arXiv subjects

Savio Freire

Publications and source records attributed to Savio Freire.

4 recordsLinked to original sources

arXiv2026

Prompt Engineering Strategies for LLM-based Qualitative Coding of Psychological Safety in Software Engineering Communities: A Controlled Empirical Study

Qualitative analysis plays a pivotal role in understanding the human and social aspects of software engineering. However, it remains a demanding process shaped by the subjective interpretation of individual researchers and sensitive to methodological choices such as prompt design. Recent advancements in Large Language Models (LLMs) offer promising opportunities to support this type of analysis, although their reliability in reproducing human qualitative reasoning under varying prompting conditions remains largely untested. This study presents a controlled empirical evaluation of three LLMs -- Claude Haiku, DeepSeek-Chat, and Gemini 2.5 Flash -- across two prompt engineering strategies (zero-shot and multi-shot closed coding), using Cohen's kappa as the primary agreement metric over ten independent runs per configuration. Results suggest that multi-shot prompting significantly improves agreement for Claude Haiku (Delta kappa = +0.034, Wilcoxon p = 0.004) but not for DeepSeek-Chat or Gemini 2.5 Flash. Intra-model stability varies substantially -- DeepSeek-Chat and Claude Haiku exhibit the lowest variance (SD approx. 0.017), while Gemini 2.5 Flash is the least stable (SD = 0.038). A systematic over-prediction of "Sharing Negative Feedback" is identified across all models (bias ratios up to 5.25x), alongside consistent under-prediction of "Expressing Concerns." Collectively, these findings provide empirical evidence for prompt engineering guidelines in LLM-assisted qualitative coding for software engineering research.

cs.SE↗

arXiv2026

What Characterizes a Software Leader? Identifying Leadership Practices from Practitioners Social Media

Context: Leadership has been extensively studied in management and agile software development; however, prior research predominantly focuses on formal roles and predefined leadership models, offering limited insight into how leadership is experienced and demonstrated by software practitioners in everyday practice. Objective: Our goal is to identify and categorize leadership practices as perceived and reported by software development practitioners based on their professional experiences. Method: We conducted a content analysis of 116 practitioner-authored articles published on the Dev.to online community. Articles were systematically collected, screened, and coded, resulting in the extraction, correlation analysis and categorization of leadership practices grounded in practitioners narratives. Results: We identified 103 practices for software project leaders, distinguished between recommended and discouraged ones. These practices were organized into five categories: People Management & Development, Processes & Execution, Professional & Personal Growth, Communication & Articulation and Strategic Vision. The most recurrent recommended practices include Cultivating & Practicing Interpersonal Skills, Managing & Delegating Team Work, and Practicing & Developing Managerial Skills, whereas Micromanagement, Counterproductive Work Patterns, and Counterproductive Communication Styles emerged as the most frequent discouraged practices. We organized all practices into a conceptual map. Conclusion: The findings indicate that software leadership is mainly associated with managerial and interpersonal practices rather than technical expertise. The resulting conceptual map summarizes these practices and can serve as a reference for understanding leadership in software development contexts.

cs.SE↗

arXiv2026

A Survey on Large Language Model Impact on Software Evolvability and Maintainability: the Good, the Bad, the Ugly, and the Remedy

Context. Large Language Models (LLMs) are increasingly embedded in software engineering workflows for tasks including code generation, summarization, repair, and testing. Empirical studies report productivity gains, improved comprehension, and reduced cognitive load. However, evidence remains fragmented, and concerns persist about hallucinations, unstable outputs, methodological limitations, and emerging forms of technical debt. How these mixed effects shape long-term software maintainability and evolvability remains unclear. Objectives. This study systematically examines how LLMs influence the maintainability and evolvability of software systems. We identify which quality attributes are addressed in existing research, the positive impacts LLMs provide, the risks and weaknesses they introduce, and the mitigation strategies proposed in the literature. Method. We conducted a systematic literature review. Searches across ACM DL, IEEE Xplore, and Scopus (2020 to 2024) yielded 87 primary studies. Qualitative evidence was extracted through a calibrated multi-researcher process. Attributes were analyzed descriptively, while impacts, risks, weaknesses, and mitigation strategies were synthesized using a hybrid thematic approach supported by an LLM-assisted analysis tool with human-in-the-loop validation. Results. LLMs provide benefits such as improved analyzability, testability, code comprehension, debugging support, and automated repair. However, they also introduce risks, including hallucinated or incorrect outputs, brittleness to context, limited domain reasoning, unstable performance, and flaws in current evaluations, which threaten long-term evolvability. Conclusion. LLMs can strengthen maintainability and evolvability, but they also pose nontrivial risks to long-term sustainability. Responsible adoption requires safeguards, rigorous evaluation, and structured human oversight.

cs.SE↗

arXiv2024

Software Fairness Debt

As software systems continue to play a significant role in modern society, ensuring their fairness has become a critical concern in software engineering. Motivated by this scenario, this paper focused on exploring the multifaceted nature of bias in software systems, aiming to provide a comprehensive understanding of its origins, manifestations, and impacts. Through a scoping study, we identified the primary causes of fairness deficiency in software development and highlighted their adverse effects on individuals and communities, including instances of discrimination and the perpetuation of inequalities. Our investigation culminated in the introduction of the concept of software fairness debt, which complements the notions of technical and social debt, encapsulating the accumulation of biases in software engineering practices while emphasizing the societal ramifications of bias embedded within software systems. Our study contributes to a deeper understanding of fairness in software engineering and paves the way for the development of more equitable and socially responsible software systems.

cs.SE↗