Decision-making requires examining underlying assumptions and concepts, considering diverse perspectives, and weighing potential consequences with clear, accurate reasoning. Recent large language models (LLMs) show promise for assisting decision-makers by combining reasoning capabilities with the ability to retrieve relevant information from large documents. However, our formative study with five professional decision-makers revealed key limitations of using LLM in workflow: time-consuming alignment of user goals, lack of evidence-based grounding, overwhelmingly long outputs, and unsurfaced assumptions undermined user trust in the LLM output and the validity of the final decision. We introduce Criticality, a system that operationalizes the Paul-Elder Critical Thinking framework to structure reasoning into interactive Elements of Thought (e.g., purpose, assumptions, perspectives, implications), and evaluates and guides reasoning using Intellectual Standards (e.g., clarity, fairness, logic). It also retrieves evidence for each claim, classifies it as supporting, neutral, or contradictory, and explains the claim-evidence link. A within-subjects study (n=13) comparing Criticality to ChatGPT 5 Pro, a state-of-the-art reasoning model in conversational interface, found that Criticality improved user interaction of steering and repairing through the decision-making process, producing better decision rationales compared to the baseline.

The temporal dynamics of quantitative metrics or key performance indicators (KPIs) are central to conversations in enterprise organizations. Recently, major business intelligence providers have introduced new infrastructure for defining, sharing, and monitoring metric values. However, these values are often presented in isolation and appropriate context is seldom externalized. In this design study, we present REMIXTAPE, an application for constructing structured narratives around metrics. With design imperatives grounded in prior work and a formative interview study, REMIXTAPE provides a hierarchical canvas for collecting and coordinating sequences of line chart representations of metrics, along with the ability to externalize situational context around them. REMIXTAPE includes affordances to semantically align and annotate juxtaposed charts and text, as well as recommendations of complementary charts based on metrics already present on the canvas. We evaluated REMIXTAPE in a study in which six enterprise data professionals reproduced and extended partial narratives. They appreciated REMIXTAPE as a novel alternative to dashboards, galleries, and slide presentations for supporting conversations about metrics. Finally, we reflect on REMIXTAPE’s usability and potential utility, and conclude with a call to define a conceptual foundation for remixing in the context of visualization.

Dashboards remain ubiquitous tools for analyzing data and disseminating the findings. Understanding the range of dashboard designs, from simple to complex, can support development of authoring tools that enable end-users to meet their analysis and communication goals. Yet, there has been little work that provides a quantifiable, systematic, and descriptive overview of dashboard design patterns. Instead, existing approaches only consider a handful of designs, which limits the breadth of patterns that can be surfaced. More quantifiable approaches, inspired by machine learning (ML), are presently limited to single visualizations or capture narrow features of dashboard designs. To address this gap, we present an approach for modeling the content and composition of dashboards using a graph representation. The graph decomposes dashboard designs into nodes featuring content "blocks'; and uses edges to model "relationships", such as layout proximity and interaction, between nodes. To demonstrate the utility of this approach, and its extension over prior work, we apply this representation to derive a census of 25,620 dashboards from Tableau Public, providing a descriptive overview of the core building blocks of dashboards in the wild and summarizing prevalent dashboard design patterns. We discuss concrete applications of both a graph representation for dashboard designs and the resulting census to guide the development of dashboard authoring tools, making dashboards accessible, and for leveraging AI/ML techniques. Our findings underscore the importance of meeting users where they are by broadly cataloging dashboard designs, both common and exotic.

In a data-driven society, being able to examine data on one’s own terms is crucial for various aspects of well-being. However, current data exploration paradigms, such as Exploratory Data Analysis (EDA), heavily rely on visualizations to unveil patterns and insights. This visual-centric approach poses significant challenges for blind and low-vision (BLV) individuals. To address this gap, we built a prototype that supports non-visual data exploration and conducted an observational user study involving 18 BLV participants. Participants were asked to conduct various analytical tasks, as well as free exploration of provided datasets. The study findings provide insights into the factors influencing inefficient data exploration and characterizations of BLV participants’ analytical behaviors. We conclude by highlighting future avenues of research for the design of data exploration tools for BLV users.

Visualization tools now commonly present automated insights highlighting salient data patterns, including correlations, distributions, outliers, and differences, among others. While these insights are valuable for data exploration and chart interpretation, users currently only have a binary choice of accepting or rejecting them, lacking the flexibility to refine the system logic or customize the insight generation process. To address this limitation, we present Groot, a prototype system that allows users to proactively specify and refine automated data insights. The system allows users to directly manipulate chart elements to receive insight recommendations based on their selections. Additionally, Groot provides users with a manual editing interface to customize, reconfigure, or add new insights to individual charts and propagate them to future explorations. We describe a usage scenario to illustrate how these features collectively support insight editing and configuration and discuss opportunities for future work, including incorporating Large Language Models (LLMs), improving semantic data and visualization search, and supporting insight management.

To enable data-driven decision-making across organizations, data professionals need to share insights with their colleagues in context-appropriate communication channels. Many of their colleagues rely on data but are not themselves analysts; furthermore, their colleagues are reluctant or unable to use dedicated analytical applications or dashboards, and they expect communication to take place within threaded collaboration platforms such as Slack or Microsoft Teams. In this paper, we introduce a set of six strategies for adapting content from business intelligence (BI) dashboards into appropriate formats for sharing on collaboration platforms, formats that we refer to as dashboard snapshots. Informed by prior studies of enterprise communication around data, these strategies go beyond redesigning or restyling by considering varying levels of data literacy across an organization, introducing affordances for self-service question-answering, and anticipating the post-sharing lifecycle of data artifacts. These strategies involve the use of templates that are matched to common communicative intents, serving to reduce the workload of data professionals. We contribute a formal representation of these strategies and demonstrate their applicability in a comprehensive enterprise communication scenario featuring multiple stakeholders that unfolds over the span of months.

Dashboards are frequently used to monitor and share data across a breadth of domains including business, finance, sports, public policy, and healthcare, just to name a few. The combination of different components (e.g., key performance indicators, charts, filtering widgets) and the interactivity between components makes dashboards powerful interfaces for data monitoring and analysis. However, these very characteristics also often make dashboards inaccessible to blind and low vision (BLV) users. Through a co-design study with two screen reader users, we investigate challenges faced by BLV users and identify design goals to support effective screen reader-based interactions with dashboards. Operationalizing the findings from the co-design process, we present a prototype system, Azimuth, that generates dashboards optimized for screen reader-based navigation along with complementary descriptions to support dashboard comprehension and interaction. Based on a follow-up study with five BLV participants, we showcase how our generated dashboards support BLV users and enable them to perform both targeted and open-ended analysis. Reflecting on our design process and study feedback, we discuss opportunities for future work on supporting interactive data analysis, understanding dashboard accessibility at scale, and investigating alternative devices and modalities for designing accessible visualization dashboards.

Data visualizations can be complex or involve numerous data points, making them impractical to navigate using screen readers alone. Question answering (QA) systems have the potential to support visualization interpretation and exploration without overwhelming blind and low vision (BLV) users. To investigate if and how QA systems can help BLV users in working with visualizations, we conducted a Wizard of Oz study with 24 BLV people where participants freely posed queries about four visualizations. We collected 979 queries and mapped them to popular analytic task taxonomies. We found that retrieving value and finding extremum were the most common tasks, participants often made complex queries and used visual references, and the data topic notably influenced the queries. We compile a list of design considerations for accessible chart QA systems and make our question corpus publicly available to guide future research and development.

Search and information retrieval systems are becoming more expressive in interpreting user queries beyond the traditional weighted bag-of-words model of document retrieval. For example, searching for a flight status or a game score returns a dynamically generated response along with supporting, pre-authored documents contextually relevant to the query. In this paper, we extend this hybrid search paradigm to data repositories that contain curated data sources and visualization content. We introduce a semantic search interface, Olio, that provides a hybrid set of results comprising both auto-generated visualization responses and pre-authored charts to blend analytical question-answering with content discovery search goals. We specifically explore three search scenarios - question-and-answering, exploratory search, and design search over data repositories. The interface also provides faceted search support for users to refine and filter the conventional best-first search results based on parameters such as author name, time, and chart type. A preliminary user evaluation of the system demonstrates that Olio’s interface and the hybrid search paradigm collectively afford greater expressivity in how users discover insights and visualization content in data repositories.

The language for expressing comparisons is often complex and nuanced, making supporting natural language-based visual comparison a non-trivial task. To better understand how people reason about comparisons in natural language, we explore a design space of utterances for comparing data entities. We identified different parameters of comparison utterances that indicate what is being compared (i.e., data variables and attributes) as well as how these parameters are specified (i.e., explicitly or implicitly). We conducted a user study with sixteen data visualization experts and non-experts to investigate how they designed visualizations for comparisons in our design space. Based on the rich set of visualization techniques observed, we extracted key design features from the visualizations and synthesized them into a subset of sixteen representative visualization designs. We then conducted a follow-up study to validate user preferences for the sixteen representative visualizations corresponding to utterances in our design space. Findings from these studies suggest guidelines and future directions for designing natural language interfaces and recommendation tools to better support natural language comparisons in visual analytics.

Despite the ever-growing popularity of dashboards across a wide range of domains, their authoring still remains a tedious and complex process. Current tools offer considerable support for creating individual visualizations but provide limited support for discovering groups of visualizations that can be collectively useful for composing analytic dashboards. To address this problem, we present MEDLEY, a mixed-initiative interface that assists in dashboard composition by recommending dashboard collections (i.e., a logically grouped set of views and filtering widgets) that map to specific analytical intents. Users can specify dashboard intents (namely, measure analysis, change analysis, category analysis, or distribution analysis) explicitly through an input panel in the interface or implicitly by selecting data attributes and views of interest. The system recommends collections based on these analytic intents, and views and widgets can be selected to compose a variety of dashboards. MEDLEY also provides a lightweight direct manipulation interface to configure interactions between views in a dashboard. Based on a study with 13 participants performing both targeted and open-ended tasks, we discuss how MEDLEY's recommendations guide dashboard composition and facilitate different user workflows. Observations from the study identify potential directions for future work, including combining manual view specification with dashboard recommendations and designing natural language interfaces for dashboard authoring.

Most mobile health apps employ data visualization to help people view their health and activity data, but these apps provide limited support for visual data exploration. Furthermore, despite its huge potential benefits, mobile visualization research in the personal data context is sparse. This work aims to empower people to easily navigate and compare their personal health data on smartphones by enabling flexible time manipulation with speech. We designed and developed [email protected], a mobile app that leverages the synergy of two complementary modalities: speech and touch. Through an exploratory study with 13 long-term Fitbit users, we examined how multimodal interaction helps participants explore their own health data. Participants successfully adopted multimodal interaction (i.e., speech and touch) for convenient and fluid data exploration. Based on the quantitative and qualitative findings, we discuss design implications and opportunities with multimodal interaction for better supporting visual data exploration on mobile devices.

Natural language interfaces (NLIs) for data visualization are becoming increasingly popular both in academic research and in commercial software. Yet, there is a lack of empirical understanding of how people specify visualizations through natural language. We conducted an online study (N = 102), showing participants a series of visualizations and asking them to provide utterances they would pose to generate the displayed charts. From the responses, we curated a dataset of 893 utterances and characterized the utterances according to (1) their phrasing (e.g., commands, queries, questions) and (2) the information they contained (e.g., chart types, data aggregations). To help guide future research and development, we contribute this utterance dataset and discuss its applications toward the creation and benchmarking of NLIs for visualization.

Humans are known to construct cognitive maps of their everyday surroundings using a variety of perceptual inputs. As such, when a human is asked for directions to a particular location, their wayfinding capability in converting this cognitive map into directional instructions is challenged. Owing to spatial anxiety, the language used in the spoken instructions can be vague and often unclear. To account for this unreliability in navigational guidance, we propose a novel Deep Reinforcement Learning (DRL) based trust-driven robot navigation algorithm that learns humans’ trustworthiness to perform a language guided navigation task.Our approach seeks to answer the question as to whether a robot can trust a human’s navigational guidance or not. To this end, we look at training a policy that learns to navigate towards a goal location using only trustworthy human guidance, driven by its own robot trust metric. We look at quantifying various affective features from language-based instructions and incorporate them into our policy’s observation space in the form of a human trust metric. We utilize both these trust metrics into an optimal cognitive reasoning scheme that decides when and when not to trust the given guidance. Our results show that the learned policy can navigate the environment in an optimal, time-efficient manner as opposed to an explorative approach that performs the same task. We showcase the efficacy of our results both in simulation and a real world environment.

Natural language interfaces (NLIs) have become a prevalent medium for conducting visual data analysis, enabling people with varying levels of analytic experience to ask questions of and interact with their data. While there have been notable improvements with respect to language understanding capabilities in these systems, fundamental user experience and interaction challenges including the lack of analytic guidance (i.e., knowing what aspects of the data to consider) and discoverability of natural language input (i.e., knowing how to phrase input utterances) persist. To address these challenges, we investigate utterance recommendations that contextually provide analytic guidance by suggesting data features (e.g., attributes, values, trends) while implicitly making users aware of the types of phrasings that an NLI supports. We present Snowy, a prototype system that generates and recommends utterances for visual analysis based on a combination of data interestingness metrics and language pragmatics. Through a preliminary user study, we found that utterance recommendations in Snowy support conversational visual analysis by guiding the participants’ analytic workflows and making them aware of the system’s language interpretation capabilities. Based on the feedback and observations from the study, we discuss potential implications and considerations for incorporating recommendations in future NLIs for visual analysis.

Natural language interfaces (NLls) have shown great promise for visual data analysis, allowing people to flexibly specify and interact with visualizations. However, developing visualization NLIs remains a challenging task, requiring low-level implementation of natural language processing (NLP) techniques as well as knowledge of visual analytic tasks and visualization design. We present NL4DV, a toolkit for natural language-driven data visualization. NL4DV is a Python package that takes as input a tabular dataset and a natural language query about that dataset. In response, the toolkit returns an analytic specification modeled as a JSON object containing data attributes, analytic tasks, and a list of Vega-Lite specifications relevant to the input query. In doing so, NL4DV aids visualization developers who may not have a background in NLP, enabling them to create new visualization NLIs or incorporate natural language input within their existing systems. We demonstrate NL4DV's usage and capabilities through four examples: 1) rendering visualizations using natural language in a Jupyter notebook, 2) developing a NLI to specify and edit Vega-Lite charts, 3) recreating data ambiguity widgets from the DataTone system, and 4) incorporating speech input to create a multimodal visualization system.

Multimodal interfaces that combine direct manipulation and natural language have shown great promise for data visualization. Such multimodal interfaces allow people to stay in the flow of their visual exploration by leveraging the strengths of one modality to complement the weaknesses of others. In this article, we introduce an approach that interweaves multimodal interaction combining direct manipulation and natural language with flexible unit visualizations. We employ the proposed approach in a proof-of-concept system, DataBreeze. Coupling pen, touch, and speech-based multimodal interaction with flexible unit visualizations, DataBreeze allows people to create and interact with both systematically bound (e.g., scatterplots, unit column charts) and manually customized views, enabling a novel visual data exploration experience. We describe our design process along with DataBreeze's interface and interactions, delineating specific aspects of the design that empower the synergistic use of multiple modalities. We also present a preliminary user study with DataBreeze, highlighting the data exploration patterns that participants employed. Finally, reflecting on our design process and preliminary user study, we discuss future research directions.

While tablet devices are a promising platform for data visualization, supporting consistent interactions across different types of visualizations on tablets remains an open challenge. In this paper, we present multimodal interactions that function consistently across different visualizations, supporting common operations during visual data analysis. By considering standard interface elements (e.g., axes, marks) and grounding our design in a set of core concepts including operations, parameters, targets, and instruments, we systematically develop interactions applicable to different visualization types. To exemplify how the proposed interactions collectively facilitate data exploration, we employ them in a tablet-based system, InChorus that supports pen, touch, and speech input. Based on a study with 12 participants performing replication and factchecking tasks with InChorus, we discuss how participants adapted to using multimodal input and highlight considerations for future multimodal visualization systems.

Interaction plays a vital role during visual network exploration as users need to engage with both elements in the view (e.g., nodes, links) and interface controls (e.g., sliders, dropdown menus). Particularly as the size and complexity of a network grow, interactive displays supporting multimodal input (e.g., touch, speech, pen, gaze) exhibit the potential to facilitate fluid interaction during visual network exploration and analysis. While multimodal interaction with network visualization seems like a promising idea, many open questions remain. For instance, do users actually prefer multimodal input over unimodal input, and if so, why? Does it enable them to interact more naturally, or does having multiple modes of input confuse users? To answer such questions, we conducted a qualitative user study in the context of a network visualization tool, comparing speech- and touch-based unimodal interfaces to a multimodal interface combining the two. Our results confirm that participants strongly prefer multimodal input over unimodal input attributing their preference to: 1) the freedom of expression, 2) the complementary nature of speech and touch, and 3) integrated interactions afforded by the combination of the two modalities. We also describe the interaction patterns participants employed to perform common network visualization operations and highlight themes for future multimodal network visualization systems to consider.

Discovering what to say and how to say it remains a challenge for users of multimodal interfaces supporting speech input. Users end up "guessing" commands that a system might support, often leading to interpretation errors and frustration. One solution to this problem is to display contextually relevant command examples as users interact with a system. The challenge, however, is deciding when, how, and which examples to recommend. In this work, we describe an approach for generating and ranking natural language command examples in multimodal interfaces. We demonstrate the approach using a prototype touch- and speech-based image editing tool. We experiment with augmentations of the UI to understand when and how to present command examples. Through an online user study, we evaluate these alternatives and find that in-situ command suggestions promote discovery and encourage the use of speech input.

Recently, an increasing number of visualization systems have begun to incorporate natural language generation (NLG) capabilities into their interfaces. NLG-based visualization systems typically leverage a suite of statistical functions to automatically extract key facts about the underlying data and surface them as natural language sentences alongside visualizations. With current systems, users are typically required to read the system-generated sentences and mentally map them back to the accompanying visualization. However, depending on the features of the visualization (e.g., visualization type, data density) and the complexity of the data fact, mentally mapping facts to visualizations can be a challenging task. Furthermore, more than one visualization could be used to illustrate a single data fact. Unfortunately, current tools provide little or no support for users to explore such alternatives. In this paper, we explore how system-generated data facts can be treated as interactive widgets to help users interpret visualizations and communicate their findings. We present Voder, a system that lets users interact with automatically-generated data facts to explore both alternative visualizations to convey a data fact as well as a set of embellishments to highlight a fact within a visualization. Leveraging data facts as interactive widgets, Voder also facilitates data fact-based visualization search. To assess Voder's design and features, we conducted a preliminary user study with 12 participants having varying levels of experience with visualization tools. Participant feedback suggested that interactive data facts aided them in interpreting visualizations. Participants also stated that the suggestions surfaced through the facts helped them explore alternative visualizations and embellishments to communicate individual data facts.

Multimodal interaction offers many potential benefits for data visualization. It can help people stay in the flow of their visual analysis and presentation, with the strengths of one interaction modality offsetting the weaknesses of others. Furthermore, multimodal interaction offers strong promise for leveraging data visualization on diverse display hardware including mobile, AR/VR, and large displays. However, prior research on visualization and interaction techniques has mostly explored a single input modality such as mouse, touch, pen, or more recently, natural language. The unique challenges and opportunities of synergistic multimodal interaction for data visualization have yet to be investigated. This workshop will bring together researchers with expertise in visualization, interaction design, and natural user interfaces. We aim to build a community of researchers focusing on multimodal interaction for data visualization, explore opportunities and challenges in our research, and establish an agenda for multimodal interaction research specifically for data visualization.

Touch-based displays are becoming a popular medium for interacting with visualizations. Network visualizations are a frequently used class of visualizations across domains to explore entities and relationships between them. However, little work has been done in exploring the design of network visualizations and corresponding interactive tasks such as selection, browsing, and navigation on touch-based displays. Network visualizations on touch-based displays are usually implemented by porting the conventional pointer based interactions as-is to a touch environment and replacing the mouse cursor with a finger. However, this approach does not fully utilize the potential of naturalistic multi-touch gestures afforded by touch displays. We present a set of single hand, multi-touch gestures for interactive exploration of network visualizations and employ these in a prototype system, Tangraphe. We discuss the proposed interactions and how they facilitate a variety of commonly performed network visualization tasks including selection, navigation, adjacency-based exploration, and layout modification. We also discuss advantages of and potential extensions to the proposed set of one-handed interactions including leveraging the non-dominant hand for enhanced interaction, incorporation of additional input modalities, and integration with other devices.

An increasingly common approach to data analysis involves using information dashboards to visually compare changing data. However, layout constraints coupled with varying levels of visualization literacy among dashboard users make facilitating visual comparison in dashboards a challenging task. In this paper, we evaluate variants of bar charts, one of the most prevalent class of charts used in dashboards. We report an online experiment (N = 74) conducted to evaluate four alternative designs: 1) grouped bar chart, 2) grouped bar chart with difference overlays, 3) bar chart with difference overlays, and 4) difference bar chart. Results show that charts with difference overlays facilitate a wider range of comparison tasks while performing comparably to charts without them on individual tasks. Finally, we discuss the implications of our findings, with a focus on supporting visual comparison in dashboards.

User interfaces for data visualization often consist of two main components: control panels for user interaction and visual representation. A recent trend in visualization is directly embedding user interaction into the visual representations. For example, instead of using control panels to adjust visualization parameters, users can directly adjust basic graphical encodings (e.g., changing distances between points in a scatterplot) to perform similar parameterizations. However, enabling embedded interactions for data visualization requires a strong understanding of how user interactions influence the ability to accurately control and perceive graphical encodings. In this paper, we study the effectiveness of these graphical encodings when serving as the method for interaction. Our user study includes 12 interactive graphical encodings. We discuss the results in terms of task performance and interaction effectiveness metrics.

Network visualizations, often in the form of node-link diagrams, are an effective means to understand relationships between entities, discover entities with interesting characteristics, and to identify clusters. While several existing tools allow users to visualize pre-defined networks, creating these networks from raw data remains a challenging task, often requiring users to program custom scripts or write complex SQL commands. Some existing tools also allow users to both visualize and model networks. Interaction techniques adopted by these tools often assume users know the exact conditions for defining edges in the resulting networks. This assumption may not always hold true, however. In cases where users do not know much about attributes in the dataset or when there are several attributes to choose from, users may not know which attributes they could use to formulate linking conditions. We propose an alternate interaction technique to model networks that allows users to demonstrate to the system a subset of nodes and links they wish to see in the resulting network. The system, in response, recommends conditions that can be used to model networks based on the specified nodes and links. In this paper, we show how such a demonstration-based interaction technique can be used to model networks by employing it in a prototype tool, Graphiti. Through multiple usage scenarios, we show how Graphiti not only allows users to model networks from a tabular dataset but also facilitates updating a pre-defined network with additional edge types.

Data visualization systems have predominantly been developed for WIMP-based direct manipulation interfaces. Only recently have other forms of interaction begun to appear, such as natural language or touch-based interaction, though usually operating only independently. Prior evaluations of natural language interfaces for visualization have indicated potential value in combining direct manipulation and natural language as complementary interaction techniques. We hypothesize that truly multimodal interfaces for visualization, those providing users with freedom of expression via both natural language and touch-based direct manipulation input, may provide an effective and engaging user experience. Unfortunately, however, little work has been done in exploring such multimodal visualization interfaces. To address this gap, we have created an architecture and a prototype visualization system called Orko that facilitates both natural language and direct manipulation input. Specifically, Orko focuses on the domain of network visualization, one that has largely relied on WIMP-based interfaces and direct manipulation interaction, and has little or no prior research exploring natural language interaction. We report results from an initial evaluation study of Orko, and use our observations to discuss opportunities and challenges for future work in multimodal network visualization interfaces.