Full Text PDF
Impact Factor (2025): 6.9
DOI Prefix: 10.47001/IRJIET
Impact Factor (2025): 6.9
DOI Prefix: 10.47001/IRJIET
Vol 10 No 5 (2026): Volume 10, Issue 5, May 2026 | Pages: 316-327
International Research Journal of Innovations in Engineering and Technology
OPEN ACCESS | Research Article | Published Date: 15-05-2026
One of the first step in the software development process is the requirements analysis. This task plays a relevant role because of his considerable impact on the developed end product. Since the security aspect of software systems are becoming much more critical this recants years, the prioritization of software security requirements in the early stage of the software development process is necessary. For that reason, the development of techniques applicable on the analysis of software security requirements are representing great advancements for the software requirements engineering activities. The literature review on methods to analyze and classify software requirements shows that, there are existing research on machine learning techniques to classify software requirements, but the most of works are working on binary classification of functional and non-functional requirements, so the multiclass classification of software security requirements are not in the focus of the most research activities. This work proposes an approach for classification of software security requirements in multiclass, using classical machine learning techniques and deep learning techniques, filling the gap on the missing activities in this area. Another contribution of this approach it the evaluation of machine learning models on multiclass classification of software security requirements. For this work, a Multinomial Naive Bayes model (MNB), an Artificial Neural Network model (ANN), a Convolutional Neural Network model (CNN) and a Recurrent Neural Network model (RNN) are trained and tested on DOSSPRE dataset. The results show that the Multinomial Naive Bayes model achieved the best performance with 72% accuracy, the worst performer was the Recurrent Neural Network model with 62% accuracy.
Requirement engineering, Deep learning, Machine learning.
Landry Giraud Wandji T. (2026). A Multiclass Classification of Software Security Requirements: A Deep Learning Approach. International Research Journal of Innovations in Engineering and Technology - IRJIET, 10(5), 316-327. Article DOI https://doi.org/10.47001/IRJIET/2026.105042
This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
Cody Baker et al. “Automatic multi-class non-functional software requirements classification using neural networks”. In: 2019 IEEE 43rd annual computer software and applications conference (COMPSAC). Vol. 2. IEEE. 2019, pp. 610–615.
Jane Cleland-Huang et al. “Automated classification of non-functional requirements”. In: Requirements engineering 12.2 (2007), pp. 103–120.
Donald Firesmith et al. “Engineering security requirements.” In: J. Object Technol. 2.1 (2003), pp. 53–68.
Wandji T. Landry G. “A Binary Classification of Software Security Requirements: A Deep Learning Approach”. In: IRJIET 09 (2025).
Shoaib Hassan et al. “A systematic mapping to investigate the application of machine learning techniques in requirement engineering activities”. In: CAAI Transactions on Intelligence Technology 9.6 (2024), pp. 1412–1434.
Rajni Jindal, Ruchika Malhotra, and Abha Jain. “Automated classification of security requirements”. In: 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE. 2016, pp. 2027–2033.
Sanjanasri Jp et al. “A non-exclusive multi-class convolutional neural network for the classification of functional requirements in AUTOSAR software requirement specification text”. In: IEEE Access 10 (2022), pp. 117707– 117714.
Prudence Kadebu et al. “A classification approach for software requirements towards maintainable security”. In: Scientific African 19 (2023), e01496.
Shah Khalid, Shengli Wu, and Fang Zhang. “A multi-objective approach to determining the usefulness of papers in academic search”. In: Data Technologies and Applications 55.5 (2021), pp. 734–748.
Mengmeng Lu and Peng Liang. “Automatic classification of non-functional requirements from augmented app user reviews”. In: Proceedings of the 21st international conference on evaluation and assessment in software engineering. 2017, pp. 344–353.
Ruchika Malhotra et al. “Analyzing and evaluating security features in software requirements”. In: 2016 International Conference on Innovation and Challenges in Cyber Security (ICICCS-INBUSH). IEEE. 2016, pp. 26–30.
Gaith Y Quba et al. “Software requirements classification using machine learning algorithm’s”. In: 2021 international conference on information technology (ICIT). IEEE. 2021, pp. 685–690.
Antonio Miguel Rosado da Cruz and Estrela Ferreira Cruz. “Machine Learning Techniques for Requirements Engineering: A Comprehensive Literature Review”. In: Software 4.3 (2025), p. 14.
P Salini and S Kanmani. “Survey and analysis on security requirements engineering”. In: Computers & Electrical Engineering 38.6 (2012), pp. 1785– 1797.
MAF Saroth, PMAK Wijerathne, and BTGS Kumara. “Automatic multiclass non-functional software requirements classification using machine learning algorithms”. In: 2024 International Research Conference on Smart Computing and Systems Engineering (SCSE). Vol. 7. IEEE. 2024, pp. 1–6.
Touseef Tahir et al. “Cross-Project Multiclass Classification of EARS Based Functional Requirements Utilizing Natural Language Processing, Machine Learning, and Deep Learning”. In: Systems 13.7 (2025), p. 567.
Sabrina Tiun et al. “Classification of functional and non-functional requirement in software requirement using Word2vec and fast Text”. In: journal of Physics: conference series. Vol. 1529. 4. IOP Publishing. 2020, p. 042077.