Developing an Advanced Software Requirements Classification Model Using BERT: An Empirical Evaluation Study on Newly Generated Turkish Data
Year: 2023
Type: article
Abstract: Requirements Engineering (RE) is an important step in the whole software development lifecycle. The problem in RE is to determine the class of the software requirements as functional and non-functional. Proper and early identification of these requirements is vital for the entire development cycle. On the other hand, manual government of requirement classes is a timewasting task, and it needs intensive effort. Automatic requirement classification techniques through advanced Machine Learning (ML) strategies are started to be developed to address this problem. Basically, software requirements are generated as natural language explanations and therefore requirement classification may be handled as a particular Natural Language Processing (NLP) problem. From ML point of view, classification strategies require dataset to be used in the training/learning phase. For this goal, we generated a unique Turkish dataset having collected the requiremenst from real-world software projects with 4600 samples. Of these requirements, 3000 and 1600 were labeled as functional and non-functional, respectively. The data set has been evaluated using (i) traditional machine learning algorithms, (ii) deep learning algorithms, and (iii) transformer models respectively. As a result BERTurk was found to be the most successful algorithm to discriminate functional and non-functional requirements in terms of 95% f-score metric.
Source: Applied Sciences
DOI: 10.3390/app132011127
Author: Fatih Yucalar
Institution: Manisa Celal Bayar University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,558
OpenAlex ID: W4387476559