The importance of data-driven decision-making is rapidly increasing thanks in part to the growing availability and accessibility of data sets and analysis tools. Yet, applicable insight can be difficult due to biases and anomalies in data. An often overlooked phenomenon is mix effects , in which subgroups of data exhibit patterns opposite to the data as a whole. This phenomenon is widespread and often leads inexperienced analysts to draw incorrect statistical conclusions. In this paper we present Wiggum, an interactive visual analysis system for uncovering both mix effects and special cases known as Simpson’s paradox . A Python-based web implementation of Wiggum lets users interactively analyze multidimensional data sets to reveal various forms of mix effects. Through use cases, we describe how Wiggum supports the examination of mix effects in three real data sets and demonstrate how a combination of visualization techniques—heatmaps, trend plots, small multiples, coordinated multiple views, and dynamic queries for multi-attribute drill-down—are effective for analyzing mix effects. We conducted a user study to evaluate Wiggum, focusing on users’ ability to comprehend the statistical concepts, identify the corresponding visual patterns, and perform common analysis tasks correctly and efficiently. We discuss usability issues, utility limitations, and outline future directions to improve Wiggum.

There are many challenging decision-making situations due to high degrees of uncertainty, turbulence, information burden, interdependencies and competing decision criteria in complex environments such as military command and control and emergency response. Unfortunately, few decision support systems help these cognitively challenged decision makers understand the relative desirability of one course of action versus another, also known as option awareness (OA). We hypothesized that providing novel data visualization displays to compare options across multiple criteria in parallel, combined with interaction mechanisms tailored to exploring options, would improve decision makers’ abilities to make better choices more confidently. To test our hypothesis, we created a design inspired by principles of OA and the forementioned challenges and instantiated it in a patented proof-of-concept implementation called the Multi-criteria Option Comparison Application (MOCA). We experimented with MOCA in command and control and emergency response scenarios with subject matter experts and obtained statistically significant quantitative data showing the participants believed their use of a MOCA-like OA application will result in more accurate and confident choices, an enhanced ability to consider multiple perspectives and relevant decision factors, and eight other benefits. Additionally, qualitative data analyses surfaced themes of innovation, discovery, collaboration, ambiguity reduction, assumption validation, and interactivity.

Immersive virtual reality (VR) environments are increasingly utilized to support training in safety-critical fields such as construction, transportation, healthcare, and emergency response. However, the reliability of these simulations depends not only on visual fidelity but also on how well user perception and behavior in virtual environments correspond with real-world expectations. This paper presents the VR Training Readiness Evaluation Model (VTREM), a cross-domain model for assessing the perceptual and behavioral credibility of scenario-based VR training systems. VTREM comprises three integrated components: a Spatial Realism Test to evaluate distance and size perception; an Action Credibility Test to examine whether motor responses align with real-world behaviors; and a Response Variability Analysis to measure behavioral consistency across users and simulation conditions. The model is based on an experimental study of egocentric distance estimation and demonstrates applicability across various industry contexts, including fire services, process plants, aviation, and healthcare. By positioning immersive environments as behaviorally expressive systems, VTREM contributes novel insights to the field of information visualization, broadening the concept of data interpretation to encompass embodied spatial decision-making. The model enables simulation designers and educators to systematically validate training environments, thereby enhancing both instructional integrity and operational preparedness.

This study presents a prototype for visualizing artifact information, allowing museum professionals to manage and utilize it without needing computer science expertise. The proposed prototype enables users to enter and manage data pertaining to artifacts and visualize the information in various methods using the entered data. Therefore, museum professionals can use it in various practical settings, such as discovering new relationships between artifacts, deriving research and exhibition topics, and developing content. This study utilized data from approximately 270 traditional paintings and 70 painters from the Joseon Dynasty of Korea to implement the visualization. Users can identify the association between the works using the patterns depicted in the paintings and their implied meanings based on the network graphs. The region of activity, period of activity, and frequency of pattern usage can be visualized by artists by combining maps, timelines, and word clouds, depending on the characteristics of the data. The developed prototype was compared with Gephi and Neo4j, commercial network graph generation tools, to determine whether it had sufficient functions for visualizing artifact information. The main process of data visualization was divided into data management, data visualization, and data exploration, while the necessary details for each step were determined as the criteria of the comparative analysis. They were compared after entering the same data into each software. The comparative evaluation was conducted in the process of creating and exploring network graphs.

There is a growing interest in presenting data clearly to users. One of the ways to increase engagement and understanding of this data is through narrative visualizations, as they utilize elements that can enhance understanding of the presented data in different ways. In this context, after a literature review on elements of narrative data visualizations, we identified a gap in detailed descriptions of narrative genres. Considering this, we conducted a focus group with professionals in the field, which resulted in the concept called “Navis Structure.” It organizes narrative genres into components for design assistance. In this case, the genres can be single-component or multi-component. Additionally, these genres were classified, considering not only this structure but also visual representation, interaction techniques, freedom of exploration, and narrative approach. Finally, we conducted a workshop with professionals experienced in data visualization to analyze and validate the proposed concept, believing that the findings contribute to advancing the understanding of narrative genres and guide future research in narrative data visualizations.

Data visualization tools are important tools for making health decisions based on large amounts of data. However, very few comparisons of data visualization tools have been done in the context of health-related research. This paper compares commonly available visualization tools from the perspective of a dashboard developer in the context of scientific health research using real-world data and to provide general suggestions for dashboard developers’ future visualization efforts in health-related scientific discoveries. We evaluated four commonly available visualization tools (Tableau, Spotfire, PowerBI, and R Shiny). Each tool was evaluated on visualization outcomes (comparing the generated outputs of tables, scatterplots, correlation plots, treemaps, heatmaps, and geographic maps), usability, Cloud compatibility, analytic integration, and a few other factors. All tools generated comparable visualization outcomes in our tests and were equally usable with the exception of R Shiny which is not recommended for users with limited coding experience. Every tool except R Shiny supports connections to PostgreSQL, gSheets, and Athena without additional configurations. All tools support integration with R and Python; however, PowerBI requires some additional configuration. Every tool is capable of data pre-processing and supports data transformation, null detection and outlier detection. Each tool has its own unique advantages and limitations.

Understanding how a classification result is generated and what role individual features play in the classification is crucial in many applications and, in particular, in medical contexts such as the translation of diagnosis biomarkers into clinical practice. The goal is to find (ideally simple) relationships between the features in multi-dimensional data and the classification for an explanation of the underlying phenomenon. Mathematical formulas allow for the expression of these relationships and can serve as classifiers. However, there are infinitely many mathematical formulas for the given features and they bear an inherent trade-off between complexity and accuracy. We present an interactive visual approach that supports domain experts to mitigate the trade-off issue. Core to our approach is a novel feature selection method, from which formulas are composed using symbolic regression and where state-of-the-art classifiers serve as a reference. To evaluate our approach and compare the achieved classification performance to the performance achieved by other state-of-the-art feature selection techniques, we test our methods with well-known machine learning data sets. Our evaluation shows that our feature selection method performs better than randomly selecting features for data sets with many features or when a low number of generations in the symbolic regression is required. Moreover, it consistently matches or outperforms state-of-the-art methods. Moreover, we apply our approach in a case study to a hemodynamic cohort data set, where we report our findings and domain expert feedback. Our approach was able to find formulas containing features that are in agreement with literature. Also, we could find formulas that performed better in the micro-averaged F1 score when compared to established histological indices.

Decision Trees (DTs) stand out as a prevalent choice among supervised Machine Learning algorithms. These algorithms form binary structures, effectively dividing data into smaller segments based on distinct rules. Consequently, DTs serve as a learning mechanism to identify optimal rules for the separation and classification of all elements within a dataset. Due to their resemblance to rule-based decisions, DTs are easy to interpret. Additionally, their minimal need for data pre-processing and versatility in handling various data types make DTs highly practical and user-friendly across diverse domains. Nevertheless, when confronted with extensive datasets or ensembles involving multiple trees, such as Random Forests, its analysis can become challenging. To facilitate the examination and validation of these models, we have developed a visual tool that incorporates a range of visualisations providing both an overview and detailed insights into a set of DTs. Our tool is designed to offer diverse perspectives on the same data, enabling a deeper understanding of the decision-making process. This article outlines our design approach, introduces various visualisation models, and details the iterative validation process. We validate our methodology through a telecommunications use case, specifically employing the visual tool to decipher how a DT-based model determines the optimal communication channel (i.e. phone call, email, SMS) for a telecommunication operator to use when contacting a client.

Keeping abreast of current trends, technologies, and best practices in visualization and data analysis is becoming increasingly difficult, especially for fledgling data scientists. In this paper, we propose lodestar, an interactive computational notebook that allows users to quickly explore and construct new data science workflows by selecting from a list of automated analysis recommendations. We derive our recommendations from directed graphs of known analysis states, with two input sources: one manually curated from online data science tutorials, and another extracted through semi-automatic analysis of a corpus of over 6000 Jupyter notebooks. We validated Lodestar through three separate user studies: first a formative evaluation involving novices learning data science using the tool. We used the feedback from this study to improve the tool. This was followed by a summative study involving both new and returning participants from the formative evaluation to test the efficacy of our improvements. We also engaged professional data scientists in an expert review assessing the utility of the different recommendations. Overall, our results suggest that both novice and professional users find Lodestar useful for rapidly creating data science workflows.

Incidental visualizations are meant to be perceived at-a-glance, on-the-go, and during short exposure times, but are not seen on demand. Instead, they appear in people’s fields of view during an ongoing primary task. They differ from glanceable visualizations because the information is not received on demand, and they differ from ambient visualizations because the information is not continuously embedded in the environment. However, current graphical perception guidelines do not consider situations where information is presented at specific moments during brief exposure times without being the user’s primary focus. Therefore, we conducted a crowdsourced user study with 99 participants to understand how accurate people’s incidental graphical perception is. Each participant was tested on one of the three conditions: position of dots, length of lines, and angle of lines. We varied the number of elements for each combination and the display time. During the study, participants were asked to perform reproduction tasks, where they had to recreate a previously shown stimulus in each. Our results indicate that incidental graphical perception can be accurate when using position, length, and angles. Furthermore, we argue that incidental visualizations should be designed for low exposure times (between 300 and 1000 ms).