arXiv subjects

Luiz Fernando Capretz

Publications and source records attributed to Luiz Fernando Capretz.

At least 19 recordsLinked to original sources

arXiv2025

WIP: Assessing the Effectiveness of ChatGPT in Preparatory Testing Activities

This innovative practice WIP paper describes a research study that explores the integration of ChatGPT into the software testing curriculum and evaluates its effectiveness compared to human-generated testing artifacts. In a Capstone Project course, students were tasked with generating preparatory testing artifacts using ChatGPT prompts, which they had previously created manually. Their understanding and the effectiveness of the Artificial Intelligence generated artifacts were assessed through targeted questions. The results, drawn from this in-class assignment at a North American community college indicate that while ChatGPT can automate many testing preparation tasks, it cannot fully replace human expertise. However, students, already familiar with Information Technology at the postgraduate level, found the integration of ChatGPT into their workflow to be straightforward. The study suggests that AI can be gradually introduced into software testing education to keep pace with technological advancements.

cs.SE↗

arXiv2024

Establishing Software Engineering Design Competence with Soft Skills

For a long time, it has been recognized that the software industry has a demand for students who are well grounded in design competencies and who are ready to contribute to a project with little additional training. In response to the industry needs, an engineering design course has been developed for senior level students enrolled in the software engineering program in Canada. The goals of the course are to provide a realistic design experience, introduce students to industry culture, improve their time management skills, challenge them technically and intellectually, improve their communication skills, raise student level of professionalism, hone their soft skills, and raise awareness of human factors in software engineering. This work discusses the details of how this design course has been developed and delivered, and the learning outcomes that has been obtained.

cs.SE↗

arXiv2024

Further Evaluations of a Didactic CPU Visual Simulator (CPUVSIM)

This paper discusses further evaluations of the educational effectiveness of an existing CPU visual simulator (CPUVSIM). The CPUVSIM, as an Open Educational Resource, has been iteratively improved over a number of years following an Open Pedagogy approach, and was designed to enhance novices understanding of computer operation and mapping from high-level code to assembly language. The literature reports previous evaluations of the simulator, at K12 and undergraduate level, conducted from the perspectives of both developers and students, albeit with a limited sample size and primarily through qualitative methods. This paper describes additional evaluation activities designed to provide a more comprehensive assessment, across diverse educational settings: an action research pilot study recently carried out in Singapore and the planning of a more quantitative-oriented study in Dubai, with a larger sample size. Results from the pilot study in Singapore confirm the effectiveness and high level of appreciation of the tool, alongside a few identified challenges, which inform the planning of the more comprehensive evaluation in Dubai.

cs.AR↗

arXiv2024

Feature Importance in the Context of Traditional and Just-In-Time Software Defect Prediction Models

Software defect prediction models can assist software testing initiatives by prioritizing testing error-prone modules. In recent years, in addition to the traditional defect prediction model approach of predicting defects from class, modules, etc., Just-In-Time defect prediction research, which focuses on the change history of software products is getting prominent. For building these defect prediction models, it is important to understand which features are primary contributors to these classifiers. This study considered developing defect prediction models incorporating the traditional and the Just-In-Time approaches from the publicly available dataset of the Apache Camel project. A multi-layer deep learning algorithm was applied to these datasets in comparison with machine learning algorithms. The deep learning algorithm achieved accuracies of 80% and 86%, with the area under receiving operator curve (AUC) scores of 66% and 78% for traditional and Just-In-Time defect prediction, respectively. Finally, the feature importance of these models was identified using a model-specific integrated gradient method and a model-agnostic Shapley Additive Explanation (SHAP) technique.

cs.SE↗

arXiv2024

Unbiasing on the Fly: Explanation-Guided Human Oversight of Machine Learning System Decisions

The widespread adoption of ML systems across critical domains like hiring, finance, and healthcare raises growing concerns about their potential for discriminatory decision-making based on protected attributes. While efforts to ensure fairness during development are crucial, they leave deployed ML systems vulnerable to potentially exhibiting discrimination during their operations. To address this gap, we propose a novel framework for on-the-fly tracking and correction of discrimination in deployed ML systems. Leveraging counterfactual explanations, the framework continuously monitors the predictions made by an ML system and flags discriminatory outcomes. When flagged, post-hoc explanations related to the original prediction and the counterfactual alternatives are presented to a human reviewer for real-time intervention. This human-in-the-loop approach empowers reviewers to accept or override the ML system decision, enabling fair and responsible ML operation under dynamic settings. While further work is needed for validation and refinement, this framework offers a promising avenue for mitigating discrimination and building trust in ML systems deployed in a wide range of domains.

cs.AI↗

arXiv2024

Cascade Generalization-based Classifiers for Software Defect Prediction

The process of software defect prediction (SDP) involves predicting which software system modules or components pose the highest risk of being defective. The projections and discernments derived from SDP can then assist the software development team in effectively allocating its finite resources toward potentially susceptible defective modules. Because of this, SDP models need to be improved and refined continuously. Hence, this research proposes the deployment of a cascade generalization (CG) function to enhance the predictive performances of machine learning (ML)-based SDP models. The CG function extends the initial sample space by introducing new samples into the neighbourhood of the distribution function generated by the base classification algorithm, subsequently mitigating its bias. Experiments were conducted to investigate the effectiveness of CG-based Naïve Bayes (NB), Decision Tree (DT), and k-Nearest Neighbor (kNN) models on NASA software defect datasets. Based on the experimental results, the CG-based models (CG-NB, CG-DT, CG-kNN) were superior in prediction performance when compared with the baseline NB, DT, and kNN models respectively. Accordingly, the average accuracy value of CG-NB, CG-DT, and CG-kNN models increased by +11.06%, +3.91%, and +5.14%, respectively, over baseline NB, DT, and kNN models. A similar performance was observed for the area under the curve (AUC) value with CG-NB, CG-DT, and CG-kNN recording an average AUC value of +7.98%, +26%, and +24.9% improvement over the baseline NB, DT, and kNN respectively. In addition, the suggested CG-based models outperformed the Bagging and Boosting ensemble variants of the NB, DT, and kNN models as well as existing computationally diverse SDP models.

cs.SE↗

arXiv2024

Factors Influencing Performance of Students in Software Automated Test Tools Course

Formal software testing education is important for building efficient QA professionals. Various aspects of quality assurance approaches are usually covered in courses for training software testing students. Automated Test Tools is one of the core courses in the software testing post-graduate curriculum due to the high demand for automated testers in the workforce. It is important to understand which factors are affecting student performance in the automated testing course to be able to assist the students early on based on their needs. Various metrics that are considered for predicting student performance in this testing course are student engagement, grades on individual deliverables, and prerequisite courses. This study identifies the impact of assessing students based on individual vs. group activities, theoretical vs. practical components, and the effect of having taken prerequisite courses in their final grade. To carry out this research, student data was collected from the automated test tools course of a community college-based postgraduate certificate program in software testing. The dataset contained student records from the years 2021 to 2022 and consisted of information from five different semesters. Various machine learning algorithms were applied to develop an effective model for predicting students performance in the automated software testing tools course, and finally, important features affecting the students performance were identified. The predictive performance model of the automated test tools course that was developed by applying the logistic regression technique, showed the best performance, with an accuracy score of 90%.

cs.SE↗

arXiv2024

Mapping the Invisible: A Framework for Tracking COVID-19 Spread Among College Students with Google Location Data

The COVID-19 pandemic and the implementation of social distancing policies have rapidly changed people's visiting patterns, as reflected in mobility data that tracks mobility traffic using location trackers on cell phones. However, the frequency and duration of concurrent occupancy at specific locations govern the transmission rather than the number of customers visiting. Therefore, understanding how people interact in different locations is crucial to target policies, inform contact tracing, and prevention strategies. This study proposes an efficient way to reduce the spread of the virus among on-campus university students by developing a self-developed Google History Location Extractor and Indicator software based on real-world human mobility data. The platform enables policymakers and researchers to explore the possibility of future developments in the epidemic's spread and simulate the outcomes of human mobility and epidemic state under different epidemic control policies. It offers functions for determining potential contacts, assessing individual infection risks, and evaluating the effectiveness of on-campus policies. The proposed multi-functional platform facilitates the screening process by more accurately targeting potential virus carriers and aids in making informed decisions on epidemic control policies, ultimately contributing to preventing and managing future outbreaks.

cs.SE↗

arXiv2023

Integrating Traditional CS Class Activities with Computing for Social Good, Ethics, and Communication and Leadership Skills

Software and information technologies are becoming increasingly integrated and pervasive in human society and range from automated decision making and social media and entertainment, to running critical social and physical infrastructures like government programs, utilities, and financial institutions. As a result, there is a growing awareness of the need to develop professionals who will harness these technologies in fair and inclusive ways and use them to address global issues like health, water management, poverty, and human rights. In this regard, many academic researchers have expressed the need to complement traditional teaching of CS technical skills with computer and information ethics (computing for social good), as well as communication and leadership skills. In this paper, we describe our goals and some possible class activities we have developed and refined over the past few years with encouraging results, to help CS students understand the potential uses of computing for social good. In these carefully planned project assignments, we seamlessly integrate traditional approaches to develop technical skills with broader professional responsibility and soft skills. We then discuss the lessons learned from these activities and briefly outline future plans.

cs.CY↗

arXiv2023

Search-Based Fairness Testing: An Overview

Artificial Intelligence (AI) has demonstrated remarkable capabilities in domains such as recruitment, finance, healthcare, and the judiciary. However, biases in AI systems raise ethical and societal concerns, emphasizing the need for effective fairness testing methods. This paper reviews current research on fairness testing, particularly its application through search-based testing. Our analysis highlights progress and identifies areas of improvement in addressing AI systems biases. Future research should focus on leveraging established search-based testing methodologies for fairness testing.

cs.AI↗

arXiv2023

A Novel Multidimensional Reference Model For Heterogeneous Textual Datasets Using Context, Semantic And Syntactic Clues

With the advent of technology and use of latest devices, they produces voluminous data. Out of it, 80% of the data are unstructured and remaining 20% are structured and semi-structured. The produced data are in heterogeneous format and without following any standards. Among heterogeneous (structured, semi-structured and unstructured) data, textual data are nowadays used by industries for prediction and visualization of future challenges. Extracting useful information from it is really challenging for stakeholders due to lexical and semantic matching. Few studies have been solving this issue by using ontologies and semantic tools, but the main limitations of proposed work were the less coverage of multidimensional terms. To solve this problem, this study aims to produce a novel multidimensional reference model using linguistics categories for heterogeneous textual datasets. The categories such context, semantic and syntactic clues are focused along with their score. The main contribution of MRM is that it checks each tokens with each term based on indexing of linguistic categories such as synonym, antonym, formal, lexical word order and co-occurrence. The experiments show that the percentage of MRM is better than the state-of-the-art single dimension reference model in terms of more coverage, linguistics categories and heterogeneous datasets.

cs.SE↗

arXiv2023

Myths and Facts about a Career in Software Testing: A Comparison between Students' Beliefs and Professionals' Experience

Testing is an indispensable part of software development. However, a career in software testing is reported to be unpopular among students in computer science and related areas. This can potentially create a shortage of testers in the software industry in the future. The question is, whether the perception that undergraduate students have about software testing is accurate and whether it differs from the experience reported by those who work in testing activities in the software development industry. This investigation demonstrates that a career in software testing is more exciting and rewarding, as reported by professionals working in the field, than students may believe. Therefore, in order to guarantee a workforce focused on software quality, the academy and the software industry need to work together to better inform students about software testing and its essential role in software development.

cs.SE↗

arXiv2023

Software Testing and Code Refactoring: A Survey with Practitioners

Nowadays, software testing professionals are commonly required to develop coding skills to work on test automation. One essential skill required from those who code is the ability to implement code refactoring, a valued quality aspect of software development; however, software developers usually encounter obstacles in successfully applying this practice. In this scenario, the present study aims to explore how software testing professionals (e.g., software testers, test engineers, test analysts, and software QAs) deal with code refactoring to understand the benefits and limitations of this practice in the context of software testing. We followed the guidelines to conduct surveys in software engineering and applied three sampling techniques, namely convenience sampling, purposive sampling, and snowballing sampling, to collect data from testing professionals. We received answers from 80 individuals reporting their experience refactoring the code of automated tests. We concluded that in the context of software testing, refactoring offers several benefits, such as supporting the maintenance of automated tests and improving the performance of the testing team. However, practitioners might encounter barriers in effectively implementing this practice, in particular, the lack of interest from managers and leaders. Our study raises discussions on the importance of having testing professionals implement refactoring in the code of automated tests, allowing them to improve their coding abilities.

cs.SE↗

arXiv2023

Explainable Software Defect Prediction from Cross Company Project Metrics Using Machine Learning

Predicting the number of defects in a project is critical for project test managers to allocate budget, resources, and schedule for testing, support and maintenance efforts. Software Defect Prediction models predict the number of defects in given projects after training the model with historical defect related information. The majority of defect prediction studies focused on predicting defect-prone modules from methods, and class-level static information, whereas this study predicts defects from project-level information based on a cross-company project dataset. This study utilizes software sizing metrics, effort metrics, and defect density information, and focuses on developing defect prediction models that apply various machine learning algorithms. One notable issue in existing defect prediction studies is the lack of transparency in the developed models. Consequently, the explain-ability of the developed model has been demonstrated using the state-of-the-art post-hoc model-agnostic method called Shapley Additive exPlanations (SHAP). Finally, important features for predicting defects from cross-company project information were identified.

cs.SE↗

arXiv2023

A Reference Framework for Variability Management of Software Product Lines

Variability management (VM) in software product line engineering (SPLE) is introduced as an abstraction that enables the reuse and customization of assets. VM is a complex task involving the identification, representation, and instantiation of variability for specific products, as well as the evolution of variability itself. This work presents a comparison and contrast between existing VM approaches using qualitative meta-synthesis to determine the underlying perspectives, metaphors, and concepts of existing methods. A common frame of reference for the VM was proposed as the result of this analysis. Putting metaphors in the context of the dimensions in which variability occurs and identifying its key concepts provides a better understanding of its management and enables several analyses and evaluation opportunities. Finally, the proposed framework was evaluated using a qualitative study approach. The results of the evaluation phase suggest that the organizations in practice only focus on one dimension. The presented frame of reference will help the organization to cover this gap in practice.

cs.SE↗

arXiv2023

What Pakistani Computer Science and Software Engineering Students Think about Software Testing?

Software testing is one of the crucial supporting processes of the software life cycle. Unfortunately for the software industry, the role is stigmatized, partly due to misperception and partly due to treatment of the role. The present study aims to analyze the situation to explore what restricts computer science and software engineering students from taking up a testing career in the software industry. To conduct this study, we surveyed 88 Pakistani students taking computer science or software engineering degrees. The results showed that the present study supports previous work into the unpopularity of testing compared to other software life cycle roles. Furthermore, the findings of our study showed that the role of tester has become a social role, with as many social connotations as technical implications.

cs.SE↗

arXiv2022

What UAE Software Students Think about Software Testing: A Replicated Study

Software testing is vital to improve software quality. However, software tester role is stigmatized, partly due to misperception and partly due to the treatment of the testing process within the software industry. The present study analyses this situation aiming to explore what might inhibit an individual from taking up a software testing career. In order to investigate this issue, we surveyed 132 senior students pursuing degrees in information systems, information and communication technology, computer science, computer engineering, software engineering, and other closely-related disciplines at three universities in the United Arab Emirates: two publicly funded and one top-notch private university. The students were asked to describe the PROs and CONs of taking up a career in software testing and to ponder the likelihood that they would take up the career themselves. The study identified 7 main PROs and 9 main CONSs for pursuing a testing career, and indicated that the role of software tester is perceived as a social role, which may require as many soft skills as technical prowess. The results also show that UAE software-related students have a stronger negative attitude towards software testing compared to their counterparts in other countries where similar investigations have been carried out in the past three years.

cs.SE↗

arXiv2022

Roadblocks to Attracting Students to Software Testing Careers: Comparisons of Replicated Studies

Context. Recently, a family of studies highlighted the unpopularity of software testing careers among undergraduate students in software engineering and computer science courses. The original study and its replications explored the perception of students in universities in four countries (Cana-da, China, India, and Malaysia), and indicated that most students do not consider a career in software testing as an option after graduation. This scenario represents a problem for the software industry since the lack of skilled testing professionals might decrease the quality of software projects and increase the number of unsuccessful projects. Goal. The present study aims to replicate, in Brazil, the studies conducted in the other four countries to establish comparisons and support the development of strategies to improve the visibility and importance of software testing among undergraduate students across the globe. Method. We followed the same protocol in the original study to collect data using a questionnaire and analyzed the answers using descriptive statistics and qualitative data analysis. Results. Our findings indicate similarities among the results obtained in Brazil in comparison to those obtained from other countries. We observed that students are not motivated to follow a testing career in the software industry based on a belief that testing activities lack challenges and opportunities for continuous learning. Conclusions. In summary, students seem to be interested in learning more about software testing. However, the lack of discussions about the theme in software development courses, as well as the limited offer of courses focused on software quality at the university level reduce the visibility of this area, which causes a decrease in the interest in this career.

cs.SE↗