Keywords: Conceptual modeling, Domain modeling, Generative AI, LLM, UML
Astract: The information systems engineering community is increasingly exploring the use of Large Language Models (LLMs) for a variety of tasks, including domain modeling, business process modeling, software modeling, and systems modeling. However, most existing research remains exploratory and lacks a systematic approach to analyzing the impact of prompt content on model quality. This paper seeks to fill this gap by investigating how different levels of description granularity (whole text vs. paragraph-by-paragraph) and modeling strategies (model-based vs. list-based) affect the quality of LLM-generated domain models. Specifically, we conducted an experiment with two state-of-the-art LLMs (GPT-4o and Llama-3.1-70b-versatile) on tasks involving use case and class modeling. Our results reveal challenges that extend beyond the chosen granularity, strategy, and LLM, emphasizing the importance of human modelers not only in crafting effective prompts but also in identifying and addressing critical aspects of LLM-generated models that require refinement and correction.

Keywords: Agility, Business Process Management, Conversational Agents, LLM, Social media
Astract: The traditional approaches in dynamic and collaborative environments that use Business Process Management (BPM) methodologies usually lack the ability to adapt to real-time changes in case of heavy human involvement in repetitive processes. The agility of social BPM is, however, still limited because of a lack of context-sensitive tool support. This paper proposes a mapping framework that leverages conversational AI agents on a social media platform to enhance BPM agility. AI-driven conversational agents are mapped to the respective phases of the BPM lifecycle to provide real-time guidance, recommendations, and context-sensitive feedback. The agents’ collaborative features enable inclusive co-construction, interactive task execution, and continuous monitoring of the processes. That allows dynamic adaptation of the processes in case of changes so that tasks remain aligned with the users’ needs and contextual demands. This framework is developed through an exploratory approach that integrates literature review, deductive design, and use case-based evaluation. This framework could bridge gaps in the current BPM practices by integrating BPM, AI, and social media, thereby offering a new model for agile and collaborative business process management.

Keywords: Artificial Intelligence, Event Log Completion, Event Log Creation, Event Log Quality Improvement, Multimodal data
Astract: Process mining uses data from event logs to understand which activities were undertaken, their timing, and the involved entities, providing a data trail for process analysis and improvement. However, a significant challenge involves ensuring that these logs accurately reflect the actual processes. Some processes leave few digital traces, and their event logs often lack details about manual and physical work that does not involve computers or simple sensors. We introduce the Business-knowledge Integration Cycles (BICycle) method and mm_proc_miner tool to convert raw and unstructured data from various modalities, such as video, audio, and sensor data, into a structured and unified event log, while keeping human-in-the-loop. Our method analyzes the semantic distance between visible, audible, and textual evidence within a self-hosted joint embedding space. Our approach is designed to consider (1) preserving the privacy of evidence data, (2) achieving real-time performance and scalability, and (3) preventing AI hallucinations. We also publish a dataset consisting of over 2K processes with 16K steps to facilitate domain inference-related tasks. For the evaluation, we created a novel test dataset in the domain of DNA home kit testing, for which we can guarantee that it was not encountered during the training of the employed AI foundational models. We show positive insights in both event log enrichment with multimodal evidence and human-in-the-loop contribution.

Keywords: Conceptual Modeling, Enterprise Modeling, Systems analysis and design
Astract: The Exploring Modeling Methods for Systems Analysis and Development (EMMSAD) conference series organized 29 events from 1996 to 2024, associated with Conference on Advanced Information Systems Engineering. In 2009, EMMSAD became a two-day working conference. Since 2017, the authors of EMMSAD’s best papers are invited to submit extended versions of their paper, for consideration to be published in the Journal of Software and Systems Modeling. The main topics of the EMMSAD series focus on models and modeling methods for the analysis and development of software information systems of any kind. These are organized into five tracks: (1) Foundations of Modeling and Method Engineering; (2) Enterprise, Business, Process, and Capability Modeling; (3) Information Systems and Requirements Modeling; (4) Domain-Specific and Knowledge Modeling; and (5) Evaluation of Models and Modeling Approaches. The aims, topics, and history of EMMSAD can be also found on its website at http://www.emmsad.org/.

Keywords: Abstract syntax, DSL, EMF, Graphical concrete syntax, M3B, MDSE, Metamodeling, Model transformation, MSDKVS, Sirius
Astract: Many powerful metamodeling platforms enabling model-driven software engineering (MDSE) exist, each with its strengths, weaknesses, functionalities, programming language(s), and developer community. Platform interoperability would enable users to exploit their mutual benefits. Such interoperability would allow the transformation of metamodels and models created in one platform into equivalent metamodels and models in other platforms. Language engineers could then freely choose the metamodeling platform without risking a lock-in effect. Two well-documented and publicly available metamodeling platforms are the eclipse modeling framework (EMF) and the modeling SDK for visual studio (MSDKVS). In this paper, we propose an M3-level-bridge (M3B) that establishes interoperability between EMF and MSDKVS on the abstract syntax level and on the graphical concrete syntax level. To establish such interoperability we (i) compare the two platforms, (ii) present a conceptual mapping between them, and (iii) implement a bidirectional transformation bridge including both the metamodel and model layer. We evaluate our approach by transforming a collection of publicly available metamodels and automatically generated or manually created models thereof. The transformation outcomes are then used to quantitatively and qualitatively evaluate the transformation’s validity, executability, and expressiveness.