High-quality exploratory data analysis (EDA) is essential in the data science pipeline, but remains highly dependent on analysts' expertise and effort. While recent LLM-based approaches partially reduce this burden, they struggle to generate effective analysis plans and appropriate insights and visualizations when user intent is abstract. Meanwhile, a vast collection of analysis notebooks produced across platforms and organizations contains rich analytical knowledge that can potentially guide automated EDA. Retrieval-augmented generation (RAG) provides a natural way to leverage such corpora, but general methods often treat notebooks as static documents and fail to fully exploit their potentially knowledge for automating EDA. To address these limitations, we propose NotebookRAG, a method that takes user intent, datasets, and existing notebooks as input to retrieve, enhance, and reuse relevant notebook content for automated EDA generation. For retrieval, we transform code cells into context-enriched executable components, which improve retrieval quality and enable rerun with new data to generate updated visualizations and reliable insights. For generation, an agent leverages enhanced retrieval content to construct effective EDA plans, derive insights, and produce appropriate visualizations. Evidence from a user study with 24 participants confirms the superiority of our method in producing high-quality and intent-aligned EDA notebooks.

Abstract Artificial agents are increasingly integrated into data analysis workflows, carrying out tasks that were primarily done by humans. Our research explores how the introduction of automation recalibrates the dynamic between humans and automating technology. To explore this question, we conducted a scoping review encompassing twenty years of mixed‐initiative visual analytic systems. To describe and contrast the relationship between humans and automation, we developed an integrated taxonomy to delineate the objectives of these mixed‐initiative visual analytics tools, how much automation they support, and the assumed roles of humans. Here, we describe our qualitative approach of integrating existing theoretical frameworks with new codes we developed. Our analysis shows that the visualization research literature lacks consensus on the definition of mixed‐initiative systems and explores a limited potential of the collaborative interaction landscape between people and automation. Our research provides a scaffold to advance the discussion of human‐AI collaboration during visual data analysis. Our integrated taxonomy is available in the form of a web application on https://smonadjemi.github.io/miva .

Virtual Reality (VR) broadcasting has emerged as a promising medium for providing immersive viewing experiences of major sports events such as tennis. However, current VR broadcast systems often lack an effective camera language and do not adequately incorporate dynamic, in-game visualizations, limiting viewer engagement and narrative clarity. To address these limitations, we analyze 400 out-of-play segments from eight major tennis broadcasts to develop a tennis-specific design framework that effectively combines cinematic camera movements with embedded visualizations. We further refine our framework by examining 25 cinematic VR animations, comparing their camera techniques with traditional tennis broadcasts to identify key differences and inform adaptations for VR. Based on data extracted from the broadcast videos, we reconstruct a simulated game that captures the players' and ball's motion and trajectories. Leveraging this design framework and processing pipeline, we develope Beyond the Broadcast, a VR tennis viewing system that integrates embedded visualizations with adaptive camera motions to construct a comprehensive and engaging narrative. Our system dynamically overlays tactical information and key match events onto the simulated environment, enhancing viewer comprehension and narrative engagement while ensuring perceptual immersion and viewing comfort. A user study involving tennis viewers demonstrate that our approach outperforms traditional VR broadcasting methods in delivering an immersive, informative viewing experience.

Update-intensive workloads are prevalent in contemporary OLTP and AI/ML scenarios. An update operation typically involves deleting the old version of the target record and then inserting a new version. In this work, we demonstrate that an LSM-tree faces two issues when dealing with update-intensive workloads. Firstly, the deleted old versions are not promptly garbage collected until they merge with their new versions during compaction. This may lead to space waste and write amplification. Secondly, it is common for an update operation to modify only a small fraction of a data record, such as one of a hundred attributes. However, state-of-the-art LSM-trees fail to effectively utilize the incremental storage strategy, which involves storing only the updated fraction rather than the entire new version to enhance efficiency. In this paper, we propose two techniques, active and fast garbage collection, and adaptive incremental updating, to address these issues, respectively. Active and fast garbage collection probes the distribution of invalid data versions in an LSM-tree and performs garbage collection in a more promptly manner. Adaptive incremental updating applies different storage modes to the update operation to achieve balanced write and read amplification ratios as much as possible. Based on the techniques, we introduce SylphDB implemented based on the codebase of RocksDB and optimized for update-intensive workloads. Experimental results demonstrated that, compared to traditional LSM-tree based systems, SylphDB can improve the efficiency of garbage collection by 2× and reduce write amplification by 20%.

Exploratory data analysis (EDA), coupled with SQL, is essential for data analysts involved in data exploration and analysis. However, data analysts often encounter two primary challenges: (1) the need to craft SQL queries skillfully and (2) the requirement to generate suitable visualization types that enhance the interpretation of query results. Due to its significance, substantial research efforts have been made to explore different approaches to address these challenges, including leveraging large language models (LLMs). However, existing methods fail to meet real-world data exploration requirements primarily due to (1) complex database schema, (2) unclear user intent, (3) limited cross-domain generalization capability, and (4) insufficient end-to-end text-to-visualization capability. This paper presents TiInsight, an automated SQL-based cross-domain exploratory data analysis system. First, we propose a hierarchical data context (i.e., HDC), which leverages LLMs to summarize the contexts related to the database schema, which is crucial for open-world EDA systems to generalize across data domains. Second, the EDA system is divided into four components (i.e., stages): HDC generation, question clarification and decomposition, text-to-SQL generation (i.e., TiSQL), and data visualization (i.e., TiChart). Finally, we implemented an end-to-end EDA system with a user-friendly GUI in the production environment at PingCAP. We have also open-sourced all APIs of TiInsight to facilitate research within the EDA community. Through extensive evaluations by a real-world user study, we demonstrate that TiInsight offers remarkable performance compared to human experts. Additionally, TiSQL achieves an execution accuracy of 86.3% on the Spider dataset when using GPT-4. It also attains an execution accuracy of 60.98% on the Bird test dataset.

Generative text-to-image models, which allow users to create appealing images through a text prompt, have seen a dramatic increase in popularity in recent years. However, most users have a limited understanding of how such models work and often rely on trial and error strategies to achieve satisfactory results. The prompt history contains a wealth of information that could provide users with insights into what has been explored and how the prompt changes impact the output image, yet little research attention has been paid to the visual analysis of such process to support users. We propose the Image Variant Graph, a novel visual representation designed to support comparing prompt-image pairs and exploring the editing history. The Image Variant Graph models prompt differences as edges between corresponding images and presents the distances between images through projection. Based on the graph, we developed the PrompTHis system through co-design with artists. Based on the review and analysis of the prompting history, users can better understand the impact of prompt changes and have a more effective control of image generation. A quantitative user study and qualitative interviews demonstrate that PrompTHis can help users review the prompt history, make sense of the model, and plan their creative process.

Cartograms serve as representations of geographical and abstract data, employing a value-by-area mapping technique. As a variant of the Dorling cartogram, the Demers cartogram utilizes squares instead of circles to represent regions. This alternative approach allows for a more intuitive comparison of regions, utilizing screen space more efficiently. However, a drawback of the Dorling cartogram and its variants lies in the potential displacement of regions from their original positions, ultimately compromising legibility, readability, and accuracy. To tackle this limitation, we propose a novel hybrid cartogram layout algorithm that incorporates topological elements, such as rivers, into Demers cartograms. The presence of rivers significantly impacts both the layout and visual appearance of the cartograms. Through a user study conducted on an Electronic Health Records (EHR) dataset, we evaluate the efficacy of the proposed hybrid layout algorithm. The obtained results illustrate that this approach successfully retains key aspects of the original cartogram while enhancing legibility, readability, and overall accuracy.

Understanding user behavior patterns and visual analysis strategies is a long-standing challenge. Existing approaches rely largely on time-consuming manual processes such as interviews and the analysis of observational data. While it is technically possible to capture a history of user interactions and application states, it remains difficult to extract and describe analysis strategies based on interaction provenance. In this article, we propose a novel visual approach to the meta-analysis of interaction provenance. We capture single and multiple user sessions as graphs of high-dimensional application states. Our meta-analysis is based on two different types of two-dimensional embeddings of these high-dimensional states: layouts based on (i) topology and (ii) attribute similarity. We applied these visualization approaches to synthetic and real user provenance data captured in two user studies. From our visualizations, we were able to extract patterns for data types and analytical reasoning strategies.

Abstract Epidemiologists use individual‐based models to (a) simulate disease spread over dynamic contact networks and (b) to investigate strategies to control the outbreak. These model simulations generate complex ‘infection maps’ of time‐varying transmission trees and patterns of spread. Conventional statistical analysis of outputs offers only limited interpretation. This paper presents a novel visual analytics approach for the inspection of infection maps along with their associated metadata, developed collaboratively over 16 months in an evolving emergency response situation. We introduce the concept of representative trees that summarize the many components of a time‐varying infection map while preserving the epidemiological characteristics of each individual transmission tree. We also present interactive visualization techniques for the quick assessment of different control policies. Through a series of case studies and a qualitative evaluation by epidemiologists, we demonstrate how our visualizations can help improve the development of epidemiological models and help interpret complex transmission patterns.

Abstract There is fast‐growing literature on provenance‐related research, covering aspects such as its theoretical framework, use cases, and techniques for capturing, visualizing, and analyzing provenance data. As a result, there is an increasing need to identify and taxonomize the existing scholarship. Such an organization of the research landscape will provide a complete picture of the current state of inquiry and identify knowledge gaps or possible avenues for further investigation. In this STAR, we aim to produce a comprehensive survey of work in the data visualization and visual analytics field that focus on the analysis of user interaction and provenance data. We structure our survey around three primary questions: (1) WHY analyze provenance data, (2) WHAT provenance data to encode and how to encode it, and (3) HOW to analyze provenance data. A concluding discussion provides evidence‐based guidelines and highlights concrete opportunities for future development in this emerging area. The survey and papers discussed can be explored online interactively at https://provenance-survey.caleydo.org .

Sensemaking is described as the process of comprehension, finding meaning and gaining insight from information, producing new knowledge and informing further action. Understanding the sensemaking process allows building effective visual analytics tools to make sense of large and complex datasets. Currently, it is often a manual and time-consuming undertaking to comprehend this: researchers collect observation data, transcribe screen capture videos and think-aloud recordings, identify recurring patterns, and eventually abstract the sensemaking process into a general model. In this paper, we propose a general approach to facilitate such a qualitative analysis process, and introduce a prototype, SensePath, to demonstrate the application of this approach with a focus on browser-based online sensemaking. The approach is based on a study of a number of qualitative research sessions including observations of users performing sensemaking tasks and post hoc analyses to uncover their sensemaking processes. Based on the study results and a follow-up participatory design session with HCI researchers, we decided to focus on the transcription and coding stages of thematic analysis. SensePath automatically captures user's sensemaking actions, i.e., analytic provenance, and provides multi-linked views to support their further analysis. A number of other requirements elicited from the design session are also implemented in SensePath, such as easy integration with existing qualitative analysis workflow and non-intrusive for participants. The tool was used by an experienced HCI researcher to analyze two sensemaking sessions. The researcher found the tool intuitive and considerably reduced analysis time, allowing better understanding of the sensemaking process.

Timeline visualization is an important tool for sense making. It allows analysts to examine information in chronological order and to identify temporal patterns and relationships. However, many existing timeline visualization methods are not designed for the dynamic and iterative nature of the sense making process and the various analysis activities it involves. In this paper, we introduce a novel timeline visualization, Schema Line, to address these deficiencies. Schema Line is designed to group notes into analyst-determined schema, using a layout algorithm to produce compact but aesthetically pleasing timeline visualization, and includes fluid user interactions to support sense making activities. It enables interactive temporal schemata construction with seamless integration with visual data exploration and note taking. Our preliminary evaluation results show that the participants found the new method easy to learn and use, and its features effective for the sense making activities for which it was designed.

We describe and demonstrate an extensible framework that supports data exploration and provenance in the context of Human Terrain Analysis (HTA). Working closely with defence analysts we extract requirements and a list of features that characterise data analysed at the end of the HTA chain. From these, we select an appropriate non-classified data source with analogous features, and model it as a set of facets. We develop ProveML, an XML-based extension of the Open Provenance Model, using these facets and augment it with the structures necessary to record the provenance of data, analytical process and interpretations. Through an iterative process, we develop and refine a prototype system for Human Terrain Visual Analytics (HTVA), and demonstrate means of storing, browsing and recalling analytical provenance and process through analytic bookmarks in ProveML. We show how these bookmarks can be combined to form narratives that link back to the live data. Throughout the process, we demonstrate that through structured workshops, rapid prototyping and structured communication with intelligence analysts we are able to establish requirements, and design schema, techniques and tools that meet the requirements of the intelligence community. We use the needs and reactions of defence analysts in defining and steering the methods to validate the framework.

Recently there has been increasing research interest in displaying graphs with curved edges to produce more readable visualizations. While there are several automatic techniques, little has been done to evaluate their effectiveness empirically. In this paper we present two experiments studying the impact of edge curvature on graph readability. The goal is to understand the advantages and disadvantages of using curved edges for common graph tasks compared to straight line segments, which are the conventional choice for showing edges in node-link diagrams. We included several edge variations: straight edges, edges with different curvature levels, and mixed straight and curved edges. During the experiments, participants were asked to complete network tasks including determination of connectivity, shortest path, node degree, and common neighbors. We also asked the participants to provide subjective ratings of the aesthetics of different edge types. The results show significant performance differences between the straight and curved edges and clear distinctions between variations of curved edges.

Many real-world networks are multivariate, i.e., they have attributes associated with nodes and/or edges. Examples include social networks whose nodes represent people and edges represent relationships. There is usually information about each person (such as name, age, and gender) and the relationship (such type, duration, and strength). Besides common graph analysis tasks (such as identifying the most influential or structurally important nodes), there are more complex analyses for multivariate networks. One of these is the multivariate graph clustering, i.e., identifying clusters formed by nodes that have similar attributes and are close to each other in terms of graph distance. For instance, in social network analysis, it is interesting to sociologists whether or not people with similar characteristics (node attributes) are also connected to each other. Currently there are very few visualization methods available for such analysis.

This paper investigates a new problem of visualizing a set of overlapping networks. We present two methods for constructing visualization of two and three overlapping networks in three dimensions. Our methods aim to achieve both drawing aesthetics (or conventions) for each individual network and exposing the common nodes between the overlapping networks. We evaluated our approaches using biological networks including protein interaction network, metabolic network, and gene regulatory network, from the bacterium Escherichia coli and crop plants to demonstrate their usefulness to support biological analysis.

With a fast paced development of bioinformatics in recent years, we have witnessed a rapid growth of the number of databases and tools available for aiding in scientific research and knowledge discovery for bioinformaticians. Web service is an enabling technique to facilitate bioinformaticians in this discovery process by integrating the databases and tools. In this paper, we will propose a novel system, called bio-sense, for supporting the sharing and exploration in bioinformatics using semantic Web services. The promising features of bio-sense will be discussed in this paper.

A k-NN query finds the k nearest-neighbors of a given point from a point database. When it is sufficient to measure object distance using the Euclidian distance, the key to efficient k-NN query processing is to fetch and check the distances of a minimum number of points from the database. For many applications, such as vehicle movement along road networks or rover and animal movement along terrain surfaces, the distance is only meaningful when it is along a valid movement path. For this type of k-NN queries, the focus of efficient query processing is to minimize the cost of computing distances using the environment data (such as the road network data and the terrain data), which can be several orders of magnitude larger than that of the point data. Efficient processing of k-NN queries based on the Euclidian distance or the road network distance has been investigated extensively in the past. In this paper, we investigate the problem of surface k-NN query processing, where the distance is calculated from the shortest path along a terrain surface. This problem is very challenging, as the terrain data can be very large and the computational cost of finding shortest paths is very high. We propose an efficient solution based on multiresolution terrain models. Our approach eliminates the need of costly process of finding shortest paths by ranking objects using estimated lower and upper bounds of distance on multiresolution terrain models.

Multiresolution Triangular Mesh (MTM) models are widely used to improve the performance of large terrain visualization by replacing the original model with a simplified one. MTM models, which consist of both original and simplified data, are commonly stored in spatial database systems due to their size. The relatively slow access speed of disks makes data retrieval the bottleneck of such terrain visualization systems. Existing spatial access methods proposed to address this problem rely on main-memory MTM models, which leads to significant overhead during query processing. In this paper, we approach the problem from a new perspective and propose a novel MTM called direct mesh that is designed specifically for secondary storage. It supports available indexing methods natively and requires no modification to MTM structure. Experiment results, which are based on two real-world data sets, show an average performance improvement of 5-10 times over the existing methods.

Terrain can be approximated by a triangular mesh consisting millions of 3D points. Multiresolution triangular mesh (MTM) structures are designed to support applications that use terrain data at variable levels of detail (LOD). Typically, an MTM adopts a tree structure where a parent node represents a lower-resolution approximation of its descendants. Given a region of interest (ROI) and a LOD, the process of retrieving the required terrain data from the database is to traverse the MTM tree from the root to reach all the nodes satisfying the ROI and LOD conditions. This process, while being commonly used for multiresolution terrain visualization, is inefficient as either a large number of sequential I/O operations or fetching a large amount of extraneous data is incurred. Various spatial indexes have been proposed in the past to address this problem, however level-by-level tree traversal remains a common practice in order to obtain topological information among the retrieved terrain data. A new MTM data structure called direct mesh is proposed. We demonstrate that with direct mesh the amount of data retrieval can be substantially reduced. Comparing with existing MTM indexing methods, a significant performance improvement has been observed for real-life terrain data.