{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T23:38:15Z","timestamp":1769729895272,"version":"3.49.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,7,28]],"date-time":"2012-07-28T00:00:00Z","timestamp":1343433600000},"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":[[2014,2]]},"DOI":"10.1007\/s10664-012-9219-7","type":"journal-article","created":{"date-parts":[[2012,7,28]],"date-time":"2012-07-28T03:12:24Z","timestamp":1343445144000},"page":"182-212","source":"Crossref","is-referenced-by-count":121,"title":["Static test case prioritization using topic models"],"prefix":"10.1007","volume":"19","author":[{"given":"Stephen W.","family":"Thomas","sequence":"first","affiliation":[]},{"given":"Hadi","family":"Hemmati","sequence":"additional","affiliation":[]},{"given":"Ahmed E.","family":"Hassan","sequence":"additional","affiliation":[]},{"given":"Dorothea","family":"Blostein","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,7,28]]},"reference":[{"issue":"6","key":"9219_CR1","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1109\/TSE.2009.52","volume":"36","author":"S Ali","year":"2009","unstructured":"Ali S, Briand LC, Hemmati H, Panesar-Walawege RK (2009) A systematic review of the application and empirical investigation of search-based test case generation. IEEE Trans Softw Eng 36(6):742\u2013762","journal-title":"IEEE Trans Softw Eng"},{"key":"9219_CR2","unstructured":"Apache Foundation (2012a) Ant. http:\/\/ant.apache.org . Accessed 17 July 2012"},{"key":"9219_CR3","unstructured":"Apache Foundation (2012b) Apache. http:\/\/www.apache.org . Accessed 17 July 2012"},{"key":"9219_CR4","unstructured":"Apache Foundation (2012c) Derby. http:\/\/db.apache.org\/derby . Accessed 17 July 2012"},{"key":"9219_CR5","doi-asserted-by":"crossref","unstructured":"Arcuri A, Briand L (2011) A practical guide for using statistical tests to assess randomized algorithms in software engineering. In: Proceedings of the 33rd international conference on software engineering, pp 1\u201310","DOI":"10.1145\/1985793.1985795"},{"key":"9219_CR6","doi-asserted-by":"crossref","unstructured":"Asuncion HU, Asuncion AU, Taylor RN (2010) Software traceability with topic modeling. In: Proceedings of the 32nd international conference on software engineering, pp 95\u2013104","DOI":"10.1145\/1806799.1806817"},{"issue":"10","key":"9219_CR7","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1145\/1449955.1449807","volume":"43","author":"PF Baldi","year":"2008","unstructured":"Baldi PF, Lopes CV, Linstead EJ, Bajracharya SK (2008) A theory of aspects as latent topics. ACM SIGPLAN Not 43(10):543\u2013562","journal-title":"ACM SIGPLAN Not"},{"key":"9219_CR8","first-page":"71","volume-title":"Text mining: classification, clustering, and applications","author":"DM Blei","year":"2009","unstructured":"Blei DM, Lafferty JD (2009) Topic models. In: Text mining: classification, clustering, and applications. Chapman & Hall, London, UK, pp\u00a071\u201394"},{"key":"9219_CR9","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993\u20131022","journal-title":"J Mach Learn Res"},{"key":"9219_CR10","unstructured":"Chang J (2011) lda: Collapsed Gibbs sampling methods for topic models. http:\/\/cran.r-project.org\/web\/packages\/lda . Accessed 17 July 2012"},{"key":"9219_CR11","doi-asserted-by":"crossref","unstructured":"Chen S, Chen Z, Zhao Z, Xu B, Feng Y (2011) Using semi-supervised clustering to improve regression test selection techniques. In: Proceedings of the 4th international conference on software testing, verification and validation, pp\u00a01\u201310","DOI":"10.1109\/ICST.2011.38"},{"issue":"3","key":"9219_CR12","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.scico.2006.04.002","volume":"61","author":"JR Cordy","year":"2006","unstructured":"Cordy JR (2006) The TXL source transformation language. Science of Computer Programming 61(3):190\u2013210","journal-title":"Science of Computer Programming"},{"issue":"4","key":"9219_CR13","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1007\/s10664-005-3861-2","volume":"10","author":"H Do","year":"2005","unstructured":"Do H, Elbaum S, Rothermel G (2005) Supporting controlled experimentation with testing techniques: an infrastructure and its potential impact. Empir Software Eng 10(4):405\u2013435","journal-title":"Empir Software Eng"},{"issue":"2","key":"9219_CR14","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1109\/32.988497","volume":"28","author":"S Elbaum","year":"2002","unstructured":"Elbaum S, Malishevsky A, Rothermel G (2002) Test case prioritization: a family of empirical studies. IEEE Trans Softw Eng 28(2):159\u2013182","journal-title":"IEEE Trans Softw Eng"},{"key":"9219_CR15","doi-asserted-by":"crossref","unstructured":"Feldt R, Torkar R, Gorschek T, Afzal W (2008) Searching for cognitively diverse tests: towards universal test diversity metrics. In: Proceedings of the international conference on software testing verification and validation workshop, pp\u00a0178\u2013186","DOI":"10.1109\/ICSTW.2008.36"},{"key":"9219_CR16","doi-asserted-by":"crossref","unstructured":"Gethers M, Poshyvanyk D (2010) Using relational topic models to capture coupling among classes in object-oriented software systems. In: Proceedings of the 26th international conference on software maintenance, pp 1\u201310","DOI":"10.1109\/ICSM.2010.5609687"},{"key":"9219_CR17","doi-asserted-by":"crossref","unstructured":"Gethers M, Oliveto R, Poshyvanyk D, Lucia A (2011) On integrating orthogonal information retrieval methods to improve traceability recovery. In: Proceedings of the 27th international conference on software maintenance, pp\u00a0133\u2013142","DOI":"10.1109\/ICSM.2011.6080780"},{"key":"9219_CR18","doi-asserted-by":"crossref","unstructured":"Grant S, Cordy JR (2010) Estimating the optimal number of latent concepts in source code analysis. In: Proceedings of the 10th international working conference on source code analysis and manipulation, pp\u00a065\u201374","DOI":"10.1109\/SCAM.2010.22"},{"key":"9219_CR19","doi-asserted-by":"crossref","first-page":"5228","DOI":"10.1073\/pnas.0307752101","volume":"101","author":"TL Griffiths","year":"2004","unstructured":"Griffiths TL, Steyvers M (2004) Finding scientific topics. Proc Natl Acad Sci 101:5228\u20135235","journal-title":"Proc Natl Acad Sci"},{"issue":"2","key":"9219_CR20","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1037\/0033-295X.114.2.211","volume":"114","author":"TL Griffiths","year":"2007","unstructured":"Griffiths TL, Steyvers M, Tenenbaum JB (2007) Topics in semantic representation. Psychol Rev 114(2):211\u2013244","journal-title":"Psychol Rev"},{"key":"9219_CR21","doi-asserted-by":"crossref","unstructured":"Hemmati H, Arcuri A, Briand L (2010a) Reducing the cost of model-based testing through test case diversity. In: Proceedings of the 22nd international conference on testing software and systems, pp\u00a063\u201378","DOI":"10.1007\/978-3-642-16573-3_6"},{"key":"9219_CR22","doi-asserted-by":"crossref","unstructured":"Hemmati H, Briand L, Arcuri A, Ali S (2010b) An enhanced test case selection approach for model-based testing: an industrial case study. In: Proceedings of the 18th international symposium on foundations of software engineering, pp\u00a0267\u2013276","DOI":"10.1145\/1882291.1882331"},{"key":"9219_CR23","doi-asserted-by":"crossref","unstructured":"Hemmati H, Arcuri A, Briand L (2011) Empirical investigation of the effects of test suite properties on similarity-based test case selection. In: Proceedings of the 4th international conference on software testing, verification and validation, pp\u00a0327\u2013336","DOI":"10.1109\/ICST.2011.12"},{"key":"9219_CR24","doi-asserted-by":"crossref","unstructured":"Hemmati H, Briand L, Arcuri A (2013) Achieving scalable model-based testing through test case diversity. ACM Trans Softw Eng Methodol 22(1) (upcoming)","DOI":"10.1145\/2430536.2430540"},{"key":"9219_CR25","doi-asserted-by":"crossref","unstructured":"Hofmann T (1999) Probabilistic Latent Semantic Indexing. In: Proceedings of the 22nd international conference on research and development in information retrieval, pp\u00a050\u201357","DOI":"10.1145\/312624.312649"},{"issue":"3","key":"9219_CR26","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1080\/10618600.1996.10474713","volume":"5","author":"R Ihaka","year":"1996","unstructured":"Ihaka R, Gentleman R (1996) R: A language for data analysis and graphics. J Comput Graph Stat 5(3):299\u2013314","journal-title":"J Comput Graph Stat"},{"key":"9219_CR27","doi-asserted-by":"crossref","unstructured":"Jiang B, Zhang Z, Chan W, Tse T (2009) Adaptive random test case prioritization. In: Proceedings of the 24th international conference on automated software engineering, pp 233\u2013244","DOI":"10.1109\/ASE.2009.77"},{"issue":"3","key":"9219_CR28","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1109\/TSE.2003.1183927","volume":"29","author":"J Jones","year":"2003","unstructured":"Jones J, Harrold M (2003) Test-suite reduction and prioritization for modified condition\/decision coverage. IEEE Trans Softw Eng 29(3):195\u2013209","journal-title":"IEEE Trans Softw Eng"},{"key":"9219_CR29","doi-asserted-by":"crossref","unstructured":"Korel B, Koutsogiannakis G, Tahat L (2007) Model-based test prioritization heuristic methods and their evaluation. In: Proceedings of the 3rd international workshop on advances in model-based testing, pp\u00a034\u201343","DOI":"10.1145\/1291535.1291539"},{"issue":"3","key":"9219_CR30","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.infsof.2006.10.017","volume":"49","author":"A Kuhn","year":"2007","unstructured":"Kuhn A, Ducasse S, Girba T (2007) Semantic clustering: identifying topics in source code. Inf Softw Technol 49(3):230\u2013243","journal-title":"Inf Softw Technol"},{"issue":"1","key":"9219_CR31","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S Kullback","year":"1951","unstructured":"Kullback S, Leibler R (1951) On information and sufficiency. Ann Math Stat 22(1):79\u201386","journal-title":"Ann Math Stat"},{"key":"9219_CR32","unstructured":"Kumar A (2010) Development at the speed and scale of google. Presented at QCon 2010, San Francisco, CA, USA"},{"key":"9219_CR33","doi-asserted-by":"crossref","unstructured":"Ledru Y, Petrenko A, Boroday S (2009) Using string distances for test case prioritisation. In: Proceedings of the 24th international conference on automated software engineering, pp\u00a0510\u2013514","DOI":"10.1109\/ASE.2009.23"},{"issue":"1","key":"9219_CR34","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/s10515-011-0093-0","volume":"19","author":"Y Ledru","year":"2011","unstructured":"Ledru Y, Petrenko A, Boroday S, Mandran N (2011) Prioritizing test cases with string distances. Autom Softw Eng 19(1):65\u201395","journal-title":"Autom Softw Eng"},{"key":"9219_CR35","doi-asserted-by":"crossref","unstructured":"Leon D, Podgurski A (2003) A comparison of coverage-based and distribution-based techniques for filtering and prioritizing test cases. In: Proceedings of the international symposium on software reliability engineering, pp 442\u2013456","DOI":"10.1109\/ISSRE.2003.1251065"},{"key":"9219_CR36","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 the 7th international conference on machine learning and applications, pp\u00a0813\u2013818","DOI":"10.1109\/ICMLA.2008.47"},{"key":"9219_CR37","doi-asserted-by":"crossref","unstructured":"Liu Y, Poshyvanyk D, Ferenc R, Gyimothy T, Chrisochoides N (2009) Modeling class cohesion as mixtures of latent topics. In: Proceedings of the 25th international conference on software maintenance, pp\u00a0233\u2013242","DOI":"10.1109\/ICSM.2009.5306318"},{"issue":"9","key":"9219_CR38","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1016\/j.infsof.2010.04.002","volume":"52","author":"SK Lukins","year":"2010","unstructured":"Lukins SK, Kraft NA, Etzkorn LH (2010) Bug localization using latent Dirichlet allocation. Inf Softw Technol 52(9):972\u2013990","journal-title":"Inf Softw Technol"},{"key":"9219_CR39","doi-asserted-by":"crossref","unstructured":"Marcus A, Sergeyev A, Rajlich V, Maletic JI (2004) An information retrieval approach to concept location in source code. In: Proceedings of the 11th working conference on reverse engineering, pp 214\u2013223","DOI":"10.1109\/WCRE.2004.10"},{"key":"9219_CR40","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 conference on India software engineering conference, pp 113\u2013120","DOI":"10.1145\/1342211.1342234"},{"issue":"7","key":"9219_CR41","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1109\/TSE.2007.1020","volume":"33","author":"W Masri","year":"2007","unstructured":"Masri W, Podgurski A, Leon D (2007) An empirical study of test case filtering techniques based on exercising information flows. IEEE Trans Softw Eng 33(7):454\u2013477","journal-title":"IEEE Trans Softw Eng"},{"issue":"1","key":"9219_CR42","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1109\/TSE.2007.70756","volume":"34","author":"S McMaster","year":"2006","unstructured":"McMaster S, Memon A (2006) Call stack coverage for GUI test-suite reduction. IEEE Trans Softw Eng 34(1):99\u2013115","journal-title":"IEEE Trans Softw Eng"},{"key":"9219_CR43","doi-asserted-by":"crossref","unstructured":"Mei H, Hao D, Zhang L, Zhang L, Zhou J, Rothermel G (2011) A static approach to prioritizing JUnit test cases. IEEE Trans Softw Eng. doi: 10.1109\/TSE.2011.106","DOI":"10.1109\/TSE.2011.106"},{"key":"9219_CR44","doi-asserted-by":"crossref","unstructured":"Oliveto R, Gethers M, Bavota G, Poshyvanyk D, De\u00a0Lucia A (2011) Identifying method friendships to remove the feature envy bad smell. In: Proceeding of the 33rd international conference on software engineering (NIER Track), pp\u00a0820\u2013823","DOI":"10.1145\/1985793.1985913"},{"key":"9219_CR45","doi-asserted-by":"crossref","unstructured":"Porteous I, Newman D, Ihler A, Asuncion A, Smyth P, Welling M (2008) Fast collapsed Gibbs sampling for latent Dirichlet allocation. In: Proceeding of the 14th international conference on knowledge discovery and data mining, pp 569\u2013577","DOI":"10.1145\/1401890.1401960"},{"key":"9219_CR46","doi-asserted-by":"crossref","unstructured":"Ramanathan MK, Koyuturk M, Grama A, Jagannathan S (2008) PHALANX: a graph-theoretic framework for test case prioritization. In: Proceedings of the 23rd ACM symposium on applied computing, pp\u00a0667\u2013673","DOI":"10.1145\/1363686.1363848"},{"issue":"10","key":"9219_CR47","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1109\/32.962562","volume":"27","author":"G Rothermel","year":"2001","unstructured":"Rothermel G, Untch R, Chu C, Harrold M (2001) Prioritizing test cases for regression testing. IEEE Trans Softw Eng 27(10):929\u2013948","journal-title":"IEEE Trans Softw Eng"},{"issue":"4","key":"9219_CR48","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1002\/stvr.256","volume":"12","author":"G Rothermel","year":"2002","unstructured":"Rothermel G, Harrold M, Von\u00a0Ronne J, Hong C (2002) Empirical studies of test-suite reduction. Softw Test Verif Reliab 12(4):219\u2013249","journal-title":"Softw Test Verif Reliab"},{"key":"9219_CR49","doi-asserted-by":"crossref","unstructured":"Sampath S, Bryce RC, Viswanath G, Kandimalla V, Koru AG (2008) Prioritizing user-session-based test cases for web applications testing. In: Proceedings of the 1st international conference on software testing, verification, and validation, pp\u00a0141\u2013150","DOI":"10.1109\/ICST.2008.42"},{"key":"9219_CR50","unstructured":"Savage T, Dit B, Gethers M, Poshyvanyk D (2010) TopicXP: Exploring topics in source code using latent Dirichlet allocation. In: Proceedings of the 26th international conference on software maintenance, pp\u00a01\u20136"},{"key":"9219_CR51","doi-asserted-by":"crossref","unstructured":"Simao A, de\u00a0Mello RF, Senger LJ (2006) A technique to reduce the test case suites for regression testing based on a self-organizing neural network architecture. In: Proceedings of the 30th annual international computer software and applications conference, pp\u00a093\u201396","DOI":"10.1109\/COMPSAC.2006.103"},{"key":"9219_CR52","unstructured":"Thomas SW (2012a) http:\/\/research.cs.queensu.ca\/~sthomas\/ . Accessed 17 July 2012"},{"key":"9219_CR53","doi-asserted-by":"crossref","unstructured":"Thomas SW (2012b) Mining software repositories with topic models. Tech. Rep. 2012-586, School of Computing, Queen\u2019s University","DOI":"10.1145\/1985793.1986020"},{"key":"9219_CR54","doi-asserted-by":"crossref","unstructured":"Thomas SW, Adams B, Hassan AE, 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, pp\u00a055\u201364","DOI":"10.1109\/SCAM.2010.13"},{"key":"9219_CR55","doi-asserted-by":"crossref","unstructured":"Thomas SW, Adams B, Hassan AE, 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"},{"issue":"2","key":"9219_CR56","first-page":"101","volume":"25","author":"A Vargha","year":"2000","unstructured":"Vargha A, Delaney HD (2000) A critique and improvement of the CL common language effect size statistics of McGraw and Wong. J Educ Behav Stat 25(2):101\u2013132","journal-title":"J Educ Behav Stat"},{"key":"9219_CR57","doi-asserted-by":"crossref","unstructured":"Wallach HM, Murray I, Salakhutdinov R, Mimno D (2009) Evaluation methods for topic models. In: Proceedings of the 26th international conference on machine learning, pp 1105\u20131112","DOI":"10.1145\/1553374.1553515"},{"key":"9219_CR58","doi-asserted-by":"crossref","unstructured":"Wang S, Lo D, Xing Z, Jiang L (2011) Concern localization using information retrieval: an empirical study on Linux kernel. In: Proceedings of the 18th working conference on reverse engineering, pp 92\u201396","DOI":"10.1109\/WCRE.2011.72"},{"key":"9219_CR59","doi-asserted-by":"crossref","unstructured":"Wong W, Horgan J, London S, Agrawal H (1997) A study of effective regression testing in practice. In: Proceedings of the 8th international symposium on software reliability engineering, pp\u00a0264\u2013274","DOI":"10.1109\/ISSRE.1997.630875"},{"issue":"2","key":"9219_CR60","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1002\/stv.430","volume":"22","author":"S Yoo","year":"2010","unstructured":"Yoo S, Harman M (2010) Regression testing minimization, selection and prioritization: a survey. Softw Test Verif Reliab 22(2):67\u2013120","journal-title":"Softw Test Verif Reliab"},{"key":"9219_CR61","doi-asserted-by":"crossref","unstructured":"Yoo S, Harman M, Tonella P, Susi A (2009) Clustering test cases to achieve effective and scalable prioritisation incorporating expert knowledge. In: Proceedings of the 18th international symposium on software testing and analysis, pp\u00a0201\u2013212","DOI":"10.1145\/1572272.1572296"},{"key":"9219_CR62","doi-asserted-by":"crossref","unstructured":"Zhang L, Zhou J, Hao D, Zhang L, Mei H (2009) Prioritizing JUnit test cases in absence of coverage information. In: Proceedings of the 25th international conference on software maintenance, pp\u00a019\u201328","DOI":"10.1109\/ICSM.2009.5306350"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-012-9219-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10664-012-9219-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-012-9219-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T15:11:51Z","timestamp":1714230711000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10664-012-9219-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,7,28]]},"references-count":62,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,2]]}},"alternative-id":["9219"],"URL":"https:\/\/doi.org\/10.1007\/s10664-012-9219-7","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,7,28]]}}}