A Deep Learning Approach to Classifying Software Requirements: The Application of Transformer-Based Ensemble Learning and Attention-Based Fusion
By: Azaz Ahmed Kiani
References
- Abdi, L., & Hashemi, S. (2015). To combat multi-class imbalanced problems by means of over-sampling and boosting techniques. Soft Computing, 19, 3369-3385.
- Baker, C., Deng, L., Chakraborty, S., & Dehlinger, J. (2019, July). Automatic multi-class non-functional software requirements classification using neural networks. In 2019 IEEE 43rd annual computer software and applications conference (COMPSAC) (Vol. 2, pp. 610-615). IEEE.
- Dias Canedo, E., & Cordeiro Mendes, B. (2020). Software requirements classification using machine learning algorithms. Entropy, 22(9), 1057.
- Fernández-Navarro, F., Hervás-Martínez, C., & Gutiérrez, P. A. (2011). A dynamic over-sampling procedure based on sensitivity for multi-class problems. Pattern Recognition, 44(8), 1821-1833.
- Formal Methods & Tools Group, Natural Language Requirements Dataset. Available online: http://fmt.isti.cnr.it/nlreqdataset/ (Last accessed on December 2023)
- Gnanasekaran, Rajesh Kumar, Suranjan Chakraborty, Josh Dehlinger, and Lin Deng. (2021) “Using Recurrent Neural Networks for Classification of Natural Language-based Non-functional Requirements.” In REFSQ Workshop
- Guru99 – Functional Requirement Specification Examples. Available online: https://www.guru99.com/functional-requirement-specification-example.html (Accessed: December 2023)
- Haque, M.A.; Rahman, M.A.; Siddik, M.S. Non-Functional Requirements Classification with Feature Extraction and Machine Learning: An Empirical Study. In Proceedings of the 1st International Conference on Advances in Science, Engineering and Robotics Technology 2019, Dhaka, Bangladesh, 3–5 May 2019
- IEEE Standard Glossary of Software Engineering Terminology. In IEEE Std 729-1983; IEEE: Manhattan, NY, USA, 1990; pp. 1–84.
- INSPIRE Helpdesk “MIWP 2014–2016” MIWP-16: Monitoring. Available online: https://ies-svn.jrc.ec.europa.eu/documents/33 (accessed on December 2023)
- Kaur, K., & Kaur, P. (2023). BERT-CNN: improving BERT for requirements classification using CNN. Procedia Computer Science, 218, 2604-2611.
- Kaur, K., & Kaur, P. (2023). MNoR-BERT: multi-label classification of nonfunctional requirements using BERT. Neural Computing and Applications, 35(30), 22487-22509.
- Kaur, K., & Kaur, P. (2024). The application of AI techniques in requirements classification: a systematic mapping. Artificial Intelligence Review, 57(3), 57.
- Kaur, Kamaljit, and Parminder Kaur. (2022) “SABDM: A self‐attention based bidirectional‐RNN deep model for requirements classification.” Journal of Software: Evolution and Process : e2430. doi: 10.1002/smr.2430
- Kici, D., Malik, G., Cevik, M., Parikh, D., & Basar, A. (2021, June). A BERT-based transfer learning approach to text classification on software requirements specifications. In Canadian AI.
- Kotonya, G., & Sommerville, I. (1998). Requirements engineering: processes and techniques. Wiley Publishing.
- Krasner, H. (2018). The cost of poor quality software in the us: A 2018 report. Consortium for IT Software Quality, Tech. Rep, 10, 8.
- Li, L.F.; Jin-An, N.C.; Kasirun, Z.M.; Piaw, C.Y. An Empirical comparison of machine learning algorithms for classification of software requirements. Int. J. Adv. Comput. Sci. Appl. 2019, 10, 258–263
- Lima, M.; Valle, V.; Costa, E.; Lira, F.; Gadelha, B. Software Engineering Repositories: Expanding the PROMISE Database; XXXIII Brazilian Symposium on Software Engineering; SBC: Porto Alegre, Brasil, 2020; pp. 427–436
- Mullis, J., Chen, C., Morkos, B., & Ferguson, S. (2024). Deep Neural Networks in Natural Language Processing for Classifying Requirements by Origin and Functionality: An Application of BERT in System Requirements. Journal of Mechanical Design, 146(4), 041401.
- Pérez-Verdejo, J. M., Sánchez-García, A. J., & Ocharán-Hernández, J. O. (2020, November). A systematic literature review on machine learning for automated requirements classification. In 2020 8th international conference in software engineering research and innovation (CONISOFT) (pp. 21-28). IEEE.
- Quba, G. Y., Al Qaisi, H., Althunibat, A., & AlZu’bi, S. (2021, July). Software requirements classification using machine learning algorithms. In 2021 international conference on information technology (ICIT) (pp. 685-690). IEEE.
- Rahimi, N., Eassa, F., & Elrefaei, L. (2020). An ensemble machine learning technique for functional requirement classification. Symmetry, 12(10), 1601.
- Rahimi, N., Eassa, F., & Elrefaei, L. (2021). One-and two-phase software requirement classification using ensemble deep learning. Entropy, 23(10), 1264.
- Rahimi, N.; Eassa, F.; Elrefaei, L. An Ensemble Machine Learning Technique for Functional Requirement Classification. Symmetry 2020, 12, 1601
- Rahman, K., Ghani, A., Misra, S., & Rahman, A. U. (2024). A deep learning framework for non-functional requirement classification. Scientific Reports, 14(1), 3216.
- Requirement Analysis & Specification (PPT Slide Content). Available online: https://slideplayer.com/slide/8979379/ (Accessed: December 2023)
- Saqib, M., Mustaqeem, M., Jawed, M. S., Abdulaziz, A., Khan, A., & Khan, J. (2025). Deep-transfer learning inspired natural language processing system for software requirements classification. Knowledge and Information Systems, 67(1), 839-861.
- Subahi, A. F. (2023). BERT-Based Approach for Greening Software Requirements Engineering Through Non-Functional Requirements. IEEE Access.
- Tanha, J., Abdi, Y., Samadi, N., Razzaghi, N., & Asadpour, M. (2020). Boosting methods for multi-class imbalanced data classification: an experimental review. Journal of Big data, 7, 1-47
- Tikayat Ray, A., Cole, B. F., Pinon Fischer, O. J., White, R. T., & Mavris, D. N. (2023). aerobert-classifier: Classification of aerospace requirements using bert. Aerospace, 10(3), 279.
- Trautsch, A., & Herbold, S. (2022, May). Predicting issue types with sebert. In Proceedings of the 1st international workshop on natural language-based software engineering (pp. 37-39).
Language: English
Page range: 71 - 110
Submitted on: Aug 29, 2025
Accepted on: Feb 18, 2026
Published on: Mar 17, 2026
Published by: Poznan University of Technology
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year
Keywords:
Related subjects:
© 2026 Azaz Ahmed Kiani, published by Poznan University of Technology
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.