Research in ML4VIS investigates how to use machine learning (ML) techniques to generate visualizations, and the field is rapidly growing with high societal impact. However, as with any computational pipeline that employs ML processes, ML4VIS approaches are susceptible to a range of ML-specific adversarial attacks. These attacks can manipulate visualization generations, causing analysts to be tricked and their judgments to be impaired. Due to a lack of synthesis from both visualization and ML perspectives, this security aspect is largely overlooked by the current ML4VIS literature. To bridge this gap, we investigate the potential vulnerabilities of ML-aided visualizations from adversarial attacks using a holistic lens of both visualization and ML perspectives. We first identify the attack surface (i.e., attack entry points) that is unique in ML-aided visualizations. We then exemplify five different adversarial attacks. These examples highlight the range of possible attacks when considering the attack surface and multiple different adversary capabilities. Our results show that adversaries can induce various attacks, such as creating arbitrary and deceptive visualizations, by systematically identifying input attributes that are influential in ML inferences. Based on our observations of the attack surface characteristics and the attack examples, we underline the importance of comprehensive studies of security issues and defense mechanisms as a call of urgency for the ML4VIS community.

Industrial applications of Artificial Intelligence (AI) can be hindered by the issues of explainability and trust from end users. Human-computer interaction and eXplainable AI (XAI) concerns become imperative in such scenarios. However, the prior evidence of applying more general principles and techniques in specialized industrial scenarios is often limited. In this case study, we focus on designing interactive interfaces of XAI solutions for operators in the pulp and paper industry. The explanation techniques supported and compared include counterfactual and feature importance explanations. We applied the user-centered design methodology, including the analysis of requirements elicited from operators during site visits and interactive interface prototype evaluation eventually conducted on site with five operators. Our results indicate that the operators preferred the combination of counterfactual and feature importance explanations. The study also provides lessons learned for researchers and practitioners.

Electric power is the foundation of modern society, yet Europe is currently facing an energy crisis, increasing interest in power generation, energy infrastructure, and grid resilience. However, power plant data are complex and multidimensional, making it difficult to gain an overview or understanding. Visualization methods can help to reduce cognitive load and facilitate exploration of such data. In this paper, we propose EuroEnergyVis, a web-based visualization approach designed for the interactive exploration of power plant data across European countries. The design requirements were motivated by gaps identified in prior work. We conducted interviews with six domain experts in power systems and energy, which indicate that our tool enhances the user experience when exploring European power plants. Their reflections also suggest directions for future work.

Similarity-based analysis is a common and intuitive tool for exploring large data sets. For instance, grouping data items by their level of similarity, regarding one or several chosen aspects, can reveal patterns and relations from the intrinsic structure of the data and thus provide important insights in the sense-making process. Existing analytical methods (such as clustering and dimensionality reduction) tend to target questions such as "Which objects are similar?"; but since they are not necessarily well-suited to answer questions such as "How does the result change if we change the similarity criteria?" or "How are the items linked together by the similarity relations?" they do not unlock the full potential of similarity-based analysis—and here we see a gap to fill. In this paper, we propose that the concept of similarity could be regarded as both: (1) a relation between items, and (2) a property in its own, with a specific distribution over the data set. Based on this approach, we developed an embedding-based computational pipeline together with a prototype visual analytics tool which allows the user to perform similarity-based exploration of a large set of scientific publications. To demonstrate the potential of our method, we present two different use cases, and we also discuss the strengths and limitations of our approach.

As extreme weather events such as floods, storms, and heatwaves proliferate, local and regional authorities face challenges in predicting, monitoring, and assessing these events and their impacts. The introduction of impact-based warning services requires detailed, location-specific information on local vulnerability and impacts. This necessitates complementing conventional data with insights from local actors, and to explore novel methods for relevant public data monitoring through social media and news outlets. This paper presents a visual analytics pipeline that was co-developed with practitioners, aiming to detect impacts of extreme weather events, particularly floods, using Volunteered Geographic Information (VGI). The pipeline steps include: collecting VGI from social media, classifying and analysing the data, and visualizing it through an interactive interface. An empirical evaluation study was performed with meteorological and hydrological experts to assess the developed visual interface. The study collected and analysed feedback on the usability of the interface and identified interaction patterns from the experiment’s screen recordings.

The Word Rain text visualisation technique aims to retain the simplicity of the classic word cloud, while addressing some of its limitations. In particular, the Word Rain visualisation uses word embeddings to automatically give the visualised words a semantically meaningful position along the horizontal axis. In this handbook chapter, we showcase how this novel approach for word positioning makes the Word Rain technique suitable for exploring, analysing and comparing texts. More specifically, we show how the Word Rain Python module can be used to visualise longitudinal changes in periodicals published by the Swedish Diabetes Association, and how the Word Rain web service can be used to create visualisations that compare the patient organisation periodicals to journals published by the Swedish Medical Association.

As the levels of automation and reliance on modern artificial intelligence (AI) approaches increase across multiple industries, the importance of the human-centered perspective becomes more evident. Various actors in such industrial applications, including equipment operators and decision makers, have their needs and preferences that often do not align with the decisions produced by black-box models, potentially leading to mistrust and wasted productivity gain opportunities. In this paper, we examine these issues through the lenses of visual analytics and, more broadly, interactive visualization, and we argue that the methods and techniques from these fields can lead to advances in both academic research and industrial innovations concerning the explainability of AI models. To address the existing gap within and across the research and application fields, we propose a conceptual framework for visual analytics design and evaluation for such scenarios, followed by a preliminary roadmap and call to action for the respective communities.

Similarity-based analysis is a powerful and intuitive tool for exploring large data sets, for instance, for revealing patterns by grouping items by similarity or for recommending items based on selected samples. However, similarity is an abstract and subjective property which makes it hard to evaluate by a purely computational approach. Furthermore, there are usually several possible computational models that could be applied to the data, each with its own strengths and weaknesses. With this in mind, we aim to extend the research frontier regarding what impact the choice of a computational model may have on the results. In this paper, we target the scope of embedding-based similarity calculations on text documents and seek to answer the research question: "How can a better understanding of the continuous similarity distribution captured by different models lead to better similarity calculations on document sets?". We propose a new and generic methodology based on similarity network comparison, and based on this approach, we have developed a computational pipeline together with a prototype visual analytics tool that allows the user to easily assess the level of model agreement/disagreement. To demonstrate the potential of our method, as well as showing its application to real world scenarios, we apply it in an experimental setup using three state-of-the-art text embedding models and three different text corpora. In view of the surprisingly low level of model agreement regarding the data, we also discuss strategies for handling model disagreement.

The sensemaking process of large sets of text documents is highly challenging for tasks such as obtaining a comprehensive overview or keeping up with the most important trends and topics. Even though several established methods for condensation and summarization of large text corpora exist, many of them lack the ability to account for difference in prevalence between identified topics, which in turn impedes quantitative analysis. In this paper, we therefore propose a novel prevalence-aware method for topic extraction, and show how it can be used to obtain important insights from two text corpora with very different content. We also implemented a prototype visual analytics tool which guides the user in the search for relevant insights and promotes trust in the yielded results. We have verified our application by a user study, as well as by a validation run on a data set with previously known topic structure. The results clearly show that our approach is suitable for text mining, that is can be used by non-experts, and that it offers features which makes it an interesting candidate for use in several different analyze scenarios.