{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T01:09:00Z","timestamp":1775005740978,"version":"3.50.1"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s10664-023-10292-0","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T08:02:28Z","timestamp":1682409748000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Ranking code clones to support maintenance activities"],"prefix":"10.1007","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5478-059X","authenticated-orcid":false,"given":"Osama","family":"Ehsan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Foutse","family":"Khomh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,25]]},"reference":[{"key":"10292_CR1","doi-asserted-by":"crossref","unstructured":"Asaduzzaman M, Roy CK, Schneider KA (2011) Viscad: flexible code clone analysis support for nicad. In: Proceedings of the 5th international workshop on software clones, pp 77\u201378","DOI":"10.1145\/1985404.1985425"},{"key":"10292_CR2","doi-asserted-by":"crossref","unstructured":"Avelino G, Constantinou E, Valente MT, Serebrenik A (2019) On the abandonment and survival of open source projects: an empirical investigation. In: 2019 ACM\/IEEE international symposium on empirical software engineering and measurement (ESEM). IEEE, pp 1\u201312","DOI":"10.1109\/ESEM.2019.8870181"},{"issue":"4","key":"10292_CR3","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1007\/s11219-017-9375-5","volume":"26","author":"L Barbour","year":"2018","unstructured":"Barbour L, An L, Khomh F, Zou Y, Wang S (2018) An investigation of the fault-proneness of clone evolutionary patterns. Softw Qual J 26 (4):1187\u20131222","journal-title":"Softw Qual J"},{"key":"10292_CR4","doi-asserted-by":"crossref","unstructured":"Barbour L, Khomh F, Zou Y (2011) Late propagation in software clones. In: 2011 27Th IEEE international conference on software maintenance (ICSM). IEEE, pp 273\u2013282","DOI":"10.1109\/ICSM.2011.6080794"},{"key":"10292_CR5","unstructured":"Bates D, Maechler M, Bolker B, Walker S, Christensen RHB, Singmann H, Dai B, Scheipl F, Grothendieck G (2011) Package \u2018lme4\u2019"},{"key":"10292_CR6","unstructured":"Berg K, Svensson O (2018) Szz unleashed: bug prediction on the jenkins core repository (open source implementations of bug prediction tools on commit level). LU-CS-EX:2018\u201304"},{"key":"10292_CR7","unstructured":"CS C (2020) whatthepatch - python\u2019s third party patch parsing library. Online (Accessed 17th August 2020)"},{"key":"10292_CR8","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp 785\u2013794","DOI":"10.1145\/2939672.2939785"},{"key":"10292_CR9","doi-asserted-by":"crossref","unstructured":"Cohen J, Cohen P, West SG, Aiken LS (2013) Applied multiple regression\/correlation analysis for the behavioral sciences. Routledge","DOI":"10.4324\/9780203774441"},{"key":"10292_CR10","doi-asserted-by":"crossref","unstructured":"Cordy JR, Roy CK (2011) The nicad clone detector. In: 2011 IEEE 19Th international conference on program comprehension, pp 219\u2013220. IEEE","DOI":"10.1109\/ICPC.2011.26"},{"issue":"7","key":"10292_CR11","doi-asserted-by":"publisher","first-page":"149","DOI":"10.3390\/info9070149","volume":"9","author":"SS Dhaliwal","year":"2018","unstructured":"Dhaliwal SS, Nahid AA, Abbas R (2018) Effective intrusion detection system using xgboost. Information 9(7):149","journal-title":"Information"},{"issue":"1","key":"10292_CR12","first-page":"1","volume":"30","author":"O Ehsan","year":"2020","unstructured":"Ehsan O, Hassan S, Mezouar ME, Zou Y (2020) An empirical study of developer discussions in the gitter platform. ACM Trans Soft Eng Method (TOSEM) 30(1):1\u201339","journal-title":"ACM Trans Soft Eng Method (TOSEM)"},{"key":"10292_CR13","doi-asserted-by":"crossref","unstructured":"Fischer M, Pinzger M, Gall H (2003) Populating a release history database from version control and bug tracking systems. In: International conference on software maintenance, 2003. ICSM 2003. Proceedings. IEEE, pp 23\u201332","DOI":"10.1109\/ICSM.2003.1235403"},{"key":"10292_CR14","unstructured":"Fowler M (2018) Refactoring: improving the design of existing code. Addison-Wesley professional"},{"key":"10292_CR15","unstructured":"Fox J, Weisberg S, Adler D, Bates D, Baud-Bovy G, Ellison S, Firth D, Friendly M, Gorjanc G, Graves S et al (2012) Package car. Vienna: R foundation for statistical computing"},{"key":"10292_CR16","doi-asserted-by":"crossref","unstructured":"Garg R, Tekchandani R (2014) An approach to rank code clones for efficient clone management. In: 2014 international conference on advances in electronics computers and communications. IEEE, pp 1\u20135","DOI":"10.1109\/ICAECC.2014.7002385"},{"key":"10292_CR17","doi-asserted-by":"crossref","unstructured":"G\u00f6de N, Koschke R (2009) Incremental clone detection. In: 2009 13Th European conference on software maintenance and reengineering. IEEE, pp 219\u2013228","DOI":"10.1109\/CSMR.2009.20"},{"key":"10292_CR18","doi-asserted-by":"crossref","unstructured":"Goutte C, Gaussier E (2005) A probabilistic interpretation of precision, recall and f-score, with implication for evaluation. In: European conference on information retrieval. Springer, pp 345\u2013359","DOI":"10.1007\/978-3-540-31865-1_25"},{"issue":"1","key":"10292_CR19","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","volume":"143","author":"JA Hanley","year":"1982","unstructured":"Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1):29\u201336","journal-title":"Radiology"},{"issue":"3","key":"10292_CR20","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1007\/s10664-017-9538-9","volume":"23","author":"S Hassan","year":"2018","unstructured":"Hassan S, Tantithamthavorn C, Bezemer CP, Hassan AE (2018) Studying the dialogue between users and developers of free apps in the google play store. Empir Softw Eng 23(3):1275\u20131312","journal-title":"Empir Softw Eng"},{"key":"10292_CR21","unstructured":"Herbold S, Trautsch A, Trautsch F, Ledel B (2019) Issues with szz: an empirical assessment of the state of practice of defect prediction data collection. arXiv:1911.08938"},{"key":"10292_CR22","unstructured":"Jr FEH (2019) Harrell miscellaneous. https:\/\/cran.r-project.org\/web\/packages\/Hmisc\/Hmisc.pdf, (Last accessed: August 2019)"},{"key":"10292_CR23","doi-asserted-by":"crossref","unstructured":"Juergens E, Deissenboeck F, Hummel B, Wagner S (2009) Do code clones matter?. In: 2009 IEEE 31St international conference on software engineering. IEEE, pp 485\u2013495","DOI":"10.1109\/ICSE.2009.5070547"},{"issue":"7","key":"10292_CR24","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1109\/TSE.2002.1019480","volume":"28","author":"T Kamiya","year":"2002","unstructured":"Kamiya T, Kusumoto S, Inoue K (2002) Ccfinder: a multilinguistic token-based code clone detection system for large scale source code. IEEE Trans Softw Eng 28(7):654\u2013670","journal-title":"IEEE Trans Softw Eng"},{"issue":"6","key":"10292_CR25","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1007\/s10664-008-9076-6","volume":"13","author":"CJ Kapser","year":"2008","unstructured":"Kapser CJ, Godfrey MW (2008) cloning considered harmful considered harmful: patterns of cloning in software. Empir Softw Eng 13(6):645\u2013692","journal-title":"Empir Softw Eng"},{"key":"10292_CR26","unstructured":"Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu TY (2017) Lightgbm: a highly efficient gradient boosting decision tree. In: Advances in neural information processing systems, pp 3146\u20133154"},{"key":"10292_CR27","doi-asserted-by":"crossref","unstructured":"Kouters E, Vasilescu B, Serebrenik A, Van Den Brand MG (2012) Who\u2019s who in gnome: Using lsa to merge software repository identities. In: 2012 28Th IEEE international conference on software maintenance (ICSM). IEEE, pp 592\u2013595","DOI":"10.1109\/ICSM.2012.6405329"},{"issue":"1","key":"10292_CR28","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/0165-1765(86)90117-5","volume":"21","author":"F Lafontaine","year":"1986","unstructured":"Lafontaine F, White KJ (1986) Obtaining any wald statistic you want. Econ Lett 21(1):35\u201340","journal-title":"Econ Lett"},{"issue":"3","key":"10292_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-02155-8","volume":"7","author":"H Li","year":"2014","unstructured":"Li H (2014) Learning to rank for information retrieval and natural language processing. Synthesis Lectures Human Language Technol 7(3):1\u2013121","journal-title":"Synthesis Lectures Human Language Technol"},{"key":"10292_CR30","doi-asserted-by":"crossref","unstructured":"Li J, Ernst MD (2012) Cbcd: cloned buggy code detector. In: 2012 34Th international conference on software engineering (ICSE). IEEE, pp 310\u2013320","DOI":"10.1109\/ICSE.2012.6227183"},{"key":"10292_CR31","doi-asserted-by":"crossref","unstructured":"Mondal M, Roy CK, Schneider KA (2017) Bug propagation through code cloning: an empirical study. In: 2017 IEEE international conference on software maintenance and evolution (ICSME). IEEE, pp 227\u2013237","DOI":"10.1109\/ICSME.2017.33"},{"key":"10292_CR32","doi-asserted-by":"crossref","unstructured":"Mondal M, Roy CK, Schneider KA (2017) Does cloned code increase maintenance effort?. In: 2017 IEEE 11Th international workshop on software clones (IWSC). IEEE, pp 1\u20137","DOI":"10.1109\/IWSC.2017.7880507"},{"key":"10292_CR33","doi-asserted-by":"crossref","unstructured":"Nakakoji K, Yamamoto Y, Nishinaka Y, Kishida K, Ye Y (2002) Evolution patterns of open-source software systems and communities. In: Proceedings of the international workshop on Principles of software evolution, pp 76\u201385","DOI":"10.1145\/512035.512055"},{"key":"10292_CR34","doi-asserted-by":"crossref","unstructured":"Pan Q, Tang W, Yao S (2020) The application of lightgbm in microsoft malware detection. In: Journal of physics: conference series. IOP Publishing, vol 1684, p 012041","DOI":"10.1088\/1742-6596\/1684\/1\/012041"},{"key":"10292_CR35","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"10292_CR36","doi-asserted-by":"crossref","unstructured":"Roy CK (2009) Detection and analysis of near-miss software clones. In: 2009 IEEE international conference on software maintenance. IEEE, pp 447\u2013450","DOI":"10.1109\/ICSM.2009.5306301"},{"key":"10292_CR37","doi-asserted-by":"crossref","unstructured":"Saha RK, Roy CK, Schneider KA (2011) An automatic framework for extracting and classifying near-miss clone genealogies. In: 2011 27Th IEEE international conference on software maintenance (ICSM). IEEE, pp 293\u2013302","DOI":"10.1109\/ICSM.2011.6080796"},{"key":"10292_CR38","doi-asserted-by":"crossref","unstructured":"Saha RK, Roy CK, Schneider KA, Perry DE (2013) Understanding the evolution of type-3 clones: an exploratory study. In: Proceedings of the 10th working conference on mining software repositories. IEEE Press, pp 139\u2013148","DOI":"10.1109\/MSR.2013.6624021"},{"key":"10292_CR39","doi-asserted-by":"crossref","unstructured":"Schwarz N, Lungu M, Robbes R (2012) On how often code is cloned across repositories. In: Proceedings of the 34th international conference on software engineering. IEEE Press, pp 1289\u20131292","DOI":"10.1109\/ICSE.2012.6227097"},{"issue":"6","key":"10292_CR40","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/TSE.2014.2322358","volume":"40","author":"M Shepperd","year":"2014","unstructured":"Shepperd M, Bowes D, Hall T (2014) Researcher bias: the use of machine learning in software defect prediction. IEEE Trans Softw Eng 40(6):603\u2013616","journal-title":"IEEE Trans Softw Eng"},{"issue":"5","key":"10292_CR41","first-page":"13","volume":"80","author":"TA Snijders","year":"1999","unstructured":"Snijders TA, Bosker RJ, et al. (1999) An introduction to basic and advanced multilevel modeling. Sage, London. WONG, GY, y MASON, WM (1985): the hierarchical logistic Regression. Model Multilevel Analy, J Am Stat Assoc 80(5):13\u2013524","journal-title":"Model Multilevel Analy, J Am Stat Assoc"},{"key":"10292_CR42","doi-asserted-by":"crossref","unstructured":"Svajlenko J, Roy CK (2014) Evaluating modern clone detection tools. In: 2014 IEEE international conference on software maintenance and evolution. IEEE, pp 321\u2013330","DOI":"10.1109\/ICSME.2014.54"},{"issue":"5","key":"10292_CR43","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1109\/TSE.2019.2912962","volume":"47","author":"J Svajlenko","year":"2019","unstructured":"Svajlenko J, Roy CK (2019) The mutation and injection framework: evaluating clone detection tools with mutation analysis. IEEE Trans Softw Eng 47 (5):1060\u20131087","journal-title":"IEEE Trans Softw Eng"},{"issue":"9","key":"10292_CR44","doi-asserted-by":"publisher","first-page":"1458","DOI":"10.3390\/sym12091458","volume":"12","author":"C Tang","year":"2020","unstructured":"Tang C, Luktarhan N, Zhao Y (2020) An efficient intrusion detection method based on lightgbm and autoencoder. Symmetry 12(9):1458","journal-title":"Symmetry"},{"issue":"2","key":"10292_CR45","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1007\/s10664-018-9645-2","volume":"24","author":"P Thongtanunam","year":"2019","unstructured":"Thongtanunam P, Shang W, Hassan AE (2019) Will this clone be short-lived? towards a better understanding of the characteristics of short-lived clones. Empir Softw Eng 24(2):937\u2013972","journal-title":"Empir Softw Eng"},{"key":"10292_CR46","doi-asserted-by":"crossref","unstructured":"Walthers J (2015) Learning to rank for cross-device identification. In: 2015 IEEE international conference on data mining workshop (ICDMW). IEEE, pp 1710\u20131712","DOI":"10.1109\/ICDMW.2015.246"},{"issue":"3","key":"10292_CR47","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.1007\/s10664-017-9558-5","volume":"23","author":"S Wang","year":"2018","unstructured":"Wang S, Chen TH, Hassan AE (2018) Understanding the factors for fast answers in technical q & a websites. Empir Softw Eng 23(3):1552\u20131593","journal-title":"Empir Softw Eng"},{"key":"10292_CR48","doi-asserted-by":"crossref","unstructured":"Wang S, Zou Y, Ng J, Ng T (2017) Context-aware service input ranking by learning from historical information. IEEE Trans Serv Comput","DOI":"10.1109\/TSC.2017.2777487"},{"key":"10292_CR49","doi-asserted-by":"crossref","unstructured":"Weisberg S (2005) Applied linear regression. Wiley, vol 528","DOI":"10.1002\/0471704091"},{"key":"10292_CR50","doi-asserted-by":"crossref","unstructured":"Wiese IS, da Silva JT, Steinmacher I, Treude C, Gerosa MA (2016) Who is who in the mailing list? comparing six disambiguation heuristics to identify multiple addresses of a participant. In: 2016 IEEE international conference on software maintenance and evolution (ICSME). IEEE, pp 345\u2013355","DOI":"10.1109\/ICSME.2016.13"},{"key":"10292_CR51","doi-asserted-by":"crossref","unstructured":"Xie S, Khomh F, Zou Y (2013) An empirical study of the fault-proneness of clone mutation and clone migration. In: 2013 10Th working conference on mining software repositories (MSR). IEEE, pp 149\u2013158","DOI":"10.1109\/MSR.2013.6624022"},{"key":"10292_CR52","doi-asserted-by":"crossref","unstructured":"Yang B, He Y, Liu H, Chen Y, Jin Z (2020) A lightweight fault localization approach based on xgboost. In: 2020 IEEE 20Th international conference on software quality, reliability and security (QRS). IEEE, pp 168\u2013179","DOI":"10.1109\/QRS51102.2020.00033"},{"issue":"1","key":"10292_CR53","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1109\/TR.2014.2370891","volume":"64","author":"X Yang","year":"2014","unstructured":"Yang X, Tang K, Yao X (2014) A learning-to-rank approach to software defect prediction. IEEE Trans Reliab 64(1):234\u2013246","journal-title":"IEEE Trans Reliab"},{"key":"10292_CR54","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.jss.2017.08.045","volume":"134","author":"F Zhang","year":"2017","unstructured":"Zhang F, Khoo SC, Su X (2017) Predicting change consistency in a clone group. J Syst Soft 134:105\u2013119","journal-title":"J Syst Soft"},{"issue":"4","key":"10292_CR55","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1007\/s10664-019-09696-8","volume":"24","author":"G Zhao","year":"2019","unstructured":"Zhao G, da Costa DA, Zou Y (2019) Improving the pull requests review process using learning-to-rank algorithms. Empir Softw Eng 24(4):2140\u20132170","journal-title":"Empir Softw Eng"},{"key":"10292_CR56","doi-asserted-by":"crossref","unstructured":"Zhou J, Zhang H (2012) Learning to rank duplicate bug reports. In: Proceedings of the 21st ACM international conference on information and knowledge management, pp 852\u2013861","DOI":"10.1145\/2396761.2396869"},{"issue":"4","key":"10292_CR57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1082983.1083147","volume":"30","author":"J \u015aliwerski","year":"2005","unstructured":"\u015aliwerski J., Zimmermann T, Zeller A (2005) When do changes induce fixes? ACM Sigsoft Soft Eng Notes 30(4):1\u20135","journal-title":"ACM Sigsoft Soft Eng Notes"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-023-10292-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-023-10292-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-023-10292-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T09:48:12Z","timestamp":1685094492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-023-10292-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,25]]},"references-count":57,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["10292"],"URL":"https:\/\/doi.org\/10.1007\/s10664-023-10292-0","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,25]]},"assertion":[{"value":"5 January 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"70"}}