Abstract. This PhD research project investigates whether emotional aware- ness can be helpful to improve developers’ productivity and well- being. The aim is to provide insights, based on self-monitoring, which can help developers to prevent or reduce stress. To support the research, a visualization tool has been built that shows biomet- rics and self-reported emotions. A series of empirical studies are conducted in the context of agile retrospective meetings, involv- ing both students in a lab setting and professional developers in the workplace. Research will also address the use of non-invasive biometric sensors as an alternative rather than a complement to self- reporting of emotions. The aim is to enable emotional awareness without the need for intrusive self-monitoring mechanisms.

Abstract. In the fast-paced world of healthcare technology, combining IoT devices with large language models (LLMs) offers a promising path to transform Clinical Decision-Support Systems (CDSS). This Ph.D. project is designed to tap into IoT’s extensive data collection ability and LLMs’ superior natural language processing skills. It aims to improve clinical decision-making and patient care through a sophisticated DSS that utilizes both technologies’ strengths. The project delves into the software engineering challenges and methodologies required to build an effective DSS. It investigates how to smoothly evaluate and integrate IoT and LLMs into healthcare environments, tackling significant issues like data complexity, privacy concerns, and the necessity for high accuracy in medical settings. It underscores the critical role of thorough evaluation and assessment in developing healthcare technologies.

Abstract. Nowadays, the rapid spread of Artificial Intelligence (AI) in the daily lives of individuals is raising multiple challenges and issues. The latter must be timely and effectively addressed since they have a substantial impact on numerous domains with implications concerning the technicalities, typically faced by computer science, and also to multiple areas of society, such as law, ethics, psychology, etc. The PhD project presented in this manuscript aims at finding new human-centered methodologies and techniques, belonging to the Human-Computer Interaction (HCI) discipline, that can be applied to the design and development of AI to foster the symbiotic relationship between machines and humans. The project deals with Symbiotic Artificial Intelligence (SAI), which has the goal of supporting humans in executing their tasks without replacing them. The research aims at finding the intersection between Software Engineering (SE), HCI, and AI to create a framework supporting and providing guidance to all the parties involved in the process of creating effective SAI systems.

Abstract. Cloud systems are becoming increasingly important nowadays, and at the same time, there is a need to ensure the security of those systems that pose specific problems. There is the lack of adequate skills and knowledge to deal with the complexity and challenges determined by security in cloud systems, particularly skills related to project management. This research aims to investigate the software project management issues and challenges in the design, development, maintenance, and operation of cloud systems while ensuring adequate security and understand best practices to address them. The ultimate goal of the research is to create a framework that will offer practical recommendations to enhance overall project understanding and support project managers in managing projects and programs related to security of cloud systems.

Abstract. Software development is essentially a collaborative, socio-technical endeavor where the interplay between stakeholders and technical elements is integral. This synergy becomes particularly crucial in the context of geographically dispersed teams, a practice that is becoming more prevalent. Despite the ubiquity of this nature, the current body of research in Global Software Development (GSD) encounters limitations, rendering the attained results less accessible for practical implementation by industry professionals. Moreover, the role of social debt, the additional cost derived by adopting socio-technical anti-patterns, in GSD still needs to be deepened. This Ph.D. research project aims to surmount these challenges by constructing a robust theoretical foundation for effectively managing socio-technical aspects—particularly in the form of factors related to social debt—in software development, with a keen focus on their correlation with cultural differences within software teams. The framework systematically captures and examines cultural differences, investigating their ramifications on various facets of software development while exploring practical strategies employed by practitioners to navigate these influences. Furthermore, the project aspires to make substantial contributions to the professional software development realm by translating research findings into tangible tools for practitioners. This framework is designed not only for immediate application but also to facilitate project success through heightened cultural awareness and adaptability. Ultimately, it strives to enhance the well-being of developers working in inclusive and culturally diverse environments.

Abstract. Artificial Intelligence (AI) is significantly impacting foreseeing fields offering a better-automated decision making process and autonomous systems. Therefore, it is important to design high-quality AI systems that focus on the users’ priorities and avoid potential unethical and undesired behaviours. In the current scenario, Human-Computer Interaction (HCI) and AI are not separate fields but they contaminate each other and, consequently, the symbiosis between humans and AI system is fostered. Ensuring that AI development benefits humans, while providing an high-level automation, remains a primary concern. For this reason, the human-centered design approach should be adopted to create systems that being trustworthy, safe, reliable, and governance compliant are able to enhance the user’s cognitive abilities and protect they from potential risks. In this context, it is fundamental to identify guidelines to follow while designing high-quality Symbiotic AI (SAI) systems and metrics for their appropriate evaluation. Assessing the empirical validity of the proposed solution is of crucial importance and the planning and execution of a user study is one of the main aspects of this work. The research project concerns the design of SAI systems, more specifically the definition of best practices and metrics to adopt while creating and evaluating these systems. This contribution presents the preliminary results obtained during the initial part of my research. The main opportunities and challenges in this new research field are also discussed.

Abstract. This research proposal aims to comprehensively explore the trustworthy, safe, and ethical use of Generative Artificial Intelligence (GAI), particularly Large Language Models (LLMs). To this end, we examine the risks and potential social hazards of LLMs, adopting a multidimensional approach—social, political, and ethical— involving various stakeholders, including the AI industry, governmental institutions, and regulatory organizations, among others. This strategy allows for offering a research proposal grounded on cybersecurity’s social and technological dimensions and providing a comprehensive diagnosis, including perceived challenges in the AI industry, regulations debate, challenges in governance, etc. By delving into these areas, we aim to design a post-audit tool to ensure models are trustworthy, socially responsible, and in alignment with human rights. Additionally, we aim to encourage responsible AI Innovation through Ethics-Driven Incentives.

Abstract. This paper presents a doctoral work focused on gender diversity in software engineering (SE), and specifically, it explores the effect of human-centered interventions to address gender disparities in the field. Despite increased enrollment of women in SE studies and social awareness around the topic, women remain underrepresented, facing persistent barriers and stereotypes. Drawing from extensive literature and empirical studies, the study discusses the results of a multifaceted approach that includes diversity policies, mentorship programs, inclusive hiring practices, and other solutions. The study presents both knowledge-seeking and solution-seeking studies. It proposes a research framework to assess the efficacy of such interventions, applying mixed-methods research. By rigorously examining their impact, the study aims to offer insights into effective strategies for empowering gender diversity and inclusivity in SE. Through empirical analysis, it seeks to contribute to a more equitable and diverse SE environment, fostering meaningful and sustainable change.

Abstract. With software maintenance accounting for 50% of the cost of developing software, enhancing code quality and reliability has become more critical than ever. In response to this challenge, this doctoral research proposal aims to explore innovative solutions by focusing on the deployment of agents powered by Large Language Models (LLMs) to perform software maintenance tasks. The iterative nature of agents, which allows for continuous learning and adaptation, can help surpass common challenges in code generation such as last-mile problems, errors at the final stage of producing functionally and contextually relevant code. Furthermore, this project aims to surpass the inherent limitations of current LLMs in source code through a collaborative framework where agents can correct and learn from each other’s errors. We aim to use the iterative feedback in these systems to further fine-tune the LLMs underlying the agents, becoming better aligned to the task of automated software improvement. Our main goal is to achieve a leap forward in the field of automatic software improvement by developing new tools and frameworks that can enhance the efficiency and reliability of software development.

Abstract. Cyberattacks are becoming more sophisticated, and organizations are constantly under threat from various types of security breaches. To protect against these threats, it is essential to identify the vulnerability and impact of these weaknesses and address them before attackers can exploit them. However, manually identifying and characterizing vulnerability can be a time-consuming and tedious process that adds to the workload of cybersecurity experts. To address this challenge, this paper presents a doctoral research proposal to automate the process of identifying novel technologies, including learning-based technologies, to infer vulnerabilities from a text about an attack. In addition, this paper uses natural language processing techniques to extract relevant information from attack text and analyze repositories for known vulnerabilities. This paper presents an in-depth analysis of the research challenges and goals to understand how innovative technologies can be used to detect and identify vulnerabilities in text about attacks. It also covers the preliminary work done, literature review findings, and threats to validity.