arXiv subjects

Elisa Schmid

Publications and source records attributed to Elisa Schmid.

4 recordsLinked to original sources

arXiv2026

How Do Software Engineering Students Use Generative AI in Real-World Capstone Projects? An Empirical Baseline Study

Real-world Capstone Projects (RWCPs) are a key component of software engineering education, enabling students to develop software for external clients under authentic conditions. Their high ecological validity, combined with substantial variation in domains, technologies, and stakeholders, typically requires flexible and minimally prescriptive teaching approaches. The rapid integration of generative AI (GenAI) into professional software development adds new challenges: students are expected to use AI tools that are common in practice, yet unguided use may affect learning, collaboration, and consistency in ways that are not yet well understood. To establish an empirical baseline for responsible GenAI integration, we conducted a large-scale study of self-determined GenAI use in an undergraduate RWCP course. The module involved 178 students working in 18 teams across 15 client projects over four months, with GenAI use explicitly permitted. We collected mixed-method survey data from 150 students on attitudes, usage prevalence, workflows, use cases, and perceived benefits and risks, and surveyed client stakeholders regarding expectations and concerns. Our findings provide (1) a characterization of GenAI practices across the software engineering lifecycle, including a distinction between emerging workflows; (2) student-recommended use cases and responsible-use directives emphasizing verification and maintaining independent understanding; (3) client perspectives highlighting strong support for GenAI use but clear expectations regarding understanding, quality, and data protection; and (4) implications for future course iterations, including the need for explicit responsible-use guidelines, targeted AI literacy resources, and team-level governance roles. This study offers a status quo baseline for evidence-based pedagogical interventions in the era of GenAI.

cs.SE↗

arXiv2026

Supporting Stakeholder Requirements Expression with LLM Revisions: An Empirical Evaluation

Stakeholders often struggle to accurately express their requirements due to articulation barriers arising from limited domain knowledge or from cognitive constraints. This can cause misalignment between expressed and intended requirements, complicating elicitation and validation. Traditional elicitation techniques, such as interviews and follow-up sessions, are time-consuming and risk distorting stakeholders' original intent across iterations. Large Language Models (LLMs) can infer user intentions from context, suggesting potential for assisting stakeholders in expressing their needs. This raises the questions of (i) how effectively LLMs can support requirement expression and (ii) whether such support benefits stakeholders with limited domain expertise. We conducted a study with 26 participants who produced 130 requirement statements. Each participant first expressed requirements unaided, then evaluated LLM-generated revisions tailored to their context. Participants rated LLM revisions significantly higher than their original statements across all dimensions-alignment with intent, readability, reasoning, and unambiguity. Qualitative feedback further showed that LLM revisions often surfaced tacit details stakeholders considered important and helped them better understand their own requirements. We present and evaluate a stakeholder-centered approach that leverages LLMs as articulation aids in requirements elicitation and validation. Our results show that LLM-assisted reformulation improves perceived completeness, clarity, and alignment of requirements. By keeping stakeholders in the validation loop, this approach promotes responsible and trustworthy use of AI in Requirements Engineering.

cs.SE↗

arXiv2025

From App Features to Explanation Needs: Analyzing Correlations and Predictive Potential

In today's digitized world, software systems must support users in understanding both how to interact with a system and why certain behaviors occur. This study investigates whether explanation needs, classified from user reviews, can be predicted based on app properties, enabling early consideration during development and large-scale requirements mining. We analyzed a gold standard dataset of 4,495 app reviews enriched with metadata (e.g., app version, ratings, age restriction, in-app purchases). Correlation analyses identified mostly weak associations between app properties and explanation needs, with moderate correlations only for specific features such as app version, number of reviews, and star ratings. Linear regression models showed limited predictive power, with no reliable forecasts across configurations. Validation on a manually labeled dataset of 495 reviews confirmed these findings. Categories such as Security & Privacy and System Behavior showed slightly higher predictive potential, while Interaction and User Interface remained most difficult to predict. Overall, our results highlight that explanation needs are highly context-dependent and cannot be precisely inferred from app metadata alone. Developers and requirements engineers should therefore supplement metadata analysis with direct user feedback to effectively design explainable and user-centered software systems.

cs.SE↗

arXiv2025

A German Gold-Standard Dataset for Sentiment Analysis in Software Engineering

Sentiment analysis is an essential technique for investigating the emotional climate within developer teams, contributing to both team productivity and project success. Existing sentiment analysis tools in software engineering primarily rely on English or non-German gold-standard datasets. To address this gap, our work introduces a German dataset of 5,949 unique developer statements, extracted from the German developer forum Android-Hilfe.de. Each statement was annotated with one of six basic emotions, based on the emotion model by Shaver et al., by four German-speaking computer science students. Evaluation of the annotation process showed high interrater agreement and reliability. These results indicate that the dataset is sufficiently valid and robust to support sentiment analysis in the German-speaking software engineering community. Evaluation with existing German sentiment analysis tools confirms the lack of domain-specific solutions for software engineering. We also discuss approaches to optimize annotation and present further use cases for the dataset.

cs.SE↗