Automated Classification and Identification of Non-Functional Requirements in Agile-Based Requirements Using Pre-Trained Language Models

被引:0
作者
Alhaizaey, Abdulrahim [1 ,2 ]
Al-Mashari, Majed [1 ]
机构
[1] King Saud Univ, Coll Comp & Informat Sci, Dept Informat Syst, Riyadh 11451, Saudi Arabia
[2] King Khalid Univ, Dept Informat Syst, Abha 61421, Saudi Arabia
关键词
Transformers; Solid modeling; Requirements engineering; Artificial intelligence; Adaptation models; Transfer learning; Training; Software quality; Natural languages; Labeling; Nonfunctional requirements; agile software development; requirements engineering; user stories; transfer learning; transformers; pre-trained language models; BERT; XLNet; ENGINEERING PRACTICES; USER STORIES; ELICITATION; CHALLENGES;
D O I
10.1109/ACCESS.2025.3570359
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Non-functional requirements (NFRs) are critical factors for software quality and success. A frequently reported challenge in agile requirements engineering is that NFRs are often neglected due to the focus on functional requirements (FRs) and the limited capability of agile requirements documented as user stories to represent NFRs. With the emergence of transfer learning and large pre-trained language models, various applications in requirements engineering have become feasible, alleviating several longstanding challenges. This study evaluates transformer-based models for the automated identification and classification of NFRs. We leveraged transfer learning with pre-trained transformer models to automate the identification and classification of NFRs in agile textual requirements documented as user stories. A dataset of over 10k user stories was collected and labeled, and pre-trained transformer models, including BERT, RoBERTa, XLNet, and DistilBERT, were fine-tuned to automate the identification of NFRs. We incorporated Focal Loss during training to mitigate the dominance of functionally driven requirements and class imbalances. In addition, thorough experiments on hyperparameter optimization were employed using Bayesian hyperparameter optimization to obtain the combination of hyperparameters that best correlated with the aim of enhancing each model's performance. Our evaluation demonstrated that the finetuned pre-trained models significantly outperformed comparable prior approaches relying on rule-based techniques or traditional machine learning, with a fine-tuned BERT model achieving an F1 Score of 93.4 %. These findings highlight the potential of pre-trained language models in agile requirements engineering, enabling more efficient NFRs identification, reducing manual review burden, and facilitating a viable and efficient approach to address the neglect of NFRs in agile development processes.
引用
收藏
页码:87401 / 87417
页数:17
相关论文
共 66 条
[1]  
Ahmed Mohsin, 2021, Proceedings of the First International Workshop on Intelligent Software Automation. ISEA 2020. Advances in Intelligent Systems and Computing (AISC 1347), P15, DOI 10.1007/978-981-16-1045-5_2
[2]   An NLP-based quality attributes extraction and prioritization framework in Agile-driven software development [J].
Ahmed, Mohsin ;
Khan, Saif Ur Rehman ;
Alam, Khubaib Amjad .
AUTOMATED SOFTWARE ENGINEERING, 2023, 30 (01)
[3]   Quality Requirements in Large-Scale Distributed Agile Projects - A Systematic Literature Review [J].
Alsaqaf, Wasim ;
Daneva, Maya ;
Wieringa, Roel .
REQUIREMENTS ENGINEERING: FOUNDATION FOR SOFTWARE QUALITY, REFSQ 2017, 2017, 10153 :219-234
[4]  
[Anonymous], 2011, ISO/IEC 25010:2011: System and Software Engineering - Systems and Software Quality Requirements and Evaluation (SQuaRE) - System and Software Quality Models
[5]  
Beedle Mike., MANIFESTO AGILE SOFT
[6]   Quality Requirement Documentation Guidelines for Agile Software Development [J].
Behutiye, Woubshet ;
Rodriguez, Pilar ;
Oivo, Markku .
IEEE ACCESS, 2022, 10 :70154-70173
[7]  
Biewald L., 2020, Experiment Tracking with Weights and Biases
[8]   Agile requirements engineering practices: An emprical study [J].
Cao, Lan ;
Ramesh, Balasubramaniam .
IEEE SOFTWARE, 2008, 25 (01) :60-67
[9]   Detecting privacy requirements from User Stories with NLP transfer learning models [J].
Casillo, Francesco ;
Deufemia, Vincenzo ;
Gravino, Carmine .
INFORMATION AND SOFTWARE TECHNOLOGY, 2022, 146
[10]   SMOTE: Synthetic minority over-sampling technique [J].
Chawla, Nitesh V. ;
Bowyer, Kevin W. ;
Hall, Lawrence O. ;
Kegelmeyer, W. Philip .
2002, American Association for Artificial Intelligence (16)