Full Text PDF
ESTD Year: 2017 | Impact Factor (2026): 8.7
DOI Prefix: 10.47001/IRJIET
ESTD Year: 2017 | Impact Factor (2026): 8.7
DOI Prefix: 10.47001/IRJIET
Vol 10 No 6 (2026): Volume 10, Issue 6, June 2026 | Pages: 96-102
International Research Journal of Innovations in Engineering and Technology
OPEN ACCESS | Research Article | Published Date: 08-06-2026
Requirements engineering (RE) is a foundational activity in software development, yet the quality of requirements remains a persistent challenge. Ambiguity, incompleteness, inconsistency, and unverifiability frequently lead to project delays, cost overruns, and system defects. Traditional rules-based evaluation methods, while useful, lack the ability to capture contextual and semantic nuances inherent in natural language requirements. Recent advances in machine learning application for requirements engineering offer new opportunities for automated, scalable, and objective requirements quality assessment. This paper presents a comprehensive deep learning approach for evaluating requirement quality through a defined requirement quality model. Using an appropriate dataset of labeled software requirements, we train and compare several machine learning models, including a Multinomial Naive Bayes (MNB), an Artificial Neural Network (ANN), a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN) model. The results demonstrate that the CNN model significantly outperforms the MNB-model as classical machine learning baselines, achieving up to 99% accuracy in multi-label classification. The findings highlight the potential of deep learning to enhance requirements engineering workflows, reduce manual review effort, and improve specification quality.
requirements quality, deep learning, machine learning.
Landry Giraud Wandji T. (2026). Requirements Quality Evaluation: A Deep Learning Approach. International Research Journal of Innovations in Engineering and Technology - IRJIET, 10(6), 96-102. Article DOI https://doi.org/10.47001/IRJIET/2026.106010
This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
Nathan Carlson and Phil Laplante. “The NASA automated requirements measurement tool: a reconstruction”. In: Innovations in Systems and Software Engineering 10.2 (2014), pp. 77–91.
Jacob Devlin et al. “Bert: Pre-training of deep bidirectional transformers for language understanding”. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 2019, pp. 4171–4186.
Fabrizio Fabbrini et al. “The linguistic approach to the natural language requirements quality: benefit of the use of an automatic tool”. In: proceedings 26th annual NASA Goddard software engineering workshop. IEEE. 2001, pp. 97–105.
Wandji T. Landry G. “A Multiclass Classification of Software Security Requirements: A Deep Learning Approach”. In: IRJIET 10 (2026).
Robert J. Halligan. “Requirements Quality Metrics: The Basis of Informed Requirements Engineering Management”. In: CSESAW ’93 (2017).
Hubert F Hofmann and Franz Lehner. “Requirements engineering as a success factor in software projects”. In: IEEE software 18.4 (2001), p. 58.
Rahat Izhar, Shahid N Bhatti, and Sultan A Alharthi. “Bridging precision and complexity: A novel machine learning approach for ambiguity detection in software requirements”. In: IEEE Access (2025).
RS Rasiman. “A machine learning approach for requirements traceability in model-driven development”. MA thesis. 2021.