Information and Software Technology最新文献

{"title":"Required knowledge, skills and transversal competences for a career in software engineering","authors":"Nikolaos Mittas ,&nbsp;Dimitrios Trygoniaris ,&nbsp;Apostolos Ampatzoglou ,&nbsp;Elvira-Maria Arvanitou ,&nbsp;Christina Volioti ,&nbsp;Alexander Chatzigeorgiou ,&nbsp;Lefteris Angelis","doi":"10.1016/j.infsof.2025.107949","DOIUrl":"10.1016/j.infsof.2025.107949","url":null,"abstract":"<div><h3>Context</h3><div>Possessing up-to-date knowledge, skills and transversal competencies (KSTs) is essential for both the successful delivery of software projects and a career in software engineering (SE). However, the technological landscape is changing rapidly, posing continuous challenges: for professionals entering the market or pivoting careers, for organizations hiring and monitoring workforce expertise and for educational institutes designing or updating their curricula.</div></div><div><h3>Objectives</h3><div>We study job requirements within and across SE occupations (Applications Programmers, Software Developers, Systems Analysts, Web and Multimedia Developers) to assist software organizations to better face skill mismatch and skills’ gap problems, software engineers in upskilling and reskilling endeavors and software education institutes in providing more industrially relevant curricula.</div></div><div><h3>Method</h3><div>In this study, we leverage a large corpus of online job advertisements, which are jointly collected by CEDEFOP and Eurostat. The dataset is analyzed through the lens of concepts and techniques from the study of biodiversity of species to assess the variation of expertise and identify skills that are transferable or unique in these occupations. Specifically, we adopt established diversity indices, such as alpha diversity, beta diversity, ordination methods, and indicator species analysis, aiming to quantify both the variety of skills within occupations and the differences across them. This approach highlights both the breadth and distinctiveness of expertise across occupations, rendering the biodiversity perspective a central and practical part of our methodology.</div></div><div><h3>Results</h3><div>The results reveal that the complete list of KSTs that is used to characterize the profiles of OJAs for SE-related occupations is very broad and that skillset required for each occupation is quite distinct, since there are statistically significant differences in the composition of the skillsets. Transversal Skills and Competences (T) appear to be the most transferable qualification; or “adapt to change” and “work in teams” are the KSTs that appears more uniformly to all studied software occupations, and “computer programming” is the top hard-skill that appears more uniformly to all occupations. However, each occupation shows some specific qualifications.</div></div><div><h3>Conclusion</h3><div>The results are contrasted against the literature, are interpreted, various implications to researchers and practitioners are provided, and a retrospective analysis of the tailoring of the biodiversity approach to SE labor landscape is provided. Overall, the proposed biodiversity analysis adds value by providing a novel, theory-driven methodology to assess skill variation, identifying both common and occupation-specific KSTs, and supporting evidence-based workforce and curriculum design.</div></div>","PeriodicalId":54983,"journal":{"name":"Information and Software Technology","volume":"190 ","pages":"Article 107949"},"PeriodicalIF":4.3,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145420378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SELink: A semantic-enhanced modular framework for issue–commit link recovery","authors":"Tao Zheng ,&nbsp;Yangyang Zhao ,&nbsp;Jiamin Guo ,&nbsp;Liming Nie ,&nbsp;Mingyue Jiang ,&nbsp;Yuming Zhou","doi":"10.1016/j.infsof.2025.107973","DOIUrl":"10.1016/j.infsof.2025.107973","url":null,"abstract":"<div><h3>Context:</h3><div>Issue–commit link recovery (ICLR) is a fundamental task in software traceability that aims to reconstruct missing or incomplete links between issue reports and code commits. Accurate link recovery supports downstream tasks such as bug localization, defect prediction, and change impact analysis. However, existing approaches often suffer from input truncation and limited semantic discrimination, which reduce their effectiveness in real-world settings.</div></div><div><h3>Objective:</h3><div>This study aims to improve the robustness and precision of issue–commit link recovery by addressing two key challenges: (1) the loss of semantic information caused by token truncation in long textual inputs, and (2) the difficulty of accurately ranking semantically similar candidate commits.</div></div><div><h3>Methods:</h3><div>We propose SELink, a Semantic-Enhanced framework that integrates large language models into the ICLR pipeline. SELink comprises three key components: a semantic summarization module that compresses verbose texts while preserving core semantics; a prediction module based on a pre-trained encoder, with flexibility to adopt various backbone models; and a semantic re-ranking module that refines the top-K candidate links through decoder-only LLM inference. In our implementation, the prediction module is instantiated using the EALink framework, though it can be substituted with other compatible encoders.</div></div><div><h3>Results:</h3><div>Experimental results show that SELink significantly outperforms state-of-the-art baseline models across most evaluation metrics and projects. In particular, it achieves notable improvements in Hit@1, NDCG@1, Recall@1 and LAG, highlighting its effectiveness in top-rank prediction accuracy. Ablation studies confirm the contribution of each module, and additional experiments across three different LLMs demonstrate the framework’s adaptability.</div></div><div><h3>Conclusion:</h3><div>SELink effectively addresses two long-standing limitations in issue–commit link recovery by leveraging LLM-based semantic compression and re-ranking. Its modular design and superior performance suggest that semantic-enhanced frameworks hold significant potential for advancing traceability tasks in software engineering.</div></div>","PeriodicalId":54983,"journal":{"name":"Information and Software Technology","volume":"190 ","pages":"Article 107973"},"PeriodicalIF":4.3,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145571288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fairness set and forgotten: Mining fairness toolkit usage in open-source machine learning projects","authors":"Alfonso Cannavale,&nbsp;Gianmario Voria,&nbsp;Antonio Scognamiglio,&nbsp;Giammaria Giordano,&nbsp;Gemma Catolino,&nbsp;Fabio Palomba","doi":"10.1016/j.infsof.2025.107957","DOIUrl":"10.1016/j.infsof.2025.107957","url":null,"abstract":"<div><h3>Context:</h3><div>The development of machine learning (ML) systems in high-stakes domains has amplified concerns about fairness, prompting the creation of fairness toolkits offering metrics and mitigation techniques. Open-source software (OSS) ecosystems, a critical driver of AI innovation, present a unique opportunity to study the practical adoption of these toolkits.</div></div><div><h3>Objective:</h3><div>This paper aims to empirically characterize the adoption of fairness toolkits in OSS ML projects by investigating <em>for what purposes</em> they are used and <em>how</em> their usage evolves over time.</div></div><div><h3>Methods:</h3><div>We conducted a mining study on <span>GitHub</span> repositories related to real-world ML projects that integrate fairness toolkits such as <span>AIF360</span> and <span>Fairlearn</span>. Starting from 1,096 candidate repositories, we applied systematic filtering to identify a final dataset of 20 relevant ML projects (comprising 5,777 total commits). We analyzed toolkit usage by examining invoked APIs and commit histories to uncover patterns of adoption and evolution.</div></div><div><h3>Results:</h3><div>Our findings reveal that fairness toolkits are predominantly used for diagnostic purposes, with analytic components integrated early in the project lifecycle and rarely modified thereafter. In contrast, mitigation techniques are infrequently adopted, tend to appear later, and exhibit short, unstable lifespans.</div></div><div><h3>Conclusion:</h3><div>Our results show that the adoption of fairness toolkits in OSS ML projects is limited and often restricted to initial diagnostic phases, with active mitigation practices remaining rare. These findings highlight the need for improved support to foster more sustained and effective integration of fairness practices within open-source development.</div></div>","PeriodicalId":54983,"journal":{"name":"Information and Software Technology","volume":"190 ","pages":"Article 107957"},"PeriodicalIF":4.3,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145468020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using LLMs to enhance code quality: A systematic literature review","authors":"Nawaf Alomari ,&nbsp;Moussa Redah ,&nbsp;Ahmad Ashraf ,&nbsp;Mohammad Alshayeb","doi":"10.1016/j.infsof.2025.107960","DOIUrl":"10.1016/j.infsof.2025.107960","url":null,"abstract":"<div><h3>Context:</h3><div>Large Language Models (LLMs) are increasingly used in software engineering to enhance code quality through tasks such as refactoring and code smell detection and many other tasks. Code smells are poor design decisions that can be resolved by changing the internal structure of the code without affecting its output, a process known as refactoring.</div></div><div><h3>Objective:</h3><div>This study systematically reviews the use of LLMs in code quality enhancement, focusing on techniques such as refactoring, smell detection, and other code improvement methods.</div></div><div><h3>Method:</h3><div>Using SLR techniques, we reviewed 49 studies up to September 2024, analyzing both qualitative and quantitative data to assess trends and effectiveness.</div></div><div><h3>Results:</h3><div>The field is active, with refactoring as the most common task, followed by smell detection. Refactored code by LLMs is not reliable. Prompting is used more frequently than fine-tuning, with few-shot learning as the leading prompting method. Java and Python are the most represented languages, while F1, Precision, Recall, and Accuracy are common evaluation metrics, along with BLEU and EM for generation tasks. Open-source and general language models are preferred, with validation datasets as the primary validation approach.</div></div><div><h3>Conclusions:</h3><div>LLMs show promise for code quality improvement, but challenges in optimization and reliability remain. Future research should prioritize fine-tuning for refactoring, linking LLMs to specific quality attributes, developing benchmark datasets, constructing datasets for diverse programming languages, and exploring a wider range of promoting techniques.</div></div>","PeriodicalId":54983,"journal":{"name":"Information and Software Technology","volume":"190 ","pages":"Article 107960"},"PeriodicalIF":4.3,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145571427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CPMT: A collaborative metamorphic relations and test cases prioritization approach for Metamorphic Testing","authors":"Chang-ai Sun,&nbsp;Shifan Liu,&nbsp;An Fu,&nbsp;Jiaming Zhang","doi":"10.1016/j.infsof.2025.107975","DOIUrl":"10.1016/j.infsof.2025.107975","url":null,"abstract":"<div><h3>Context:</h3><div>Metamorphic Testing (MT) is a widely adopted software testing technique that addresses the <em>oracle problem</em> by leveraging Metamorphic Relations (MRs). Various test case prioritization (TCP) techniques have been developed to improve the fault detection efficiency by scheduling the execution order of test cases. However, these techniques cannot be directly applied to MT due to its unique features, such as involving the execution of source and follow-up test cases, application of MRs, and the result verification depends on the availability of the corresponding outputs.</div></div><div><h3>Objective:</h3><div>This study aims to improve the fault detection efficiency of MT by developing a collaborative prioritization approach called <em>CPMT</em> that considers the scheduling of both MRs and test cases.</div></div><div><h3>Methods:</h3><div>We first formulate the prioritization problem in MT and then propose to schedule the execution of MRs and test cases based on three strategies, which prioritize the execution of MRs and test cases with a higher potential of fault detection from the different perspectives, including the contributions to specification/implementation coverage, the strictness of output relation, and the earlier detection opportunities.</div></div><div><h3>Results:</h3><div>Extensive experiments were conducted on seven subject programs to evaluate the effectiveness of <em>CPMT</em>. The experimental results have demonstrated that the proposed approach significantly improved the fault detection efficiency and outperformed the baseline techniques.</div></div><div><h3>Conclusion:</h3><div><em>CPMT</em> provides a promising way to improve the fault detection efficiency of MT.</div></div>","PeriodicalId":54983,"journal":{"name":"Information and Software Technology","volume":"190 ","pages":"Article 107975"},"PeriodicalIF":4.3,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145617875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"KIBO, a new hybrid software development method with enhanced information systems auditing capability","authors":"Ioannis Kirpitsas,&nbsp;Theodore Pachidis","doi":"10.1016/j.infsof.2025.107958","DOIUrl":"10.1016/j.infsof.2025.107958","url":null,"abstract":"<div><h3>Context</h3><div>The agile revolution has transformed software development, accelerating the adoption of hybrid methods that combine agile and traditional plan-driven practices. These methods offer IT organizations speed and flexibility. However, they can increase governance complexity and complicate value assurance, which is defined here as protecting business value through auditable compliance.</div></div><div><h3>Objective</h3><div>This paper introduces KIBO, a hybrid software development method. This method embeds auditability that is aligned with COBIT 2019 objectives, the industry-standard framework for IT governance and management, offering more robust control processes than existing methods.</div></div><div><h3>Method</h3><div>KIBO integrates Scrum, DevOps, and Disciplined Agile Delivery with governance principles through three practices. First, it incorporates IT controls from sprint planning. Second, it applies structured application lifecycle management elements for transparency and traceability. Third, it offers a centralized information systems audit hub that enables continuous auditing. The method was validated in two stages. Initially, the theoretical model was assessed by 90 experts against existing hybrid methods using selected COBIT 2019 objectives as reference criteria. Subsequently, a practical evaluation validated expectations derived from this theoretical assessment.</div></div><div><h3>Results</h3><div>Theoretical assessment indicates that KIBO enhances IT governance, risk management, and quality. During a 7-week deployment at a leading Southeastern European digital services organization, delivery accelerated by 6.4 % to reach the 95 % epic completion threshold, while issue density decreased by 17.9 % compared to organizational averages. Additionally, the team reported improved quality, process reliability, and net developer satisfaction in practice.</div></div><div><h3>Conclusion</h3><div>The evaluation suggests KIBO can enhance governance in agile development by supporting alignment with business objectives, improving process efficiency, and strengthening audit readiness. Although challenges remain in role integration and security oversight, KIBO helps balance agility and control. We recommend broader deployments to validate and further extend these positive outcomes.</div></div>","PeriodicalId":54983,"journal":{"name":"Information and Software Technology","volume":"190 ","pages":"Article 107958"},"PeriodicalIF":4.3,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145468024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The role of voice and silence behaviors in software development: a structural equation modeling analysis","authors":"Mary Sánchez-Gordón ,&nbsp;Ricardo Colomo-Palacios ,&nbsp;Alex Sanchez Gordon ,&nbsp;Aliaksandr Hubin","doi":"10.1016/j.infsof.2025.107972","DOIUrl":"10.1016/j.infsof.2025.107972","url":null,"abstract":"<div><h3>Context</h3><div>Most software companies strive to have high-performing teams and mitigate withdrawal behaviors like being present but unproductive. In this context, psychological safety and developers’ perceived impact are suggested as potential drivers of voice and silence behaviors. However, understanding these social aspects of software development entails the incorporation of social science theories.</div></div><div><h3>Objective</h3><div>This study aims to empirically explore the relationships among software professionals’ perceived impact, psychological safety, voice and silence behaviors, burnout particularly withdrawal and performance using a theoretical model.</div></div><div><h3>Method</h3><div>A survey questionnaire was conducted, resulting in 158 valid responses from software development teams. Then, we analyzed the responses using structural equation modeling (SEM) and a novel semi-confirmatory SEM. All variables were measured using pre-validated instruments.</div></div><div><h3>Results</h3><div>The findings supported the theoretical model, showing that psychological safety was more related to silence than voice, whereas perceived impact showed a stronger relationship with voice than with silence. Furthermore, silence contributed to higher burnout, whereas voice alleviated it. In contrast, silence showed a negative association with performance, whereas voice was positively associated with it.</div></div><div><h3>Conclusions</h3><div>This study examines the direct effects of perceived impact and psychological safety on voice and silence behaviors. Additionally, it examines the direct effects of these behaviors on burnout and task performance among software professionals. Consequently, the findings offer both theoretical and practical insights.</div></div>","PeriodicalId":54983,"journal":{"name":"Information and Software Technology","volume":"190 ","pages":"Article 107972"},"PeriodicalIF":4.3,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145617876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detecting Slow Loop smell by using deep learning: From direct-learning to transfer-learning in cross-language settings","authors":"Yuqi Li ,&nbsp;Ruonan Ma ,&nbsp;Yixin Bian ,&nbsp;Weijie Chen ,&nbsp;Lin Huang ,&nbsp;Jiaying Li ,&nbsp;Federica Sarro","doi":"10.1016/j.infsof.2025.107976","DOIUrl":"10.1016/j.infsof.2025.107976","url":null,"abstract":"<div><h3>Context:</h3><div>Code smells are symptoms of poor quality code that hinder software maintenance and evolution. Although most existing studies have focused on Object-Oriented code smells, limited attention has been paid to Android-specific smells, particularly in Kotlin-based Android applications.</div></div><div><h3>Objective:</h3><div>To identify Android-specific code smells, with a focus on the Slow Loop smell in both Java-based and Kotlin-based Android apps.</div></div><div><h3>Methods:</h3><div>This paper presents a novel deep learning–based approach for identifying the Slow Loop smell in both Java-based and Kotlin-based Android apps. We propose a two-phase strategy that integrates direct-learning and transfer-learning. In the first phase, Slow Loop smells are identified in Java-based Android applications using a custom tool, Android-specific Smell Detection, which generates labeled training samples. These samples are tokenized and used to train five deep learning models, namely CNN, RNN, CNN-LSTM, and two variants of autoencoders. In the second phase, a transfer-learning mechanism adapts Java-trained models to Kotlin-based applications, thus enabling cross-language detection. The effectiveness of the approach is empirically validated in 80 Java and 90 Kotlin applications, using precision, recall, F1-score, and MCC as evaluation metrics.</div></div><div><h3>Results:</h3><div>The findings indicate that deep learning methods can be used to detect Android-specific code smells in Java-developed Android applications. In addition, transfer-learning successfully enables Kotlin smell detection, achieving competitive performance without the need for Kotlin-specific training from scratch.</div></div><div><h3>Conclusions:</h3><div>This study demonstrates the feasibility of applying transfer-learning to cross-language code smell detection. It contributes a scalable framework to identify Android-specific smells and provides new insights into improving code quality in mobile software development.</div></div>","PeriodicalId":54983,"journal":{"name":"Information and Software Technology","volume":"190 ","pages":"Article 107976"},"PeriodicalIF":4.3,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145617877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GreenDFL: A framework for assessing the sustainability of Decentralized Federated Learning systems","authors":"Chao Feng ,&nbsp;Alberto Huertas Celdrán ,&nbsp;Xi Cheng ,&nbsp;Gérôme Bovet ,&nbsp;Burkhard Stiller","doi":"10.1016/j.infsof.2025.107937","DOIUrl":"10.1016/j.infsof.2025.107937","url":null,"abstract":"<div><h3>Context:</h3><div>Decentralized Federated Learning (DFL) is an emerging paradigm that enables collaborative model training without centralized data and model aggregation, enhancing privacy and resilience. However, its sustainability remains underexplored, as energy consumption and carbon emissions vary across different system configurations. Understanding the environmental impact of DFL is crucial for optimizing its design and deployment.</div></div><div><h3>Objective:</h3><div>This work aims to develop a comprehensive and operational framework for assessing the sustainability of DFL systems. To address it, this work provides a systematic method for quantifying energy consumption and carbon emissions, offering insights into improving the sustainability of DFL.</div></div><div><h3>Methods:</h3><div>This work proposes <em>GreenDFL</em>, a fully implementable framework that has been integrated into a real-world DFL platform. <em>GreenDFL</em> systematically analyzes the impact of various factors, including hardware accelerators, model architecture, communication medium, data distribution, network topology, and federation size, on the sustainability of DFL systems. Besides, a sustainability-aware aggregation algorithm (<em>GreenDFL-SA</em>) and a node selection algorithm (<em>GreenDFL-SN</em>) are developed to optimize energy efficiency and reduce carbon emissions in DFL training.</div></div><div><h3>Results:</h3><div>Empirical experiments are conducted on multiple datasets, measuring energy consumption and carbon emissions at different phases of the DFL lifecycle. Results indicate that local training dominates energy consumption and carbon emissions, while communication has a relatively minor impact. Optimizing model complexity, using GPUs instead of CPUs, and strategically selecting participating nodes significantly improve sustainability. Additionally, using wired communication, particularly optical fiber, effectively reduces energy consumption during the communication phase, while integrating early stopping mechanisms further minimizes overall emissions.</div></div><div><h3>Conclusion:</h3><div>The proposed <em>GreenDFL</em> provides a comprehensive and practical approach for assessing the sustainability of DFL systems. Furthermore, it offers best practices for improving environmental efficiency in DFL, making sustainability considerations more actionable in real-world deployments.</div></div>","PeriodicalId":54983,"journal":{"name":"Information and Software Technology","volume":"190 ","pages":"Article 107937"},"PeriodicalIF":4.3,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145371152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-project software defects prediction using fuzzy embedding and deep learning","authors":"Mohammad Azzeh ,&nbsp;Mohammad J. Abdel-Rahman","doi":"10.1016/j.infsof.2025.107968","DOIUrl":"10.1016/j.infsof.2025.107968","url":null,"abstract":"<div><h3>Context:</h3><div>Cross-project defect prediction (CPDP) aims to predict software defects in a target project using data from related source projects, especially when defect data for the target project is limited or unavailable. A key challenge in CPDP is data heterogeneity and distributional differences across projects, which often lead to poor performance and unreliable predictions.</div></div><div><h3>Objectives:</h3><div>This study proposes a new CPDP model that improves prediction accuracy and robustness by introducing fuzzy embedding and deep learning to better capture similarities and differences across projects. The method is designed to mitigate mismatches in data distribution that hinder existing transfer learning and transformation-based approaches.</div></div><div><h3>Methods:</h3><div>The fuzzy embedding technique is built on fuzzy clustering and fuzzy set theory, which map each data point into a two-dimensional space of membership degrees across clusters. This representation models complex relationships with partial memberships and preserves contextual information that is often lost in conventional transformations. A deep learning model based on convolutional neural networks (CNN) processes the embedding matrices to learn discriminative defect patterns. The framework is evaluated against state-of-the-art CPDP models across multiple datasets, and sensitivity analysis is conducted on the number of clusters used in fuzzy embeddings.</div></div><div><h3>Results:</h3><div>Empirical evaluation shows that the proposed model consistently outperforms advanced CPDP approaches that rely on standard transformation or weighting methods. Improvements are observed in AUC and other key metrics across diverse datasets, demonstrating that fuzzy embeddings enhance the ability of deep learning to generalize knowledge across projects with varying characteristics.</div></div><div><h3>Conclusion:</h3><div>This work contributes a practical and effective solution for addressing heterogeneity in CPDP. By combining fuzzy embeddings with deep learning, the model not only achieves higher predictive accuracy but also improves reliability in real-world scenarios where project data distributions differ significantly. These findings highlight the potential of fuzzy embedding to support more resilient software quality assurance practices and provide actionable insights for practitioners dealing with limited or imbalanced defect data.</div></div>","PeriodicalId":54983,"journal":{"name":"Information and Software Technology","volume":"190 ","pages":"Article 107968"},"PeriodicalIF":4.3,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145468021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}