9 results
Search Results
Now showing 1 - 9 of 9
Item Towards a Visual Analytics System for Emotion Trajectories in Multiparty Conversations(The Eurographics Association, 2024) Huang, Zeyang; Kucher, Kostiantyn; Kerren, Andreas; Kucher, Kostiantyn; Diehl, Alexandra; Gillmann, ChristinaVisualizing sentiments in textual data has received growing interest; however, representing emotions within interlocutor relationships and associating them with the temporal progression of dialogues remains challenging. In this poster abstract, we describe the ongoing work on a visual analytics tool designed for analyzing emotion trajectories within dialogue collections composed of utterances from multiple speakers. The proposed tool provides exploration at different levels of detail to complex multigraphs, where edges represent direct responses between speakers through their utterances. Our approach includes several selection strategies for connecting different views: summaries of emotion transitions across dialogue groups, detailed analyses of individual utterances within specific dialogues of interest in interlocutor networks, and close reading. The tool aims to support model development in natural language processing by allowing users to explore text corpora interactively.Item Visual Analysis of Humor Assessment Annotations for News Headlines in the Humicroedit Data Set(The Eurographics Association, 2024) Kucher, Kostiantyn; Akkurt, Elin; Folde, Johanna; Kerren, Andreas; Yousef, Tariq; Al-Khatib, KhalidEffective utilization of training data is a critical component for the success of any artificial intelligence algorithm, including natural language processing (NLP) tasks. One particular task of interest is related to detecting or ranking humor in texts, as exemplified by the Humicroedit data set used for the SemEval 2020 task of assessing humor in micro-edited news headlines. Rather than focusing on text classification or prediction, in this study, we focus on gaining a deeper understanding and utilization of the data through the use of information visualization techniques facilitated by the established NLP methods such as sentiment analysis and topic modeling. We describe the design of an interactive visualization tool prototype that relies on multiple coordinated views to allow the user explore and analyze the relationships between the annotated humor scores, sentiments, and topics. Evaluation of the proposed approach involves a case study with the Humicroedit data set as well as domain expert reviews with four participants. The experts deemed the prototype useful for its purpose and saw potential in exploring similar data sets with it, as well as further potential applications in their line of work. Our study thus contributes to the body of work on visual text analytics for supporting computational humor analysis as well as annotated text data analysis in general.Item Visual Analysis of Power Plant Data for European Countries(The Eurographics Association, 2024) Wang, Jinyi; Kucher, Kostiantyn; Kerren, Andreas; Kucher, Kostiantyn; Diehl, Alexandra; Gillmann, ChristinaA power plant is a complex real-world system associated with rich multidimensional data relevant to its construction and activity. Thus, choosing an appropriate way to visualize power plant data is important for users to understand and explore more about such systems. Most of the approaches existing in this field support only a static representation of data from a small region. This makes it hard for the users to get an overview or explore specific power plants. In this poster abstract, we describe an interactive visualization tool designed for the analysis of power plant data in Europe. Our approach provides an overview and detail visualization approach for Global Power Plant Database entries. With this tool, users can easily find power plants, see details on demand, filter, compare, and explore the power plant outage scenarios from the nearest neighbor perspective.Item EuroVis 2024 CGF 43-3 STARs: Frontmatter(The Eurographics Association and John Wiley & Sons Ltd., 2024) Garth, Christoph; Kerren, Andreas; Raidou, Renata; Garth, Christoph; Kerren, Andreas; Raidou, RenataItem DeforestVis: Behaviour Analysis of Machine Learning Models with Surrogate Decision Stumps(© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) Chatzimparmpas, Angelos; Martins, Rafeal M.; Telea, Alexandru C.; Kerren, Andreas; Alliez, Pierre; Wimmer, MichaelAs the complexity of machine learning (ML) models increases and their application in different (and critical) domains grows, there is a strong demand for more interpretable and trustworthy ML. A direct, model‐agnostic, way to interpret such models is to train surrogate models—such as rule sets and decision trees—that sufficiently approximate the original ones while being simpler and easier‐to‐explain. Yet, rule sets can become very lengthy, with many if–else statements, and decision tree depth grows rapidly when accurately emulating complex ML models. In such cases, both approaches can fail to meet their core goal—providing users with model interpretability. To tackle this, we propose DeforestVis, a visual analytics tool that offers summarization of the behaviour of complex ML models by providing surrogate decision stumps (one‐level decision trees) generated with the Adaptive Boosting (AdaBoost) technique. DeforestVis helps users to explore the complexity versus fidelity trade‐off by incrementally generating more stumps, creating attribute‐based explanations with weighted stumps to justify decision making, and analysing the impact of rule overriding on training instance allocation between one or more stumps. An independent test set allows users to monitor the effectiveness of manual rule changes and form hypotheses based on case‐by‐case analyses. We show the applicability and usefulness of DeforestVis with two use cases and expert interviews with data analysts and model developers.Item Matrix Snap&Go: Visualization of Paths on Matrices(The Eurographics Association, 2024) Huang, Zeyang; Archambault, Daniel; Borgo, Rita; Kerren, Andreas; Tominski, Christian; Waldner, Manuela; Wang, BeiMatrix representations can be effective for visualizing networks. However, it is very difficult to follow or explore specific paths in a matrix representation. In this paper, we introduce an interactive method for exploring paths on a matrix, called Matrix Snap&Go. Our visualization approach relies heavily on interactive exploration, bringing in the local neighborhood of selected nodes and tracing the path progression through the matrix. We demonstrate the utility of our approach by performing and analyzing test runs with synthetic input graphs of various node/edge densities as well as by discussing a use case based on the exploration of citation networks.Item EuroVis 2025 CGF 44-3 STARs: Frontmatter(The Eurographics Association and John Wiley & Sons Ltd., 2025) Angellini, Marco; Garth, Christoph; Kerren, Andreas; Angellini, Marco; Garth, Christoph; Kerren, AndreasItem Fairness-Aware Urban Planning in Sweden: An Interactive Visualization Tool for Equitable Cities(The Eurographics Association, 2025) Othman, Reem; Powley, Benjamin; Martins, Rafael M.; Soares, Amilcar; Kerren, Andreas; Ferreira, Nivan; Linhares, Claudio D. G.; Diehl, Alexandra; Kucher, Kostiantyn; Médoc, NicolasThis study presents an interactive visualization tool that facilitates fairness-aware urban planning. The system introduces a fairness scale to assess the accessibility of potential new developments, using color-coded scatter plots to visualize disparities. An intuitive interaction design minimizes complexity while enhancing usability, enabling users to analyze urban infrastructure and services. Developed with web technologies, the tool leverages OpenStreetMap data to ensure adaptability across different cities. Future optimizations include advanced analytical capabilities and broader dataset integrations to improve decisionmaking in urban development.Item InfraVis - The Swedish Research Infrastructure for Visualization Support(The Eurographics Association, 2025) Weinkauf, Tino; Romero, Mario; Besançon, Lonni; Ahlstedt, Jonas; Berendt, Filip; Billger, Monica; Danielsson, Karin; Davies, Melvyn B.; Filipsson, Helena; Gelfgren, Stefan; Kerren, Andreas; Larsson, Emanuel; Latino, Fabio; Liliequist, Evelina; Nyström, Ingela; Paulsson, Kajsa; Podkorytova, Maria; Pirzamanbein, Behnaz; Sjöström, Mårten; Sopasakis, Alexandros; Thuresson, Björn; Westin, Jonathan; Ynnerman, Anders; Gillmann, Christina; Krone, Michael; Reina, Guido; Wischgoll, ThomasEssentially all academic research of today relies on analysis of data from a wide range of sources. Several underpinning, and rapidly developing, technologies are supporting the analysis of this data. Visualization serves as an interface to this ecosystem of tools and methods and integrates them into environments supporting scientific workflows, effectively sharing cognitive load between computers and humans. There is, however, a gap between the state-of-the-art in visual data analysis and current wide-spread academic practice. Support for the introduction of new, improved and tailored, visual data analysis environments thus has the potential to address challenges involving large and complex data, creating competitive advantages for researchers. To fill the gap and capitalize on this opportunity, the InfraVis initiative has been created in Sweden with the mission to operate an infrastructure consisting of visualization experts, software solutions, and access to high-end visualization laboratories. Users of InfraVis are offered assistance through a national helpdesk with rapid response times as well as more in-depth projects addressing specific data and software challenges. InfraVis provides software solutions based on development within connected research groups, curation of international software and best practice, and user training in the form of courses, seminars and on-line documentation. To build an infrastructure with national coverage, we have pooled together nine visualization environments in Sweden interconnected in a nodal structure. The nodes are hosted in proximity to research environments in visualization, which enables direct access to the research front as well as to state-of-art facilities. The governance structure of InfraVis is based on the leading researchers in visualization in Sweden as well as an international advisory board.