arXiv subjects

Paulo Carvalho

Publications and source records attributed to Paulo Carvalho.

9 recordsLinked to original sources

arXiv2026

AI-assisted Script Management for Requirements Elicitation Interviews

Requirements elicitation interviews require interviewers to balance topic coverage, active listening, and adaptive probing while responding to stakeholders in real time. Although prior work has explored AI support for isolated interviewing tasks, such as script generation and follow-up question generation, little is known about how integrated support affects the interview and what requirements artifacts emerge. Furthermore, script management---which helps the interviewer track topic coverage in real time and decide when to probe further---remains underexplored. This paper presents an AI-assisted elicitation workflow that combines theory-guided script generation grounded in business goals with live support for topic coverage tracking and on-demand follow-up question generation. We evaluate the workflow in a between-subjects quasi-experimental study comparing a no-training, AI-assisted condition with a training, AI-unassisted condition. Based on a rubric derived from elicitation best practices, the AI-generated scripts score higher than training-only scripts (92.8 vs. 74.8 out of 100). AI-assisted interviews cover fewer topics (9.6 vs. 14.5), cover more scripted questions (86% vs. 69%), ask more follow-ups per topic (3.43 vs. 1.15), and produce more refined goal models (lowest-level goal fraction 0.653 vs. 0.598). Participants find script management useful, rating topic tracking as the most useful workflow feature (86% agreement). Collectively, these results show that the AI-assisted condition is associated with a different interview trajectory and different elicited requirements than a training-only condition, positioning AI-assisted workflows as elicitation scaffolds for future studies.

cs.SE↗

arXiv2026

Decomposing the Doer Effect in Programming Practice: Code Writing Stands Out Among Active Practice

The "doer effect" suggests that actively doing practice activities is more strongly associated with learning outcomes than passively viewing content. In the doer effect literature, "doing" refers specifically to active practice. However, this categorization treats different forms of active practice as equivalent, leaving open whether some types of active practice are more effective than others. In this paper, we investigate whether the doer effect extends to computer science instruction and whether some forms of doing stand out compared to other forms. We analyze log data from 334 students across 11 semesters of introductory and intermediate Java who used an interactive practice system with five content types: Code Writing, Code Tracing, Code Completion, Code Visualizations, and Code Explanations. Consistent with prior doer effect work, we find that active practice activities were associated with 3.2 times better learning outcomes than passive activities. Interestingly, among the active practice, code writing was the most strongly associated with improved posttest performance, while no other activity type showed a comparable association. These results highlight the importance of challenging, feedback-supported practice activities, such as code writing problems.

cs.SE↗

arXiv2026

BRHC: Backend-driven Reactive Hypermedia Controls with a Statically Typed Kotlin DSL

AI-assisted coding tools (e.g., Copilot, Cursor, Claude) are increasingly ubiquitous and enable rapid generation of web applications. However, this raises concerns regarding complexity, longevity and the long-term maintainability of generated systems. A key source of complexity is the heterogeneity between backend and frontend programming models, where multiple languages and paradigms are combined within a single application, often leading to duplicated logic and fragmented state management. To address this issue, recent approaches (e.g., HTMX, Turbo Hotwire, Datastar, etc.) follow the Hypermedia-Driven Application (HDA) model, positioning HTML as the primary communication medium between client and server. Unlike SPA-centric architectures, HDA systems shift the application state and interaction logic to the server, where backend-driven reactive signals synchronize with the client user interface. However, these approaches still introduce complexity through custom attributes and do not fully eliminate JavaScript, particularly in computed expressions. In this work, we propose a statically typed approach using a Kotlin-based HTML DSL (Domain-Specific Language) for backend-driven reactive web applications. We extend the HtmlFlow Kotlin DSL with typed custom HTML attributes (i.e., Datastar data-* attributes) and signal-based bindings using statically typed builders. We demonstrate the approach through a catalog of reactive interaction patterns and a Petclinic Spring MVC case study. The results indicate that the proposed approach can nearly eliminate the need for JavaScript while improving type safety and preserving a homogeneous programming model across frontend and backend, bridged through a backend-driven reactive, signal-centric architecture.

cs.SE↗

arXiv2026

AI Knows Best? The Paradox of Expertise, AI-Reliance, and Performance in Educational Tutoring Decision-Making Tasks

We present an empirical study of how both experienced tutors and non-tutors judge the correctness of tutor praise responses under different Artificial Intelligence (AI)-assisted interfaces, types of explanation (textual explanations vs. inline highlighting). We first fine-tuned several Large Language Models (LLMs) to produce binary correctness labels and explanations, achieving up to 88% accuracy and 0.92 F1 score with GPT-4. We then let the GPT-4 models assist 95 participants in tutoring decision-making tasks by offering different types of explanations. Our findings show that although human-AI collaboration outperforms humans alone in evaluating tutor responses, it remains less accurate than AI alone. Moreover, we find that non-tutors tend to follow the AI's advice more consistently, which boosts their overall accuracy on the task: especially when the AI is correct. In contrast, experienced tutors often override the AI's correct suggestions and thus miss out on potential gains from the AI's generally high baseline accuracy. Further analysis reveals that explanations in text reasoning will increase over-reliance and reduce underreliance, while inline highlighting does not. Moreover, neither explanation style actually has a significant effect on performance and costs participants more time to complete the task, instead of saving time. Our findings reveal a tension between expertise, explanation design, and efficiency in AI-assisted decision-making, highlighting the need for balanced approaches that foster more effective human-AI collaboration.

cs.HC↗

arXiv2025

Small but Significant: On the Promise of Small Language Models for Accessible AIED

GPT has become nearly synonymous with large language models (LLMs), an increasingly popular term in AIED proceedings. A simple keyword-based search reveals that 61% of the 76 long and short papers presented at AIED 2024 describe novel solutions using LLMs to address some of the long-standing challenges in education, and 43% specifically mention GPT. Although LLMs pioneered by GPT create exciting opportunities to strengthen the impact of AI on education, we argue that the field's predominant focus on GPT and other resource-intensive LLMs (with more than 10B parameters) risks neglecting the potential impact that small language models (SLMs) can make in providing resource-constrained institutions with equitable and affordable access to high-quality AI tools. Supported by positive results on knowledge component (KC) discovery, a critical challenge in AIED, we demonstrate that SLMs such as Phi-2 can produce an effective solution without elaborate prompting strategies. Hence, we call for more attention to developing SLM-based AIED approaches.

cs.CL↗

arXiv2025

KCluster: An LLM-based Clustering Approach to Knowledge Component Discovery

Educators evaluate student knowledge using knowledge component (KC) models that map assessment questions to KCs. Still, designing KC models for large question banks remains an insurmountable challenge for instructors who need to analyze each question by hand. The growing use of Generative AI in education is expected only to aggravate this chronic deficiency of expert-designed KC models, as course engineers designing KCs struggle to keep up with the pace at which questions are generated. In this work, we propose KCluster, a novel KC discovery algorithm based on identifying clusters of congruent questions according to a new similarity metric induced by a large language model (LLM). We demonstrate in three datasets that an LLM can create an effective metric of question similarity, which a clustering algorithm can use to create KC models from questions with minimal human effort. Combining the strengths of LLM and clustering, KCluster generates descriptive KC labels and discovers KC models that predict student performance better than the best expert-designed models available. In anticipation of future work, we illustrate how KCluster can reveal insights into difficult KCs and suggest improvements to instruction.

cs.AI↗

arXiv2025

An Integrated Platform for Studying Learning with Intelligent Tutoring Systems: CTAT+TutorShop

Intelligent tutoring systems (ITSs) are effective in helping students learn; further research could make them even more effective. Particularly desirable is research into how students learn with these systems, how these systems best support student learning, and what learning sciences principles are key in ITSs. CTAT+Tutorshop provides a full stack integrated platform that facilitates a complete research lifecycle with ITSs, which includes using ITS data to discover learner challenges, to identify opportunities for system improvements, and to conduct experimental studies. The platform includes authoring tools to support and accelerate development of ITS, which provide automatic data logging in a format compatible with DataShop, an independent site that supports the analysis of ed tech log data to study student learnings. Among the many technology platforms that exist to support learning sciences research, CTAT+Tutorshop may be the only one that offers researchers the possibility to author elements of ITSs, or whole ITSs, as part of designing studies. This platform has been used to develop and conduct an estimated 147 research studies which have run in a wide variety of laboratory and real-world educational settings, including K-12 and higher education, and have addressed a wide range of research questions. This paper presents five case studies of research conducted on the CTAT+Tutorshop platform, and summarizes what has been accomplished and what is possible for future researchers. We reflect on the distinctive elements of this platform that have made it so effective in facilitating a wide range of ITS research.

cs.CY↗

arXiv2024

Study of MRI-compatible Notched Plastic Ultrasonic Stator with FEM Simulation and Holography Validation

Intra-operative image guidance using magnetic resonance imaging (MRI) can significantly enhance the precision of surgical procedures, such as deep brain tumor ablation. However, the powerful magnetic fields and limited space within an MRI scanner require the use of robotic devices to aid surgeons. Piezoelectric motors are commonly utilized to drive these robots, with piezoelectric ultrasonic motors being particularly notable. These motors consist of a piezoelectric ring stator that is bonded to a rotor through frictional coupling. When the stator is excited at specific frequencies, it generates distinctive mode shapes with surface waves that exhibit both in-plane and out-of-plane displacement, leading to the rotation of the rotor. In this study, we continue our previous work and refine the motor design and performance, we combine finite element modeling (FEM) with stroboscopic and time-averaged digital holography to validate a further plastic-based ultrasonic motor with better rotary performance.

cs.RO↗

arXiv2020

Influence of Event Duration on Automatic Wheeze Classification

Patients with respiratory conditions typically exhibit adventitious respiratory sounds, such as wheezes. Wheeze events have variable duration. In this work we studied the influence of event duration on wheeze classification, namely how the creation of the non-wheeze class affected the classifiers' performance. First, we evaluated several classifiers on an open access respiratory sound database, with the best one reaching sensitivity and specificity values of 98% and 95%, respectively. Then, by changing one parameter in the design of the non-wheeze class, i.e., event duration, the best classifier only reached sensitivity and specificity values of 55% and 76%, respectively. These results demonstrate the importance of experimental design on the assessment of wheeze classification algorithms' performance.

cs.SD↗