@article{RodighieroDerryDuhaimeetal., author = {Rodighiero, Dario and Derry, Lins and Duhaime, Douglas and Kruguer, Jordan and Mueller, Maximilian C. and Pietsch, Christopher and Schnapp, Jeffrey T. and Steward, Jeff}, title = {Surprise machines : revealing Harvard Art Museums' image collection}, series = {Information Design Journal}, volume = {27}, journal = {Information Design Journal}, number = {1}, publisher = {John Benjamins Publishing Company}, address = {Amsterdam}, issn = {1569-979X}, doi = {10.1075/idj.22013.rod}, pages = {21 -- 34}, abstract = {Surprise Machines is a project of experimental museology that sets out to visualize the entire image collection of the Harvard Art Museums, with a view to opening up unexpected vistas on more than 200,000 objects usually inaccessible to visitors. The project is part of the exhibition organized by metaLAB (at) Harvard entitled Curatorial A(i)gents and explores the limits of artificial intelligence to display a large set of images and create surprise among visitors. To achieve this feeling of surprise, a choreographic interface was designed to connect the audience's movement with several unique views of the collection.}, subject = {K{\"u}nstliche Intelligenz}, language = {en} } @article{KauerDoerkBach, author = {Kauer, Tobias and D{\"o}rk, Marian and Bach, Benjamin}, title = {Towards Collective Storytelling}, series = {IEEE Computer Graphics and Applications}, volume = {45}, journal = {IEEE Computer Graphics and Applications}, number = {3}, address = {New York}, organization = {Institute of Electrical and Electronics Engineers (IEEE)}, issn = {0272-1716}, doi = {10.1109/MCG.2025.3547944}, pages = {17 -- 31}, abstract = {This work investigates personal perspectives in visualization annotations as devices for collective data-driven storytelling. Inspired by existing efforts in critical cartography, we show how people share personal memories in a visualization of COVID-19 data and how comments by other visualization readers influence the reading and understanding of visualizations. Analyzing interaction logs, reader surveys, visualization annotations, and interviews, we find that reader annotations help other viewers relate to other people's stories and reflect on their own experiences. Further, we found that annotations embedded directly into the visualization can serve as social traces guiding through a visualization and help readers contextualize their own stories. With that, they supersede the attention paid to data encodings and become the main focal point of the visualization.}, subject = {Annotation}, language = {en} } @article{SafariallahkheiliSchieweMeier, author = {Safariallahkheili, Qasem and Schiewe, Jochen and Meier, Sebastian}, title = {Post-Hoc Explanation of AI Predictions in Wildfire Risk Mapping Through an Interactive Web-Based GeoXAI System}, series = {KN - Journal of cartography and geographic information}, journal = {KN - Journal of cartography and geographic information}, publisher = {Springer International Publishing}, address = {Cham}, issn = {2524-4957}, doi = {10.1007/s42489-025-00194-0}, pages = {16}, abstract = {This case study presents an innovative approach for explaining wildfire susceptibility through a web-based Geospatial eXplainable Artificial Intelligence (GeoXAI) system. By addressing limitations in traditional GeoXAI tools, such as the lack of geographical context for model predictions and local explanation, this system integrates state-of-the-art XAI methods with open-source geospatial technologies. Applied to the wildfire-prone regions of Berlin and Brandenburg, Germany, the system combines environmental, topographic, and meteorological features derived from high-resolution geospatial data for training a Random Forest (RF) model. The web-based GeoXAI system enables interactive exploration of the model output and its features, allowing users to visualize wildfire susceptibility, examine feature contributions, and correlate predictions with spatial patterns through post-hoc interpretability. By employing post-hoc explanation methods like SHAP, the system offers clear insights into model predictions by analyzing feature contributions after training, which helps users better understand AI-driven outcomes. Designed with a user-centered approach, the platform promotes trust and usability through transparent predictions, interactive geovisualizations, and local explanations, allowing users to navigate spatial data intuitively by exploring overviews, focusing on specific regions, and accessing detailed insights on demand. This work highlights the potential of combining GeoXAI with machine learning to improve decision-making in wildfire prevention and management.}, subject = {Entscheidungsunterst{\"u}tzungssystem}, language = {en} }