{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:43:44Z","timestamp":1780357424753,"version":"3.54.1"},"reference-count":26,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Recent advances in natural language processing (NLP) have enabled the automation of Software Requirements Classification (SRC), particularly through fine-tuning models such as Bidirectional Encoder Representations from Transformers (BERTs). While BERT-based models have shown promising results, the impact of hyperparameter sensitivity and dataset size on SRC performance remains underexplored. To address this gap, we present three main contributions: (1) the development and evaluation of BERT fine-tuning for SRC, with emphasis on the effects of key hyperparameters and dataset size; (2) comprehensive experiments to analyze the influence of individual hyperparameters to identify optimal configurations for robust and efficient performance; and (3) controlled experiments highlighting the critical factors that affect the fine-tuning outcomes in SRC, particularly dataset size and hyperparameter sensitivity. Our approach was assessed on two datasets: the PROMISE dataset and FR_NFR, a tailored dataset for the SRC task. The proposed method outperformed baseline models, achieving an average F1-score of 0.99 on PROMISE and 0.97 on FR_NFR. These findings provide empirical evidence on optimization strategies for BERT-based requirements classification and offer practical guidance to software engineering practitioners.<\/jats:p>","DOI":"10.3390\/info16110981","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T17:33:21Z","timestamp":1763141601000},"page":"981","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["BERT  Fine-Tuning for Software Requirement Classification: Impact of Model Components and Dataset Size"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1490-948X","authenticated-orcid":false,"given":"Safaa","family":"Eltahier","sequence":"first","affiliation":[{"name":"Software Engineering Department, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj 11942, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0305-0092","authenticated-orcid":false,"given":"Omer","family":"Dawood","sequence":"additional","affiliation":[{"name":"Computer Engineering and Information Department, College of Engineering in Wadi Aldawasir, Prince Sattam Bin Abdulaziz University, Wadi Aldawasir 11991, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imtithal","family":"Saeed","sequence":"additional","affiliation":[{"name":"Information Systems Department, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj 11942, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ozkaya, M., Kardas, G., and Kose, M.A. (2023). An Analysis of the Features of Requirements Engineering Tools. Systems, 11.","DOI":"10.3390\/systems11120576"},{"key":"ref_2","unstructured":"Wiegers, K.E., Beatty, J., and Wiegers, K.E. (2013). Software Requirements, Microsoft Press. [3rd ed.]. Best practices."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/s10462-023-10667-1","article-title":"The Application of AI Techniques in Requirements Classification: A Systematic Mapping","volume":"57","author":"Kaur","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"124159","DOI":"10.1109\/ACCESS.2021.3052921","article-title":"Identifying Non-Functional Requirements from Unconstrained Documents Using Natural Language Processing and Machine Learning Approaches","volume":"13","author":"Shreda","year":"2025","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2604","DOI":"10.1016\/j.procs.2023.01.234","article-title":"BERT-CNN: Improving BERT for Requirements Classification Using CNN","volume":"218","author":"Kaur","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Luo, X., Xue, Y., Xing, Z., and Sun, J. (2022, January 10\u201314). PRCBERT: Prompt Learning for Requirement Classification Using BERT-Based Pretrained Language Models. Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering, Rochester, MI, USA.","DOI":"10.1145\/3551349.3560417"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kurtanovi\u0107, Z., and Maalej, W. (2017, January 4\u20138). Automatically Classifying Functional and Non-Functional Requirements Using Supervised Machine Learning. Proceedings of the 2017 IEEE 25th International Requirements Engineering Conference (RE), Lisbon, Portugal.","DOI":"10.1109\/RE.2017.82"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"30080","DOI":"10.1109\/ACCESS.2022.3159238","article-title":"Automatic Requirements Classification Based on Graph Attention Network","volume":"10","author":"Li","year":"2022","journal-title":"IEEE Access"},{"key":"ref_9","unstructured":"Dalpiaz, F., and Spoletini, P. (2021). Automatically Classifying Non-Functional Requirements with Feature Extraction and Supervised Machine Learning Techniques: A Research Preview. Proceedings of the Requirements Engineering: Foundation for Software Quality, Virtual, 12\u201315 April 2021, Springer International Publishing."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Abad, Z.S.H., Karras, O., Ghazi, P., Glinz, M., Ruhe, G., and Schneider, K. (2017, January 4\u20138). What Works Better? A Study of Classifying Requirements. Proceedings of the 2017 IEEE 25th International Requirements Engineering Conference (RE), Lisbon, Portugal.","DOI":"10.1109\/RE.2017.36"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Haque, M.A., Rahman, M.A., and Siddik, M.S. (2019, January 3\u20135). Non-Functional Requirements Classification with Feature Extraction and Machine Learning: An Empirical Study. Proceedings of the 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), Dhaka, Bangladesh.","DOI":"10.1109\/ICASERT.2019.8934499"},{"key":"ref_12","first-page":"85","article-title":"Mining Non-Functional Requirements Using Machine Learning Techniques","volume":"15","author":"Jindal","year":"2021","journal-title":"e-Inform. Softw. Eng. J."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4955691","DOI":"10.1155\/2024\/4955691","article-title":"Enhancing Software Requirements Classification with Semisupervised GAN-BERT Technique","volume":"2024","author":"Airlangga","year":"2024","journal-title":"J. Electr. Comput. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Navarro-Almanza, R., Juarez-Ramirez, R., and Licea, G. (2017, January 25\u201327). Towards Supporting Software Engineering Using Deep Learning: A Case of Software Requirements Classification. Proceedings of the 2017 5th International Conference in Software Engineering Research and Innovation (CONISOFT), Merida, Mexico.","DOI":"10.1109\/CONISOFT.2017.00021"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Baker, C., Deng, L., Chakraborty, S., and Dehlinger, J. (2019, January 15\u201319). Automatic Multi-Class Non-Functional Software Requirements Classification Using Neural Networks. Proceedings of the 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC), Milwaukee, WI, USA.","DOI":"10.1109\/COMPSAC.2019.10275"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kici, D., Malik, G., Cevik, M., Parikh, D., and Ba\u015far, A. (2021, January 25\u201328). A BERT-Based Transfer Learning Approach to Text Classification on Software Requirements Specifications. Proceedings of the 34th Canadian Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.21428\/594757db.a4880a62"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Hey, T., Keim, J., Koziolek, A., and Tichy, W.F. (September, January 31). NoRBERT: Transfer Learning for Requirements Classification. Proceedings of the 2020 IEEE 28th International Requirements Engineering Conference (RE), Zurich, Switzerland.","DOI":"10.1109\/RE48521.2020.00028"},{"key":"ref_18","unstructured":"(2017, January 4\u20138). PURE: A Dataset of Public Requirements Documents. Proceedings of the 2017 IEEE 25th International Requirements Engineering Conference (RE), Lisbon, Portugal. Available online: https:\/\/ieeexplore.ieee.org\/document\/8049173."},{"key":"ref_19","unstructured":"Sonali, S., and Thamada, S. FR_NFR_Dataset 2024. Available online: https:\/\/data.mendeley.com\/datasets\/4ysx9fyzv4\/1."},{"key":"ref_20","unstructured":"Burstein, J., Doran, C., and Solorio, T. (2019). BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Minnesota, 3\u20135 June 2019, Association for Computational Linguistics. Volume 1 (Long and Short Papers)."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1007\/s10462-025-11162-5","article-title":"BERT Applications in Natural Language Processing: A Review","volume":"58","author":"Gardazi","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_22","unstructured":"Kingma, D.P., and Ba, J. (2017). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Gkouti, N., Malakasiotis, P., Toumpis, S., and Androutsopoulos, I. (2024). Should I Try Multiple Optimizers When Fine-Tuning Pre-Trained Transformers for NLP Tasks? Should I Tune Their Hyperparameters?. arXiv.","DOI":"10.18653\/v1\/2024.eacl-long.157"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"110632","DOI":"10.1016\/j.engappai.2025.110632","article-title":"Aspect-Based Sentiment Analysis for Software Requirements Elicitation Using Fine-Tuned Bidirectional Encoder Representations from Transformers and Explainable Artificial Intelligence","volume":"151","author":"Taj","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_25","unstructured":"Mosbach, M., Andriushchenko, M., and Klakow, D. (2021). On the Stability of Fine-Tuning BERT: Misconceptions, Explanations, and Strong Baselines. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ferrari, A., and Ginde, G. (2025). Machine Learning for Requirements Classification. Handbook on Natural Language Processing for Requirements Engineering, Springer Nature.","DOI":"10.1007\/978-3-031-73143-3"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/11\/981\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T17:35:50Z","timestamp":1763141750000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/11\/981"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,13]]},"references-count":26,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["info16110981"],"URL":"https:\/\/doi.org\/10.3390\/info16110981","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,13]]}}}