Skip to main content
SpringerLink
Log in

Severity Classification of Code Smells Using Machine-Learning Methods

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

Code smell detection can be very useful for minimizing maintenance costs and improving software quality. Code smells help developers/programmers, researchers to subjectively interpret design defects in different ways. Code smells instances can have varied size, intensity or severity which needs to be focused upon as they affect the software quality accordingly. Therefore, this study aims to detect the severity of code smells from code smell datasets. The severity of code smells is significant for reporting code smell detection performance, as it permits refactoring efforts to be prioritized. Code smell severity also describes extent of effort required during software maintenance. In our work, we have considered four code smells severity datasets to detect the severity of code smell. These datasets are data class, god class, feature envy and long method code smells. This paper uses four machine-learning and three ensemble learning approaches to identify the severity of code smells. To improve the models’ performance, we used fivefold cross-validation method: Chi-square-based feature selection algorithm and parameter optimization techniques. We applied two-parameter optimization techniques, namely grid search and random search and also compared their accuracy. The conclusion of this study is that the XG Boost model obtained an accuracy of 99.12%, using the Chi-square-based feature selection technique for the long method code smell dataset. In this study, the results show that ensemble learning is best as compared to machine learning for severity detection of code smells.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Data availability

The dataset can be found at http://essere.disco.unimib.it/reverse/MLCSD.html.

References

  1. Lehman MM. Programs, life cycles, and laws of software evolution. Proc IEEE. 1980;68(9):1060–76.

    Article  Google Scholar 

  2. Wiegers K, Beatty J. Software Requirements. London: Pearson Education; 2013.

    Google Scholar 

  3. Chung L, Do PLJCS. On non-functional requirements in software engineering. In: Borgida AT, Chaudhri V, Giorgini P, Yue ES, editors. conceptual modeling: foundations and applications (lecture notes in computer science). Cham: Springer; 2009. p. 363–79.

    Chapter  Google Scholar 

  4. Fontana FA, Zanoni M. Code smell severity classification using machine learning techniques. Knowl Based Syst. 2017. https://doi.org/10.1016/j.knosys.2017.04.014.

    Article  Google Scholar 

  5. Vidal SA, Marcos C, Dıaz-Pace JA. An approach to prioritize code smells for refactoring. Autom Softw Eng. 2016;23(3):501–32. https://doi.org/10.1007/s10515-014-0175-x.

    Article  Google Scholar 

  6. Liu W, Wang S, Chen X, Jiang H. Predicting the severity of bug reports based on feature selection. Int J Softw Eng Knowl Eng. 2018;28(04):537–58. https://doi.org/10.1142/S0218194018500158.

    Article  Google Scholar 

  7. Tiwari O, Joshi R (2020) Functionality based code smell detection and severity classification. In: ISEC 2020: 13th innovations in software engineering conference, pp 1–5. https://doi.org/10.1145/3385032.3385048.

  8. Baarah A, Aloqaily A, Salah Z, Zamzeer M, Sallam M. Machine learning approaches for predicting the severity level of software bug reports in closed source projects. (IJACSA) Int J Adv Comput Sci Appl. 2019;10(8):285–94.

  9. Fontana FA, Mäntylä MV, Zanoni M, Marino A. Comparing and experimenting machine learning techniques for code smell detection. Empir Softw Eng. 2016;21(3):1143–91.

    Article  Google Scholar 

  10. Mhawish MY, Gupta M. Generating code-smell prediction rules using decision tree algorithm and software metrics. Int J Comput Sci Eng (IJCSE). 2019;7(5):41–8.

    Google Scholar 

  11. Mhawish MY, Gupta M. Predicting code smells and analysis of predictions: using machine learning techniques and software metrics. J Comput Sci Technol. 2020;35(6):1428–45. https://doi.org/10.1007/s11390-020-0323-7.

    Article  Google Scholar 

  12. Kaur I, Kaur A. A novel four-way approach designed with ensemble feature selection for code smell detection. IEEE Access. 2021;9:8695–707. https://doi.org/10.1109/ACCESS.2021.3049823.

    Article  Google Scholar 

  13. Pushpalatha MN, Mrunalini M. Predicting the severity of closed source bug reports using ensemble methods. In: Satapathy S, Bhateja V, Das S, editors. Smart intelligent computing and applications. Smart innovation, systems and technologies, vol. 105. Singapore: Springer; 2019. https://doi.org/10.1007/978-981-13-1927-3_62.

    Chapter  Google Scholar 

  14. Alazba A, Aljamaan HI. Code smell detection using feature selection and stacking ensemble: an empirical investigation. Inf Softw Technol. 2021;138: 106648.

    Article  Google Scholar 

  15. Draz MM, Farhan MS, Abdulkader SN, Gafar MG. Code smell detection using whale optimization algorithm. Comput Mater Continua. 2021;68(2):1919–35.

    Article  Google Scholar 

  16. Dewangan S, Rao RS, Mishra A, Gupta M. A novel approach for code smell detection: an empirical study. IEEE Access. 2021;9:162869–83. https://doi.org/10.1109/ACCESS.2021.3133810.

    Article  Google Scholar 

  17. Reis JPD, Abreu FBE, Carneiro GDF. Crowd smelling: a preliminary study on using collective knowledge in code smells detection. Empir Softw Eng. 2022;27:69. https://doi.org/10.1007/s10664-021-10110-5.

    Article  Google Scholar 

  18. van Oort B, Cruz L, Aniche M, van Deursen A. (2021) The prevalence of code smells in machine learning projects, IEEE/ACM 1st Workshop on AI Engineering - Software Engineering for AI (WAIN). Madrid, Spain. p. 1–8. https://doi.org/10.1109/WAIN52551.2021.00011.

  19. Fontana A, Mariani E, Morniroli A, Sormani R, Tonello A. (2011). An experience report on using code smells detection tools. In: IEEE fourth international conference on software testing, verification and validation workshops, RefTest 2011. Berlin: IEEE Computer Society; 2011. p. 450–7. https://doi.org/10.1109/ICSTW.2011.12.

  20. Boutaib S, Elarbi M, Bechikh S, Palomba F, Said LB. A bi-level evolutionary approach for the multi-label detection of smelly classes. In: GECCO 22 companion, July 9–13, 2022, Boston, MA, USA. ACM ISBN 978-1-4503-9268-6/22/07. (2022). https://doi.org/10.1145/3520304.3528946.

  21. Abdou AS, Darwish NR. Early prediction of software defect using ensemble learning: a comparative study. Int J Comput Appl. 2018;179(46):29–40. https://doi.org/10.5120/ijca2018917185.

    Article  Google Scholar 

  22. Dewangan S, Rao RS, Mishra A, Gupta M. Code smell detection using ensemble machine learning algorithms. Appl Sci. 2022;12(20):10321. https://doi.org/10.3390/app122010321.

    Article  Google Scholar 

  23. Dewangan S, Rao RS. Code smell detection using classification approaches. In: Udgata SK, Sethi S, Gao XZ, editors. Intelligent systems; lecture notes in networks and systems, vol. 431. Singapore: Springer; 2022. https://doi.org/10.1007/978-981-19-0901-6_25.

    Chapter  Google Scholar 

  24. Dewangan S, Rao RS, Yadav PS. Dimensionally reduction based machine learning approaches for code smells detection. In: 2022 international conference on intelligent controller and computing for smart power (ICICCSP); 2022. p. 1–4. https://doi.org/10.1109/ICICCSP53532.2022.9862030. Accessed 30 Jan 2023.

  25. Fowler M. Refactoring: improving the design of existing code. Boston: Addison-Wesley Longman Publishing Co. Inc. http://www.refactoring.com/ (1999).

  26. Gupta A, Chauhan NK. A severity-based classification assessment of code smells in Kotlin and Java application. Arab J Sci Eng. 2022;47:1831–48. https://doi.org/10.1007/s13369-021-06077-6.

    Article  Google Scholar 

  27. Abdou A, Darwish N. Severity classification of software code smells using machine learning techniques: a comparative study. J Softw Evol Proc. 2022. https://doi.org/10.1002/smr.2454.

    Article  Google Scholar 

  28. Hejres S, Hammad M. Code smell severity detection using machine learning. In: 4th smart cities symposium (SCS 2021); 2021. p. 89–96. https://doi.org/10.1049/icp.2022.0320.

  29. Nanda J, Chhabra JK. SSHM: SMOTE-stacked hybrid model for improving severity classification of code smell. Int J Inf Technol. 2022. https://doi.org/10.1007/s41870-022-00943-8.

    Article  Google Scholar 

  30. Tempero E, Anslow C, Dietrich J, Han T, Li J, Lumpe M, Melton H, Noble J. The qualitas corpus: a curated collection of java code for empirical studies. In: Proceedings of the 17th Asia Pacific software engineering conference (APSEC 2010). IEEE Computer Society; 2010. p. 336–45. https://doi.org/10.1109/APSEC.2010.46.

  31. Olbrich S, Cruzes D, Sjoberg DIK. Are all code smells harmful? A study of god classes and brain classes in the evolution of three open source systems. In: Proceedings of the IEEE international conference on software maintenance (ICSM 2010), Timisoara, Romania; 2010. p. 1–10. https://doi.org/10.1109/ICSM.2010.5609564.

  32. Marinescu C, Marinescu R, Mihancea P, Ratiu D, Wettel R. iPlasma: an integrated platform for quality assessment of object-oriented design. In: Proceedings of the 21st IEEE international conference on software maintenance (ICSM 2005) (industrial and tool Proceedings), tool demonstration track. Budapest, Hungary: IEEE; 2005. p. 77–80.

  33. Nongpong K. Integrating “code smell” detection with refactoring tool support. Ph.D. thesis, University of Wisconsin Milwaukee (2012).

  34. Marinescu R. Measurement and quality in object oriented design. Ph.D. thesis, Department of Computer Science, “Polytechnic” University of Timisoara (2002).

  35. Ali PJM, Faraj RH. Data normalization and standardization : a technical report. Mach Learn Tech Rep. 2014;1(1):1–6.

    Google Scholar 

  36. Romero E, Sopena JM. Performing feature selection with multilayer perceptrons. IEEE Trans Neural Netw. 2008;19(3):431–41.

    Article  Google Scholar 

  37. https://www.geeksforgeeks.org/ml-chi-square-test-for-feature-selection. Accessed 30 Jan 2023.

  38. Hsu CW, Chang CC, Lin CJ. A practical guide to support vector classification. Technical Report, Taiwan University; 2008. https://www.csie.ntu.edu.tw/cjlin/papers/guide/guide.pdf (2020).

  39. Chaitra PC, Saravana Kumar R. A review of multi-class classification algorithm. Int J Pure Appl Math. 2018;118(14):17–26.

    Google Scholar 

  40. https://www.tutorialspoint.com/machine_learning_with_python/machine_learning_with_python_knn_algorithm_finding_nearest_neighbors.htm. Accessed 30 Jan 2023.

  41. https://www.geeksforgeeks.org/boosting-in-machine-learning-boosting-and-adaboost/. (Last Updated: 11 Oct 2021). Retrieved 26 Nov 2021.

  42. https://analyticsindiamag.com/xgboost-internal-working-to-make-decision-trees-and-deduce-predictions/. Last Updated 2 Nov 2020. Retrieved 26 Nov 2021.

  43. https://www.analyticsvidhya.com/blog/2021/04/how-the-gradient-boosting-algorithm-works/. (Last Updated 19 Apr 2021). Retrieved 26 Nov 2021.

  44. https://www.geeksforgeeks.org/paired-t-test-a-detailed-overview/. (Last Updated 28 Feb 2022). Retrieved 26 Jan 2023.

  45. https://towardsdatascience.com/paired-t-test-to-evaluate-machine-learning-classifiers-1f395a6c93fa. (Last Updated 6 July 2022). Retrieved 26 Jan 2023.

Download references

Funding

This study was not supported by any other sources.

Author information

Authors and Affiliations

  1. Department of Computer Science and Information Technology, Guru Ghasidas Vishwavidyalaya, Bilaspur, Chhattisgarh, India

    Seema Dewangan & Rajwant Singh Rao

  2. Computer Science, DST-Centre for Interdisciplinary Mathematical Sciences, Institute of Science, Banaras Hindu University, Varanasi, India

    Sripriya Roy Chowdhuri & Manjari Gupta

Authors
  1. Seema Dewangan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rajwant Singh Rao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sripriya Roy Chowdhuri
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Manjari Gupta
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization, MG, and RSR; data curation, SD; formal analysis, MG, RSR; investigation, SD, and RSR; methodology, MG, and RSR; supervision, MG, RSR; validation, RSR, SD, and MG; visualization, SD, and RSR; writing, SD, and RSR; review and editing, RSR, MG, and SRC.

Corresponding author

Correspondence to Rajwant Singh Rao.

Ethics declarations

Conflict of Interest

No conflicts of interest exist, according to the authors, with the publishing of this work.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the topical collection “Research Trends in Computational Intelligence” guest edited by Anshul Verma, Pradeepika Verma, Vivek Kumar Singh and S. Karthikeyan.

Appendix

Appendix

See Table 21.

Table 21 Description of all selected metrics [4]
Full size table

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dewangan, S., Rao, R.S., Chowdhuri, S.R. et al. Severity Classification of Code Smells Using Machine-Learning Methods. SN COMPUT. SCI. 4, 564 (2023). https://doi.org/10.1007/s42979-023-01979-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-023-01979-8

Keywords

Search

Navigation