Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
5 results
Search Results
Article Automating Software Size Measurement from Python Code Using Language Models(Springer, 2025) Tenekeci, Samet; Unlu, Huseyin; Gul, Bedir Arda; Keles, Damla; Kuuk, Murat; Demirors, OnurSoftware size is a key input for project planning, effort estimation, and productivity analysis. While pre-trained language models have shown promise in deriving functional size from natural-language requirements, measuring size directly from source code remains under-explored. Yet, code-based size measurement is critical in modern workflows where requirement documents are often incomplete or unavailable, especially in Agile development environments. This exploratory study investigates the use of CodeBERT, a pre-trained bimodal transformer model, for measuring software size directly from Python source code according to two measurement methods: COSMIC Function Points and MicroM. We construct two curated datasets from the Python subset of the CodeSearchNet corpus, and manually annotate each function with its corresponding size. Our experimental results show that CodeBERT can successfully measure COSMIC data movements with up to 91.4% accuracy and generalize to the functional, architectural, and algorithmic event types defined in MicroM, reaching up to 81.5% accuracy. These findings highlight the potential of code-based language models for automated functional size measurement when requirement artifacts are absent or unreliable.Article Citation - WoS: 1Citation - Scopus: 1Automating Software Size Measurement With Language Models: Insights From Industrial Case Studies(Elsevier Science Inc, 2026) Unlu, Huseyin; Tenekeci, Samet; Kennouche, Dhia Eddine; Demirors, OnurObjective software size measurement is critical for accurate effort estimation, yet many organizations avoid it due to high costs, required expertise, and time-consuming manual effort. This often leads to vague predictions, poor planning, and project overruns. To address this challenge, we investigate the use of pre-trained language models - BERT and SE-BERT - to automate size measurement based on textual requirements using COSMIC and MicroM methods. We constructed one heterogeneous dataset and two industrial datasets, each manually measured by experienced analysts. Models were evaluated in three settings: (i) generic model evaluation, where the models are trained and tested on heterogeneous data, (ii) internal evaluation, where the models are trained and tested on organization-specific data, and (iii) external evaluation, where generic models were tested on organization-specific data. Results show that organization-specific models significantly outperform generic models, indicating that aligning training data with the target organization's requirement style is critical for accuracy. SE-BERT, a domain-adapted variant of BERT, improves performance, particularly in low-resource settings. These findings highlight the practical potential of tailoring training data for broader adoption and cost-effective software size measurement in industrial contexts.Conference Object Measuring the Size of Change Requests in Microservice-Based Software Projects(Springer Science and Business Media Deutschland GmbH, 2026) Yenel, M.; Ünlu, H.; Demirors, O.Accurately estimating the effort required for implementing change requests remains a critical challenge in software engineering, especially in microservice-based software architectures (MSSA). Traditional functional size measurement methods often fail to capture the distinct characteristics of MSSAs. To address this limitation, we propose a change size measurement method based on MicroM, a size measurement approach specifically developed for MSSAs. The proposed method counts added, deleted, and modified events across functional, architectural, and algorithmic levels, and includes the number of affected initial requirements. We conducted an exploratory case study with 18 change requests and built four regression-based effort estimation models. The results show that combining event counts with the number of affected requirements improves estimation accuracy. Our method provides a more precise and context-aware way to estimate change-related effort in MSSA projects. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - WoS: 1Citation - Scopus: 1Towards the Construction of a Software Benchmarking Dataset Via Systematic Literature Review(IEEE, 2024) Yurum, Ozan Rasit; Unlu, Huseyin; Demirors, OnurEffort estimation is a fundamental task during the planning of software projects. Prediction models usually rely on two essential factors: software size and effort data. Measuring the size of the software can be done at various stages of the project with desired accuracy. Nevertheless, the industry faces challenges when it comes to collecting reliable actual effort data. Consequently, organizations encounter difficulties in establishing effort prediction models. Benchmarking datasets are available, but, in most cases, they have huge variances that make them less useful for effort prediction. In this study, we aimed to answer whether creating a software benchmarking dataset is possible by gathering the data from the literature. To the best of our knowledge, a comprehensive dataset that gathers the functional size and effort data of the studies from the literature is unavailable. For this purpose, we performed a systematic literature review to find studies that include projects measured with the COSMIC Functional Size Measurement (FSM) method and the related effort. As a result, we formed a dataset including 337 records from 18 studies that shared the corresponding size and effort data. Although we performed a limited search, we created a larger dataset than many datasets in the literature. In light of our review, we obtained that most studies did not share their dataset, and many lacked case details such as implementation environment and the scope of software development life cycle activities included in the effort data. We also compared the dataset with the ISBSG repository and found that our dataset has less variation in productivity. Our review showed the applicability of creating a software benchmarking dataset is possible by gathering the data from the literature. In conclusion, this study addresses gaps in the literature through a cost-free and easily extendable dataset.Conference Object Citation - Scopus: 3Predicting Software Size and Effort From Code Using Natural Language Processing(CEUR-WS, 2024) Tenekeci, S.; Demirörs, Onur; Ünlü, H.; Dikenelli, E.; Selçuk, U.; Kılınç Soylu, G.; Demirörs, O.Software Size Measurement (SSM) holds a crucial role in software project management by facilitating the acquisition of software size, which serves as the primary input for development effort and schedule estimation. However, many small and medium-sized companies encounter challenges in conducting objective SSM and Software Effort Estimation (SEE) due to resource constraints and a lack of expert workforce. This often leads to inaccurate estimates and projects exceeding planned time and budget. Hence, organizations need to perform objective SSM and SEE with minimal resources and without relying on an expert workforce. In this research, we introduce two exploratory case studies aimed at predicting the functional size (COSMIC and Event-based size) and effort of software projects from the code using a deep-learning-based NLP model: CodeBERT. For this purpose, we collected and annotated two datasets consisting of 4800 Python and 1100 C# functions. Then, we trained a classification model to predict COSMIC data movements (entry, exit, read, write) and four regression models to predict Event-based size (interaction, communication, process) and effort. Despite utilizing a relatively small dataset for model training, we achieved promising results with an 84.5% accuracy for the COSMIC size, 0.13 normalized mean absolute error (NMAE) for the Event-based size, and 0.18 NMAE for the effort. These findings are particularly insightful as they demonstrate the practical utility of language models in SSM and SEE. © 2024 Copyright for this paper by its authors.