TY - CHAP A1 - Meier, Sebastian A1 - Glinka, Katrin ED - Stolze, Markus ED - Loch, Frieder ED - Baldauf, Matthias ED - Alt, Florian ED - Schneegass, Christina ED - Kosch, Thomas ED - Hirzle, Teresa ED - Sadeghian, Shadan ED - Draxler, Fiona ED - Bektas, Kenan ED - Lohan, Katrin ED - Knierim, Pascal T1 - To Classify is to Interpret BT - Building Taxonomies from Heterogeneous Data through Human-AI Collaboration T2 - Proceedings of Mensch und Computer 2023 N2 - Taxonomy building is a task that requires interpreting and classifying data within a given frame of reference, which comes to play in many areas of application that deal with knowledge and information organization. In this paper, we explore how taxonomy building can be supported with systems that integrate machine learning (ML). However, relying only on black-boxed ML-based systems to automate taxonomy building would sideline the users’ expertise. We propose an approach that allows the user to iteratively take into account multiple model’s outputs as part of their sensemaking process. We implemented our approach in two real-world use cases. The work is positioned in the context of HCI research that investigates the design of ML-based systems with an emphasis on enabling human-AI collaboration. KW - Künstliche Intelligenz KW - Taxonomie KW - Maschinelles Lernen KW - Mensch-Maschine-Schnittstelle Y1 - 2023 SN - 979-8-4007-0771-1 U6 - https://doi.org/10.1145/3603555.3608532 SP - 395 EP - 401 PB - Association for Computing Machinery CY - New York ER - TY - JOUR A1 - Bruhn, Thomas A1 - Meier, Sebastian A1 - Lawrence, Mark G. T1 - Interactive network visualization on the integration of mindsets and sustainability : creating conditions for emergence through a relational narrative JF - Innovation : The European Journal of Social Science Research N2 - Transdisciplinary research processes often involve the integration of knowledge and stakeholders from various backgrounds. Here, we introduce the story of the research project AMA (A Mindset for the Anthropocene) on the role of mindsets in the context of sustainability and present an interactive visualization tool that we developed for stakeholder mapping and research communication. Through this platform, we provide access and navigation to everyone interested in this field of research and we have simultaneously created a channel for all stakeholders to co-create content. Here, we describe the design and functionalities of the platform and the participatory way it was developed as part of our stakeholder engagement. We discuss upon how such a design allows for reflection of potential biases in transdisciplinary research processes and simultaneously catalyzing self-organization in stakeholder networks. KW - Stakeholder KW - Nachhaltigkeit KW - Transdisziplinarität KW - Visualisierung KW - Datenbank Y1 - 2022 U6 - https://doi.org/10.1080/13511610.2022.2101987 SN - 1351-1610 VL - 36 IS - 1 SP - 71 EP - 84 PB - Routledge, Taylor & Francis Group CY - London ER - TY - CHAP A1 - Meier, Sebastian T1 - Semi-automatic spatial classification of heterogeneous spatial open government data : use case of Germany T2 - Abstracts of the International Cartographic Association N2 - As part of the research project Open Data Cloud Services (ODCS), we have been trying to overcome some of the limitations introduced through the heterogeneity of spatial open government data (sOGD). In this paper we describe some of the challenges of sODG and one of the tools we built to spatially organize heterogenous sOGD, to make it easier for users to find data and automatically integrate it into existing data structures and in the future allow for cross-dataset spatial analysis. KW - Open Government Data KW - Klassifikation KW - Ähnlichkeitssuche KW - Taxonomie KW - Automation Y1 - 2022 U6 - https://doi.org/10.5194/ica-abs-5-59-2022 SN - 2570-2106 PB - Copernicus Publications CY - Göttingen ER - TY - JOUR A1 - Çay, Damla A1 - Nagel, Till A1 - Meier, Sebastian T1 - The UDV Card Deck BT - A Collaborative Design Framework to Facilitate Urban Visualization Conversations JF - IEEE Computer Graphics and Applications N2 - This paper presents the Urban Data Visualization (UDV) card deck, a tool designed to facilitate reflective discussions and inform the collaborative design process of urban data visualizations. The UDV card deck was developed to bridge the gap between theoretical knowledge and practice in workshop settings, fostering inclusive and reflective approaches to visualization design. Drawing from urban visualization design literature and the results from a series of expert workshops, these cards summarize key considerations when designing urban data visualizations. The card deck guides different activities in an engaging, collaborative, and structured format, promoting inclusion of diverse urban actors. We introduce the card deck and its goals, demonstrate its use in four case studies, and discuss our findings. Feedback from workshop participants indicates that the UDV card deck can serve as a supportive and reflective tool for urban data visualization researchers, designers and practitioners. KW - Urban Data Visualization KW - Fallstudie KW - Kartenspiel KW - Visualisierung Y1 - 2025 U6 - https://doi.org/10.1109/MCG.2025.3556573 SN - 0272-1716 SN - 1558-1756 VL - 45 IS - 4 SP - 30 EP - 44 CY - New York ER - TY - JOUR A1 - Safariallahkheili, Qasem A1 - Schiewe, Jochen A1 - Meier, Sebastian T1 - Interactive web-based Geospatial eXplainable Artificial Intelligence for AI model output exploration JF - AGILE : GIScience series N2 - This case study presents a web-based Geospatial eXplainable Artificial Intelligence (GeoXAI) system demonstrated through a case study for wildfire susceptibility assessment. Addressing limitations in traditional GeoXAI tools, the system integrates XAI methods with open-source geospatial technologies. Using a Random Forest model, the system combines environmental, topographic, and meteorological features to provide global and local insights. SHAP values offer feature-level explanations, while the interactive platform enables users to visualize wildfire susceptibility, examine feature contributions, and correlate predictions with spatial patterns and distribution of feature values. This approach tries to enhance transparency in AI-driven environmental decision support systems, with a specific focus on the interpretability of model output. KW - Erklärbare künstliche Intelligenz KW - Geoinformationssystem KW - Random Forest KW - Waldbrand Y1 - 2025 U6 - https://doi.org/10.5194/agile-giss-6-44-2025 SN - 2700-8150 VL - 6 IS - 44 PB - Copernicus Publications CY - Göttingen ER - TY - JOUR A1 - Meier, Sebastian T1 - Offene Daten und Interoperabilität BT - Ein Werkstattbericht zum Status Quo und aktuellen Entwicklungen JF - Vermessung Brandenburg N2 - Das Thema „Offene Daten“ (Open Data) gewinnt in immer mehr Anwendungsgebieten an Bedeutung. Auch in Behörden und der öffentlichen Verwaltung etabliert sich zunehmend eine Open-Data-Kultur. Offene Daten aus der Verwaltung, im englischen „Open Government Data“ (OGD), bergen viele Potentiale – ob es die Erleichterung der bereichsübergreifenden Zusammenarbeit innerhalb der Verwaltung selbst ist oder das Schaffen von Transparenz gegenüber Bürgerinnen und Bürgern. Auch auf wirtschaftlicher Ebene bieten sich neue Möglichkeiten für datengestützte Geschäftsfelder. Doch bei der Entwicklung neuer zivilgesellschaftlicher oder wirtschaftlicher Anwendungen basierend auf behördlichen offenen Daten ergeben sich auch Herausforderungen. KW - Cloud Computing KW - Erklärbare künstliche Intelligenz KW - Open Data KW - Verwaltung Y1 - 2024 UR - https://geobasis-bb.de/sixcms/media.php/9/vbb_124.pdf SN - 1430-7650 VL - 29 IS - 1.2024 SP - 22 EP - 29 CY - Potsdam ER -