft. 2008 IEEE International Conference on Global Software Engineering (ICGSE\u201908), pp 182\u2013191","DOI":"10.1109\/ICGSE.2008.18"},{"key":"9230_CR9","doi-asserted-by":"crossref","unstructured":"Cohen WW (1995) Fast effective rule induction. 12th International Conference on Machine Learning, pp 115\u2013123","DOI":"10.1016\/B978-1-55860-377-6.50023-2"},{"issue":"6","key":"9230_CR10","first-page":"1025","volume":"3","author":"K Crammer","year":"2003","unstructured":"Crammer K, Singer Y (2003) A family of additive online algorithms for category ranking. J Mach Learn Res 3(6):1025\u20131058","journal-title":"J Mach Learn Res"},{"key":"9230_CR11","doi-asserted-by":"crossref","unstructured":"de Carvalho ACPLF, Freitas AA (2009) A tutorial on multi-label classification techniques. Foundations of Computational Intelligence. A. Abraham, A.-E. Hassanien and V. Sn\u00e1sel, Springer-Verlag, 5","DOI":"10.1007\/978-3-642-01536-6_8"},{"key":"9230_CR12","first-page":"1","volume":"7","author":"J Demsar","year":"2006","unstructured":"Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1\u201330","journal-title":"J Mach Learn Res"},{"key":"9230_CR13","doi-asserted-by":"crossref","unstructured":"Di Lucca GA, Di Penta M, Gradara S (2002) An approach to classify software maintenance requests. IEEE International Conference on Software Maintenance (ICSM\u201902), Montr\u00e9al, Qu\u00e9bec, Canada, pp 93\u2013102","DOI":"10.1109\/ICSM.2002.1167756"},{"key":"9230_CR14","doi-asserted-by":"crossref","unstructured":"Dit B, Guerrouj L, Poshyvanyk D, Antoniol G (2011) Can better identifier splitting techniques help feature location? 19th IEEE International Conference on Program Comprehension (ICPC\u201911), Kingston, Ontario, Canada, pp 11\u201320","DOI":"10.1109\/ICPC.2011.47"},{"key":"9230_CR15","doi-asserted-by":"crossref","unstructured":"Dumitru H, Gibiec M, Hariri N, Cleland-Huang J, Mobasher B, Castro-Herrera C, Mirakhorli M (2011) On-demand feature recommendations derived from mining public product descriptions. 33rd IEEE\/ACM International Conference on Software Engineering (ICSE\u201911), Honolulu, Hawaii, USA, pp 181\u2013190","DOI":"10.1145\/1985793.1985819"},{"issue":"6","key":"9230_CR16","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1080\/09511920701530943","volume":"21","author":"C-XJ Feng","year":"2008","unstructured":"Feng C-XJ, Yu Z-GS, Emanuel JT, Li P-G, Shao X-Y, Wang Z-H (2008) Threefold versus fivefold cross-validation and individual versus average data in predictive regression modelling of machining experimental data. Int J Comput Integrated Manuf 21(6):702\u2013714","journal-title":"Int J Comput Integrated Manuf"},{"key":"9230_CR17","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1023\/A:1018972323770","volume":"5","author":"W Frakes","year":"1998","unstructured":"Frakes W, Prieto-Diaz R, Fox C (1998) DARE: domain analysis and reuse environment. Ann Software Eng 5:125\u2013141","journal-title":"Ann Software Eng"},{"key":"9230_CR18","doi-asserted-by":"crossref","unstructured":"Grechanik M, Csallner C, Fu C, Xie Q (2010) Is data privacy always good for software testing? 21st IEEE International Symposium on Software Reliability Engineering (ISSRE\u201910), San Jose, California, USA, pp 368\u2013377","DOI":"10.1109\/ISSRE.2010.13"},{"key":"9230_CR19","doi-asserted-by":"crossref","unstructured":"Grechanik M, Fu C, Xie Q, McMillan C, Poshyvanyk D, Cumby C (2010) A search engine for finding highly relevant applications. 32nd ACM\/IEEE International Conference on Software Engineering (ICSE\u201910), Cape Town, South Africa, pp 475\u2013484","DOI":"10.1145\/1806799.1806868"},{"key":"9230_CR20","doi-asserted-by":"crossref","unstructured":"Grechanik M, McMillan C, DeFerrari L, Comi M, Crespi S, Poshyvanyk D, Fu C, Xie Q, Ghezzi C (2010) An empirical investigation into a large-scale java open source code repository. 4th ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM \u201910), Bolzano-Bozen, Italy","DOI":"10.1145\/1852786.1852801"},{"key":"9230_CR21","doi-asserted-by":"crossref","DOI":"10.4324\/9780203803233","volume-title":"Effect sizes for research: univariate and multivariate applications","author":"RJ Grissom","year":"2012","unstructured":"Grissom RJ, Kim JJ (2012) Effect sizes for research: univariate and multivariate applications, 2nd edn. Taylor & Francis, New York","edition":"2"},{"key":"9230_CR22","first-page":"1157","volume":"3","author":"I Guyon","year":"2003","unstructured":"Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157\u20131182","journal-title":"J Mach Learn Res"},{"key":"9230_CR23","doi-asserted-by":"crossref","unstructured":"Hindle A, Germ\u00e1n DM, Godfrey MW, Holt RC (2009) Automatic Classification of Large Changes into Maintenance Categories. 17th IEEE International Conference on Program Comprehension (ICPC\u201909), Vancouver, Canada, pp 30\u201339","DOI":"10.1109\/ICPC.2009.5090025"},{"issue":"2","key":"9230_CR24","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1109\/72.991427","volume":"13","author":"C Hsu","year":"2002","unstructured":"Hsu C, Lin C (2002) A comparison of methods for multiclass support vector machines. IEEE Trans Neural Network 13(2):415\u2013425","journal-title":"IEEE Trans Neural Network"},{"key":"9230_CR25","doi-asserted-by":"crossref","unstructured":"Ji S, Tang L, Yu S, Ye J (2008) Extracting shared subspace for multi-label classification. 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD\u201908), Las Vegas, Nevada, USA, pp 381\u2013389","DOI":"10.1145\/1401890.1401939"},{"key":"9230_CR26","volume-title":"Software engineering best practices","author":"C Jones","year":"2010","unstructured":"Jones C (2010) Software engineering best practices. McGraw-Hill, New York"},{"key":"9230_CR27","doi-asserted-by":"crossref","unstructured":"Kang KC, Cohen S, Hess J, Novak W, Peterson A (1990) Feature-oriented domain analysis (FODA) feasibility study Pittsburgh, Pennsylvania, USA, Carnegie Mellon University, Software Engineering Institute","DOI":"10.21236\/ADA235785"},{"key":"9230_CR28","doi-asserted-by":"crossref","unstructured":"Kawaguchi S, Garg PK, Matsushita M, Inoue K (2003) Automatic categorization algorithm for evolvable software archive. 6th International Workshop on Principles of Software Evolution (IWPSE\u201903), pp 195\u2013200","DOI":"10.1109\/IWPSE.2003.1231227"},{"issue":"7","key":"9230_CR29","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1016\/j.jss.2005.06.044","volume":"79","author":"S Kawaguchi","year":"2006","unstructured":"Kawaguchi S, Garg PK, Matsushita M, Inoue K (2006) MUDABlue: an automatic categorization system for open source repositories. J Syst Software 79(7):939\u2013953","journal-title":"J Syst Software"},{"key":"9230_CR30","doi-asserted-by":"crossref","unstructured":"Kelly MB, Alexander JS, Adams B, Hassan AE (2011) Recovering a balanced overview of topics in a software domain. 11th IEEE International Working Conference on Source Code Analysis and Manipulation (SCAM\u201911), Williamsburg, VA, USA, to appear","DOI":"10.1109\/SCAM.2011.23"},{"issue":"1","key":"9230_CR31","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1023\/A:1012491419635","volume":"46","author":"E Leopold","year":"2002","unstructured":"Leopold E, Kindermann J (2002) Text categorization with support vector machines. How to represent texts in input space? Mach Learn 46(1):423\u2013444","journal-title":"Mach Learn"},{"key":"9230_CR32","unstructured":"Lorena AC, De Carvalho ACPLF (2004) Comparing techniques for multiclass classification using binary SVM predictors. Third Mexican International Conference on Artificial Intelligence (MICAI\u201904), Mexico City, Mexico, Springer, pp 272\u2013281"},{"key":"9230_CR33","doi-asserted-by":"crossref","unstructured":"McMillan C, Grechanik M, Poshyvanyk D, Xie Q, Fu C (2011) Portfolio: finding relevant functions and their usages. 33rd IEEE\/ACM International Conference on Software Engineering (ICSE\u201911), Honolulu, Hawaii, USA, pp 111\u2013120","DOI":"10.1145\/1985793.1985809"},{"key":"9230_CR34","doi-asserted-by":"crossref","unstructured":"McMillan C, Linares-V\u00e1squez M, Poshyvanyk D, Grechanik M (2011) Categorizing software applications for maintenance. 27th IEEE International Conference on Software Maintenance (ICSM\u201911), Williamsburg, Virginia, USA, pp 343\u2013352","DOI":"10.1109\/ICSM.2011.6080801"},{"key":"9230_CR35","doi-asserted-by":"crossref","unstructured":"Menzies T, Marcus A (2008) Automated severity assessment of software defect reports. IEEE International Conference on Software Maintenance (ICSM\u201908), Beijing, China, pp 346\u2013355","DOI":"10.1109\/ICSM.2008.4658083"},{"key":"9230_CR36","doi-asserted-by":"crossref","unstructured":"Poshyvanyk D, Grechanik M (2009) Creating and evolving software by searching, selecting and synthesizing relevant source code. 31st IEEE\/ACM International Conference on Software Engineering (ICSE\u201909), Vancouver, British Columbia, Canada, pp 283\u2013286","DOI":"10.1109\/ICSE-COMPANION.2009.5071002"},{"issue":"2","key":"9230_CR37","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1145\/382296.382703","volume":"15","author":"R Prieto-Diaz","year":"1990","unstructured":"Prieto-Diaz R (1990) Domain analysis: an introduction. ACM SIGSOFT Software Eng Notes 15(2):47\u201354","journal-title":"ACM SIGSOFT Software Eng Notes"},{"key":"9230_CR38","doi-asserted-by":"crossref","unstructured":"Ratiu D, Deissenboeck F (2006) How programs represent reality (and How They Don\u2019t). 13th Working Conference on Reverse Engineering (WCRE\u201906), pp 83\u201392","DOI":"10.1109\/WCRE.2006.32"},{"key":"9230_CR39","doi-asserted-by":"crossref","unstructured":"Ratiu D, Deissenboeck F (2007) From reality to programs and (not quite) back again. 15th IEEE International Conference on Program Comprehension (ICPC\u201907), Banff, Alberta, Canada, pp 91\u2013102","DOI":"10.1109\/ICPC.2007.22"},{"issue":"5","key":"9230_CR40","doi-asserted-by":"crossref","first-page":"266","DOI":"10.3844\/jcssp.2007.266.273","volume":"3","author":"PS Sandhu","year":"2007","unstructured":"Sandhu PS, Singh J, Singh H (2007) Approaches for categorization of reusable software components. J Comput Sci 3(5):266\u2013273","journal-title":"J Comput Sci"},{"key":"9230_CR41","doi-asserted-by":"crossref","unstructured":"Schuler D, Dallmeir V, Lindig C (2007) A dynamic birthmark for java. Twenty-second IEEE\/ACM International Conference on Automated software Engineering (ASE 2007), Atlanta, Georgia, USA, pp 274\u2013283","DOI":"10.1145\/1321631.1321672"},{"key":"9230_CR42","doi-asserted-by":"crossref","unstructured":"Sebastiani, F. (2002) Machine learning in automated text categorization. ACM Comput Surv 34(1):1\u201347","DOI":"10.1145\/505282.505283"},{"key":"9230_CR43","doi-asserted-by":"crossref","unstructured":"Sim SE, Umarji M, Ratanotayanon S, Lopes CV (2011) How well do search engines support code retrieval on the web? ACM Trans Software Eng Meth (TOSEM) 21(1)","DOI":"10.1145\/2063239.2063243"},{"key":"9230_CR44","doi-asserted-by":"crossref","unstructured":"Tian K, Revelle M, Poshyvanyk D (2009) Using latent Dirichlet allocation for automatic categorization of software. 6th IEEE Working Conference on Mining Software Repositories (MSR\u201909), Vancouver, British Columbia, Canada, pp 163\u2013166","DOI":"10.1109\/MSR.2009.5069496"},{"key":"9230_CR45","doi-asserted-by":"crossref","unstructured":"Ugurel S, Krovetz R, Giles CL (2002) What\u2019s the code ? Automatic classification of source code archives. Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2002), Edmontong, Alberta, Canada, pp 632\u2013638","DOI":"10.1145\/775047.775141"},{"key":"9230_CR46","doi-asserted-by":"crossref","unstructured":"\u00dajh\u00e1zi B, Ferenc R, Poshyvanyk D, Gyim\u00f3thy T (2010) New conceptual coupling and cohesion metrics for object-oriented systems. 10th IEEE International Working Conference on Source Code Analysis and Manipulation (SCAM\u201910), Timi\u015foara, Romania, pp 33\u201342","DOI":"10.1109\/SCAM.2010.14"},{"key":"9230_CR47","doi-asserted-by":"crossref","unstructured":"Weiss C, Premraj R, Zimmermann T, Zeller A (2007) How long will it take to fix this bug? 4th IEEE International Workshop on Mining Software Repositories (MSR\u201907), Minneapolis, MN, pp 1\u20138","DOI":"10.1109\/MSR.2007.13"},{"key":"9230_CR48","unstructured":"Zhang M-L, Zhou Z-H (2005) A k-nearest neighbor based algorithm for multi-label classification. IEEE International Conference on Granular Computing, Beijing, China, pp 718\u2013721"},{"issue":"10","key":"9230_CR49","doi-asserted-by":"crossref","first-page":"1338","DOI":"10.1109\/TKDE.2006.162","volume":"18","author":"M-L Zhang","year":"2006","unstructured":"Zhang M-L, Zhou Z-H (2006) Multi-label neural networks with applications to functional genomics and text categorization. IEEE Trans Knowl Data Eng 18(10):1338\u20131351","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"9230_CR50","unstructured":"Zimmermann T, Nagappan N, Gall H, Giger E, Murphy B (2009) Cross-project defect prediction: a large scale experiment on data vs. domain vs. process. ESEC\/SIGSOFT FSE 2009, Amsterdam, The Netherlands, pp 91\u2013100"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-012-9230-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10664-012-9230-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-012-9230-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,30]],"date-time":"2022-01-30T03:23:50Z","timestamp":1643513030000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10664-012-9230-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,10,10]]},"references-count":50,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,6]]}},"alternative-id":["9230"],"URL":"https:\/\/doi.org\/10.1007\/s10664-012-9230-z","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,10,10]]}}}