arXiv subjects

Jan Joosten

Publications and source records attributed to Jan Joosten.

4 recordsLinked to original sources

arXiv2026

User eXperience Perception Insights Dataset (UXPID): Synthetic User Feedback from Public Industrial Forums

Customer feedback in industrial forums offers rich but underexplored insights into real-world product experience. Yet systematic analysis remains challenging due to unstructured, domain-specific content and the scarcity of high-quality labeled datasets. This paper presents the User eXperience Perception Insights Dataset (UXPID), a collection of 7130 synthesized and anonymized user feedback branches extracted from a public industrial automation forum. Each JSON record contains multi-post comments enriched with metadata and annotated by a large language model (LLM) for UX insights, user expectations, severity ratings, sentiment, and topic classifications. UXPID is designed to facilitate research in user requirements, user experience (UX) analysis, and AI-driven feedback processing, particularly where privacy and licensing restrictions limit access to real-world data. It supports the training and evaluation of transformer-based models for tasks such as issue detection, sentiment analysis, and requirements extraction in technical forums, providing a valuable resource for advancing NLP methods within industrial product support and software engineering domains.

cs.CL↗

arXiv2026

How to Build AI Agents by Augmenting LLMs with Codified Human Expert Domain Knowledge? A Software Engineering Framework

Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insights and diverting expert time. This paper investigates how to capture and embed human domain knowledge into AI agent systems through an industrial case study. We propose a software engineering framework to capture human domain knowledge for engineering AI agents in simulation data visualization by augmenting a Large Language Model (LLM) with a request classifier, Retrieval-Augmented Generation (RAG) system for code generation, codified expert rules, and visualization design principles unified in an agent demonstrating autonomous, reactive, proactive, and social behavior. Evaluation across five scenarios spanning multiple engineering domains with 12 evaluators demonstrates 206% improvement in output quality, with our agent achieving expert-level ratings in all cases versus baseline's poor performance, while maintaining superior code quality with lower variance. Our contributions are: an automated agent-based system for visualization generation and a validated framework for systematically capturing human domain knowledge and codifying tacit expert knowledge into AI agents, demonstrating that non-experts can achieve expert-level outcomes in specialized domains.

cs.AI↗

arXiv2026

Tables or Sankey Diagrams? Investigating User Interaction with Different Representations of Simulation Parameters

Understanding complex parameter dependencies is critical for effective configuration and maintenance of software systems across diverse domains - from Computer-Aided Engineering (CAE) to cloud infrastructure and database management. However, legacy tabular interfaces create a major bottleneck: engineers cannot easily comprehend how parameters relate across the system, leading to inefficient workflows, costly configuration errors, and reduced system trust - a fundamental program comprehension challenge in configuration-intensive software. This research evaluates whether interactive Sankey diagrams can improve comprehension of parameter dependencies compared to traditional spreadsheet interfaces. We employed a heuristic evaluation using the PURE method with three expert evaluators (UX design, simulation, and software development specialists) to compare a Sankey-based prototype to traditional tabular representations for core engineering tasks. Our key contribution demonstrates that flow-based parameter visualizations significantly reduce cognitive load (51% lower PURE scores) and interaction complexity (56% fewer steps) compared to traditional tables, while making parameter dependencies immediately visible rather than requiring mental reconstruction. By explicitly visualizing parameter relationships, Sankey diagrams address a core software visualization challenge: helping users comprehend complex system configurations without requiring deep tool-specific knowledge. While demonstrated through CAE software, this research contributes to program comprehension and software visualization by showing that dependency-aware visualizations can significantly improve understanding of configuration-intensive systems. The findings have implications for any software domain where comprehending complex parameter relationships is essential for effective system use and maintenance.

cs.HC↗

arXiv2025

AI for Better UX in Computer-Aided Engineering: Is Academia Catching Up with Industry Demands? A Multivocal Literature Review

Computer-Aided Engineering (CAE) enables simulation experts to optimize complex models, but faces challenges in user experience (UX) that limit efficiency and accessibility. While artificial intelligence (AI) has demonstrated potential to enhance CAE processes, research integrating these fields with a focus on UX remains fragmented. This paper presents a multivocal literature review (MLR) examining how AI enhances UX in CAE software across both academic research and industry implementations. Our analysis reveals significant gaps between academic explorations and industry applications, with companies actively implementing LLMs, adaptive UIs, and recommender systems while academic research focuses primarily on technical capabilities without UX validation. Key findings demonstrate opportunities in AI-powered guidance, adaptive interfaces, and workflow automation that remain underexplored in current research. By mapping the intersection of these domains, this study provides a foundation for future work to address the identified research gaps and advance the integration of AI to improve CAE user experience.

cs.HC↗