Enhancing Software Requirements Classification: Integrating Recurrent Neural Networks and Natural Language Processing for Managing Structural Complexity
Keywords:
Requirements Engineering, Deep Learning, Recurrent Neural Network, Requirements Classification, Structural Complexity in Software, NLPAbstract
The inherent complexity of software requirements poses significant challenges in project planning and quality assurance. This research addresses these challenges by enhancing the classification of software requirements. It explores the dynamic relationships between requirements and their associated acceptance criteria through advanced deep-learning methods. The primary objective is to improve the accuracy and efficiency of requirements classification, thereby contributing to more effective project management and development processes. We propose a novel approach using a Recurrent Neural Network for Requirement Engineering (RNNRE) model. This model integrates natural language processing to analyze and process complex, multilevel requirements’ temporal and functional dynamics. Our methodology is rigorously tested on the Baseline EMR, a comprehensive real-world dataset, to assess the model’s effectiveness and accuracy in classifying software requirements. Results: The study reveals that finer granularity in requirement conditions substantially influences classification outcomes, impacting the precision of acceptance statements. The RNNRE model demonstrates robust performance, achieving an accuracy of 82.6%, a recall rate of 80%, and a precision of 100%. These results notably surpass the performance of several benchmarked state-of-the-art models, showcasing the model’s effectiveness in handling complex requirement scenarios. The RNNRE model marks a significant advancement in refining the requirements engineering process, particularly for intricate and multileveled requirements. This research demonstrates the practical application of deep learning in requirements classification. It contributes valuable insights to the field, enhancing the understanding and methodology of managing structural complexity in software requirements engineering.
Downloads
References
Abualhaija, S., Arora, C., Sabetzadeh, M., Briand, L. C. & Traynor, M. Automated demarcation of requirements in textual specifications: a machine learning-based approach. Empirical Software Engineering, 25 (2020), 5454–5497. https://link.springer.com/article/10.1007/s10664-020-09864-1
Sleem, S., Capretz, L. F. & Ahmed, F. Benchmarking machine learning tech- nologies for software defect detection., 2015, https:arXiv preprint arXiv:1506.07563. https://doi.org/10.48550/arXiv.1506.07563
Alrumaih, H., Mirza, A. & Alsalamah, H. Domain ontology for requirements classi- fication in a requirements engineering context. IEEE Access, 8 (2020), 89899–89908. https://ieeexplore.ieee.org/document/9091131
AlOmar, E., A., Mkaouer, W., M., Newman, C. & Ouni, A. On preserving the behavior in software refactoring: A systematic mapping study. Information and Software Technology, 140 (2021), no. 2, 459–502. https://doi.org/10.1016/j.infsof.2021.106675
Barry-Straume, J., Tschannen, A., Engels, D. W. & Fine, E. An evaluation of training size impacts validation accuracy for optimized convolutional neural networks. SMU Data Sci- ence Review, 1 (2018), no. 1, 12. https://scholar.smu.edu/datasciencereview/vol1/iss4/12.
Maciejauskaite˙, M. & Miliauskaite˙, J. (2024). The efficiency of machine learning algorithms in classifying non-functional requirements. New Trends in Computer Sciences, 2(1), 46–56. https://doi.org/10.3846/ntcs.2024.21574
Patel, V., Mehta, P. & Lavingia, K. Software Requirement Classification Using Ma- chine Learning Algorithms. Proceedings of the 2023, nternational Conference on Artifi- cial Intelligence and Applications (ICAIA) Alliance Technology Conference (ATCON-1). https://ieeexplore.ieee.org/document/10169588
Damasiotis, V., Fitsilis, P., Considine, P. & Kane, O. J. Analysis of software project complexity factors. Proceedings of the 2017 International Conference on Management Engineering, Software Engineering and Service Sciences, 2017, 54–58. https://dl.acm.org/doi/pdf/10.1145/3034950.3034989
Fitsilis, P. Measuring the complexity of software projects. 2009 WRI World Congress on Computer Science and Information Engineering, 7 (2009), 644–648. http://dx.doi.org/10.1109/CSIE.2009.936
Gupta, Varun and Fernandez-Crehuet, Jose Maria and Hanne, Thomas and Telesko, Rainer. Requirements engineering in software startups: A systematic mapping study. Ap- plied Sciences, 10 (2020), no. 17, 6125. http://dx.doi.org/10.3390/app10176125
Hey, T., Keim, J., Koziolek, A. & Tichy, W. F. Norbert: Transfer learning for requirements classification—2020 IEEE 28th International Requirements Engineering Conference (RE) 2020, 169–179. https://doi.org/10.1109/RE48521.2020.00028
Hossin, M. & Sulaiman, M. N. A review on evaluation metrics for data classification eval- uations.International journal of data mining & knowledge management process., 2015, https://DOI : 10.5121/ijdkp.2015.5201.
Ismail, F. H., Forestier, G., Weber, J., Idoumghar, L. & Muller, P. A. Deep learning for time series classification: a review. Data mining and knowledge discovery, 33 (2019), 917–963. https://doi.org/10.1007/s10618-019-00619-
Jiao, J. & Chen, C. H. Customer requirement management in product develop- ment: a review of research issues. Concurrent Engineering, 14 (2006), no. 3, 173–185. http://dx.doi.org/10.1177/1063293X06068357
Khattak, F. K., Jeblee, S., Pou-Prom, C., Abdalla, M., Meaney, C. & Rudzicz, F. A survey of word embeddings for clinical text. Journal of Biomedical Informatics, 100 (2019), 100057. https://doi.org/10.1016/j.yjbinx.2019.100057
Kowsari, K., Jafari, M. K., Heidarysafa, M., Mendu, S., Barnes, L. & Brown, D. Text classification algorithms: A survey. Information, 10 (2019), no. 4, 150. https://doi.org/10.3390/info10040150
Li, C., Huang, L., Ge, J., Luo, B. & Ng, V. Automatically classifying user requests in crowdsourcing requirements engineering. Journal of Systems and Software, 138 (2018), 108–123. https://doi.org/10.1016/j.jss.2017.12.028
Maxwell, A., Li, R., Yang, B., Weng, H., Ou, A., Hong, H., Zhou, Z., Gong, P. & Zhang, C. Deep learning architectures for multi-label classification of intelligent health risk prediction.
BMC bioinformatics, 18 (2017), 121–131. https://doi.org/10.1186/s12859-017-1898-z
Onyeka, E. A process framework for managing implicit requirements using analogy-based reasoning: Doctoral consortium paper. IEEE 7th International Conference on Research Challenges in Information Science (RCIS), 2013, 1–5. https://ieeexplore.ieee.org/document/6577726
Rahman, M. A., Haque, M. A., Tawhid, M. N. A. & Siddik, M. S. Classifying non-functional requirements using RNN variants for quality software development. Proceedings of the 3rd ACM SIGSOFT International Workshop on Machine Learning Techniques for Software Quality Evaluation, 2019, 25–30. https://doi.org/10.1145/3340482.3342745
Khurana, D., Koli, A., Khatter, K. et al. Natural language processing: state of the art, current trends and challenges. Multimed Tools Appl 82, 3713–3744 (2023). https://doi.org/10.1007/s11042-022-13428-4
Randell, A., Spellman, E., Ulrich, W. & Wallk, J. Leveraging business architec- ture to improve business requirements analysis. Business Architecture Guild, 2014. https://cdn.ymaws.com/www.businessarchitectureguild.org
Rasheed, A., Zafar, B., Shehryar, T., Aslam, N. A., Sajid, M., Ali, N., Dar, S. H & Khalid, S. Requirement engineering challenges in agile software development. Mathematical Problems in Engineering, 2021 (2021), 1–18. https://doi.org/10.1155/2021/6696695
Ren, Y., Zhao, P., Sheng, Y., Yao, D. & Xu, Z. Robust softmax regression for multi-class classification with self-paced learning. Proceedings of the 26th International Joint Confer- ence on Artificial Intelligence, 2017, 2641–2647. https://doi.org/10.24963/ijcai.2017/368
Rodriguez, S., Thangarajah, J. & Winikoff, M. User and System Stories: an agile approach for managing requirements in AOSE. Open Access Te Herenga Waka-Victoria University of Wellington, 2021. https://doi.org/10.26686/wgtn.14527758.v1
San Crist´obal, J. R., Carral, L., Diaz, E., Fraguela, J. A., Iglesias, G. & oth- ers. Complexity and project management: A general overview. Complexity, 2018. https://api.semanticscholar.org/CorpusID:53098515
Shabi, J., Reich, Y., Robinzon, R. & Mirer, T. A decision support model to manage overspecification in system development projects. Journal of Engineering Design, 32 (2021), no. 7, 323–345. https://doi.org/10.1080/09544828.2021.190897
Torfi, A., Shirvani, R. A., Keneshloo, Y., Tavaf, N. & Fox, E. A. Natural language processing advancements by deep learning: A survey., 2020, https://arXiv preprint arXiv:2003.01200.
Wallace, D. R. & Cherniavsky, J. C. Guide to software acceptance. DIANE Publishing, 1990. https://api.semanticscholar.org/CorpusID:56489605
Winkler, J. P., Gr¨onberg, J. & Vogelsang, A. Predicting How to Test Requirements: An Automated Approach. 2019 IEEE 27th International Requirements Engineering Conference (RE), 2019, 120–130. https://ieeexplore.ieee.org/document/8920404
Zhao, L., Alhoshan, W., Ferrari, A. & Letsholo, K. J. Classification of natural lan- guage processing techniques for requirements engineering., 2022, https://arXiv preprint arXiv:2204.04282.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
