Search

Large Language Models (LLMs) have gained significant attention but also raised concerns due to the risk of misuse. Jailbreak prompts, a popular type of adversarial attack towards LLMs, have appeared and constantly evolved to breach the safety protocols of LLMs. To address this issue, LLMs are regularly updated with safety patches based on reported jailbreak prompts. However, malicious users often keep their successful jailbreak prompts private to exploit LLMs. To uncover these private jailbreak prompts, extensive analysis of large-scale conversational datasets is necessary to identify prompts that still manage to bypass the system's defenses. This task is highly challenging due to the immense volume of conversation data, diverse characteristics of jailbreak prompts, and their presence in complex multi-turn conversations. To tackle these challenges, we introduce JailbreakHunter, a visual analytics approach for identifying jailbreak prompts in large-scale human-LLM conversational datasets. We have designed a workflow with three analysis levels: group-level, conversation-level, and turn-level. Group-level analysis enables users to grasp the distribution of conversations and identify suspicious conversations using multiple criteria, such as similarity with reported jailbreak prompts in previous research and attack success rates. Conversation-level analysis facilitates the understanding of the progress of conversations and helps discover jailbreak prompts within their conversation contexts. Turn-level analysis allows users to explore the semantic similarity and token overlap between a singleturn prompt and the reported jailbreak prompts, aiding in the identification of new jailbreak strategies. The effectiveness and usability of the system were verified through multiple case studies and expert interviews., Comment: 18 pages, 9 figures

Exploratory visual data analysis tools empower data analysts to efficiently and intuitively explore data insights throughout the entire analysis cycle. However, the gap between common programmatic analysis (e.g., within computational notebooks) and exploratory visual analysis leads to a disjointed and inefficient data analysis experience. To bridge this gap, we developed PyGWalker, a Python library that offers on-the-fly assistance for exploratory visual data analysis. It features a lightweight and intuitive GUI with a shelf builder modality. Its loosely coupled architecture supports multiple computational environments to accommodate varying data sizes. Since its release in February 2023, PyGWalker has gained much attention, with 612k downloads on PyPI and over 10.5k stars on GitHub as of June 2024. This demonstrates its value to the data science and visualization community, with researchers and developers integrating it into their own applications and studies., Comment: To appear at the IEEE VIS Conference 2024

Large language models (LLMs) have exhibited impressive abilities for multimodal content comprehension and reasoning with proper prompting in zero- or few-shot settings. Despite the proliferation of interactive systems developed to support prompt engineering for LLMs across various tasks, most have primarily focused on textual or visual inputs, thus neglecting the complex interplay between modalities within multimodal inputs. This oversight hinders the development of effective prompts that guide model multimodal reasoning processes by fully exploiting the rich context provided by multiple modalities. In this paper, we present POEM, a visual analytics system to facilitate efficient prompt engineering for enhancing the multimodal reasoning performance of LLMs. The system enables users to explore the interaction patterns across modalities at varying levels of detail for a comprehensive understanding of the multimodal knowledge elicited by various prompts. Through diverse recommendations of demonstration examples and instructional principles, POEM supports users in iteratively crafting and refining prompts to better align and enhance model knowledge with human insights. The effectiveness and efficiency of our system are validated through two case studies and interviews with experts., Comment: 11 pages, 5 figures

The escalating frequency and intensity of heat-related climate events, particularly heatwaves, emphasize the pressing need for advanced heat risk management strategies. Current approaches, primarily relying on numerical models, face challenges in spatial-temporal resolution and in capturing the dynamic interplay of environmental, social, and behavioral factors affecting heat risks. This has led to difficulties in translating risk assessments into effective mitigation actions. Recognizing these problems, we introduce a novel approach leveraging the burgeoning capabilities of Large Language Models (LLMs) to extract rich and contextual insights from news reports. We hence propose an LLM-empowered visual analytics system, Havior, that integrates the precise, data-driven insights of numerical models with nuanced news report information. This hybrid approach enables a more comprehensive assessment of heat risks and better identification, assessment, and mitigation of heat-related threats. The system incorporates novel visualization designs, such as "thermoglyph" and news glyph, enhancing intuitive understanding and analysis of heat risks. The integration of LLM-based techniques also enables advanced information retrieval and semantic knowledge extraction that can be guided by experts' analytics needs. Our case studies on two cities that faced significant heatwave events and interviews with five experts have demonstrated the usefulness of our system in providing in-depth and actionable insights for heat risk management.

Text animation serves as an expressive medium, transforming static communication into dynamic experiences by infusing words with motion to evoke emotions, emphasize meanings, and construct compelling narratives. Crafting animations that are semantically aware poses significant challenges, demanding expertise in graphic design and animation. We present an automated text animation scheme, termed "Dynamic Typography", which combines two challenging tasks. It deforms letters to convey semantic meaning and infuses them with vibrant movements based on user prompts. Our technique harnesses vector graphics representations and an end-to-end optimization-based framework. This framework employs neural displacement fields to convert letters into base shapes and applies per-frame motion, encouraging coherence with the intended textual concept. Shape preservation techniques and perceptual loss regularization are employed to maintain legibility and structural integrity throughout the animation process. We demonstrate the generalizability of our approach across various text-to-video models and highlight the superiority of our end-to-end methodology over baseline methods, which might comprise separate tasks. Through quantitative and qualitative evaluations, we demonstrate the effectiveness of our framework in generating coherent text animations that faithfully interpret user prompts while maintaining readability. Our code is available at: https://animate-your-word.github.io/demo/., Comment: Our demo page is available at: https://animate-your-word.github.io/demo/

Computational notebooks are widely utilized for exploration and analysis. However, creating slides to communicate analysis results from these notebooks is quite tedious and time-consuming. Researchers have proposed automatic systems for generating slides from notebooks, which, however, often do not consider the process of users conceiving and organizing their messages from massive code cells. Those systems ask users to go directly into the slide creation process, which causes potentially ill-structured slides and burdens in further refinement. Inspired by the common and widely recommended slide creation practice: drafting outlines first and then adding concrete content, we introduce OutlineSpark, an AI-powered slide creation tool that generates slides from a slide outline written by the user. The tool automatically retrieves relevant notebook cells based on the outlines and converts them into slide content. We evaluated OutlineSpark with 12 users. Both the quantitative and qualitative feedback from the participants verify its effectiveness and usability., Comment: To appear in Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI 2024)

Recent achievements in deep learning (DL) have shown its potential for predicting traffic flows. Such predictions are beneficial for understanding the situation and making decisions in traffic control. However, most state-of-the-art DL models are considered "black boxes" with little to no transparency for end users with respect to the underlying mechanisms. Some previous work tried to "open the black boxes" and increase the interpretability of how predictions are generated. However, it still remains challenging to handle complex models on large-scale spatio-temporal data and discover salient spatial and temporal patterns that significantly influence traffic flows. To overcome the challenges, we present TrafPS, a visual analytics approach for interpreting traffic prediction outcomes to support decision-making in traffic management and urban planning. The measurements, region SHAP and trajectory SHAP, are proposed to quantify the impact of flow patterns on urban traffic at different levels. Based on the task requirement from the domain experts, we employ an interactive visual interface for multi-aspect exploration and analysis of significant flow patterns. Two real-world case studies demonstrate the effectiveness of TrafPS in identifying key routes and decision-making support for urban planning.

Higher-order patterns reveal sequential multistep state transitions, which are usually superior to origin-destination analysis, which depicts only first-order geospatial movement patterns. Conventional methods for higher-order movement modeling first construct a directed acyclic graph (DAG) of movements, then extract higher-order patterns from the DAG. However, DAG-based methods heavily rely on the identification of movement keypoints that are challenging for sparse movements and fail to consider the temporal variants that are critical for movements in urban environments. To overcome the limitations, we propose HoLens, a novel approach for modeling and visualizing higher-order movement patterns in the context of an urban environment. HoLens mainly makes twofold contributions: first, we design an auto-adaptive movement aggregation algorithm that self-organizes movements hierarchically by considering spatial proximity, contextual information, and temporal variability; second, we develop an interactive visual analytics interface consisting of well-established visualization techniques, including the H-Flow for visualizing the higher-order patterns on the map and the higher-order state sequence chart for representing the higher-order state transitions. Two real-world case studies manifest that the method can adaptively aggregate the data and exhibit the process of how to explore the higher-order patterns by HoLens. We also demonstrate our approach's feasibility, usability, and effectiveness through an expert interview with three domain experts., Comment: 20 pages, 18 figures, is accepted by computational visual media journal

Financial cluster analysis allows investors to discover investment alternatives and avoid undertaking excessive risks. However, this analytical task faces substantial challenges arising from many pairwise comparisons, the dynamic correlations across time spans, and the ambiguity in deriving implications from business relational knowledge. We propose Prismatic, a visual analytics system that integrates quantitative analysis of historical performance and qualitative analysis of business relational knowledge to cluster correlated businesses interactively. Prismatic features three clustering processes: dynamic cluster generation, knowledge-based cluster exploration, and correlation-based cluster validation. Utilizing a multi-view clustering approach, it enriches data-driven clusters with knowledge-driven similarity, providing a nuanced understanding of business correlations. Through well-coordinated visual views, Prismatic facilitates a comprehensive interpretation of intertwined quantitative and qualitative features, demonstrating its usefulness and effectiveness via case studies on formulating concept stocks and extensive interviews with domain experts., Comment: 14 pages. A preprint version submitted to IEEE Transactions on Visualization and Computer Graphics (TVCG), 2024

The global aging trend compels older adults to navigate the evolving digital landscape, presenting a substantial challenge in mastering smartphone applications. While Augmented Reality (AR) holds promise for enhancing learning and user experience, its role in aiding older adults' smartphone app exploration remains insufficiently explored. Therefore, we conducted a two-phase study: (1) a workshop with 18 older adults to identify app exploration challenges and potential AR interventions, and (2) tech-probe participatory design sessions with 15 participants to co-create AR support tools. Our research highlights AR's effectiveness in reducing physical and cognitive strain among older adults during app exploration, especially during multi-app usage and the trial-and-error learning process. We also examined their interactional experiences with AR, yielding design considerations on tailoring AR tools for smartphone app exploration. Ultimately, our study unveils the prospective landscape of AR in supporting the older demographic, both presently and in future scenarios.

Multiplayer Online Battle Arenas (MOBAs) have gained a significant player base worldwide, generating over two billion US dollars in annual game revenue. However, the presence of griefers, who deliberately irritate and harass other players within the game, can have a detrimental impact on players' experience, compromising game fairness and potentially leading to the emergence of gray industries. Unfortunately, the absence of a standardized criterion, and the lack of high-quality labeled and annotated data has made it challenging to detect the presence of griefers. Given the complexity of the multivariant spatiotemporal data for MOBA games, game developers heavily rely on manual review of entire game video recordings to label and annotate griefers, which is a time-consuming process. To alleviate this issue, we have collaborated with a team of game specialists to develop an interactive visual analysis interface, called GrieferLens. It overviews players' behavior analysis and synthesizes their key match events. By presenting multiple views of information, GrieferLens can help the game design team efficiently recognize and label griefers in MOBA games and build up a foundation for creating a more enjoyable and fair gameplay environment., Comment: IEEE VIS 2023 (Poster)

Automated visualization recommendation facilitates the rapid creation of effective visualizations, which is especially beneficial for users with limited time and limited knowledge of data visualization. There is an increasing trend in leveraging machine learning (ML) techniques to achieve an end-to-end visualization recommendation. However, existing ML-based approaches implicitly assume that there is only one appropriate visualization for a specific dataset, which is often not true for real applications. Also, they often work like a black box, and are difficult for users to understand the reasons for recommending specific visualizations. To fill the research gap, we propose AdaVis, an adaptive and explainable approach to recommend one or multiple appropriate visualizations for a tabular dataset. It leverages a box embedding-based knowledge graph to well model the possible one-to-many mapping relations among different entities (i.e., data features, dataset columns, datasets, and visualization choices). The embeddings of the entities and relations can be learned from dataset-visualization pairs. Also, AdaVis incorporates the attention mechanism into the inference framework. Attention can indicate the relative importance of data features for a dataset and provide fine-grained explainability. Our extensive evaluations through quantitative metric evaluations, case studies, and user interviews demonstrate the effectiveness of AdaVis.

Recent advances in mobile augmented reality (AR) techniques have shed new light on personal visualization for their advantages of fitting visualization within personal routines, situating visualization in a real-world context, and arousing users' interests. However, enabling non-experts to create data visualization in mobile AR environments is challenging given the lack of tools that allow in-situ design while supporting the binding of data to AR content. Most existing AR authoring tools require working on personal computers or manually creating each virtual object and modifying its visual attributes. We systematically study this issue by identifying the specificity of AR glyph-based visualization authoring tool and distill four design considerations. Following these design considerations, we design and implement MARVisT, a mobile authoring tool that leverages information from reality to assist non-experts in addressing relationships between data and virtual glyphs, real objects and virtual glyphs, and real objects and data. With MARVisT, users without visualization expertise can bind data to real-world objects to create expressive AR glyph-based visualizations rapidly and effortlessly, reshaping the representation of the real world with data. We use several examples to demonstrate the expressiveness of MARVisT. A user study with non-experts is also conducted to evaluate the authoring experience of MARVisT.

This paper presents an authoring environment for augmenting static visualizations with virtual content in augmented reality. Augmenting static visualizations can leverage the best of both physical and digital worlds, but its creation currently involves different tools and devices, without any means to explicitly design and debug both static and virtual content simultaneously. To address these issues, we design an environment that seamlessly integrates all steps of a design and deployment workflow through its main features: i) an extension to Vega, ii) a preview, and iii) debug hints that facilitate valid combinations of static and augmented content. We inform our design through a design space with four ways to augment static visualizations. We demonstrate the expressiveness of our tool through examples, including books, posters, projections, wall-sized visualizations. A user study shows high user satisfaction of our environment and confirms that participants can create augmented visualizations in an average of 4.63 minutes.

Data storytelling is powerful for communicating data insights, but it requires diverse skills and considerable effort from human creators. Recent research has widely explored the potential for artificial intelligence (AI) to support and augment humans in data storytelling. However, there lacks a systematic review to understand data storytelling tools from the perspective of human-AI collaboration, which hinders researchers from reflecting on the existing collaborative tool designs that promote humans' and AI's advantages and mitigate their shortcomings. This paper investigated existing tools with a framework from two perspectives: the stages in the storytelling workflow where a tool serves, including analysis, planning, implementation, and communication, and the roles of humans and AI in each stage, such as creators, assistants, optimizers, and reviewers. Through our analysis, we recognize the common collaboration patterns in existing tools, summarize lessons learned from these patterns, and further illustrate research opportunities for human-AI collaboration in data storytelling., Comment: Accepted by CHI 2024

Understanding how local environments influence individual behaviors, such as voting patterns or suicidal tendencies, is crucial in social science to reveal and reduce spatial disparities and promote social well-being. With the increasing availability of large-scale individual-level census data, new analytical opportunities arise for social scientists to explore human behaviors (e.g., political engagement) among social groups at a fine-grained level. However, traditional statistical methods mostly focus on global, aggregated spatial correlations, which are limited to understanding and comparing the impact of local environments (e.g., neighborhoods) on human behaviors among social groups. In this study, we introduce a new analytical framework for analyzing multi-variate neighborhood effects between social groups. We then propose NeighVi, an interactive visual analytics system that helps social scientists explore, understand, and verify the influence of neighborhood effects on human behaviors. Finally, we use a case study to illustrate the effectiveness and usability of our system., Comment: Symposium on Visualization in Data Science (VDS) at IEEE VIS 2023

Data charts are prevalent across various fields due to their efficacy in conveying complex data relationships. However, static charts may sometimes struggle to engage readers and efficiently present intricate information, potentially resulting in limited understanding. We introduce "Live Charts," a new format of presentation that decomposes complex information within a chart and explains the information pieces sequentially through rich animations and accompanying audio narration. We propose an automated approach to revive static charts into Live Charts. Our method integrates GNN-based techniques to analyze the chart components and extract data from charts. Then we adopt large natural language models to generate appropriate animated visuals along with a voice-over to produce Live Charts from static ones. We conducted a thorough evaluation of our approach, which involved the model performance, use cases, a crowd-sourced user study, and expert interviews. The results demonstrate Live Charts offer a multi-sensory experience where readers can follow the information and understand the data insights better. We analyze the benefits and drawbacks of Live Charts over static charts as a new information consumption experience., Comment: Accepted by IEEE TVCG

Although visualization tools are widely available and accessible, not everyone knows the best practices and guidelines for creating accurate and honest visual representations of data. Numerous books and articles have been written to expose the misleading potential of poorly constructed charts and teach people how to avoid being deceived by them or making their own mistakes. These readings use various rhetorical devices to explain the concepts to their readers. In our analysis of a collection of books, online materials, and a design workshop, we identified six common explanation methods. To assess the effectiveness of these methods, we conducted two crowdsourced studies (each with N = 125) to evaluate their ability to teach and persuade people to make design changes. In addition to these existing methods, we brought in the idea of Explorable Explanations, which allows readers to experiment with different chart settings and observe how the changes are reflected in the visualization. While we did not find significant differences across explanation methods, the results of our experiments indicate that, following the exposure to the explanations, the participants showed improved proficiency in identifying deceptive charts and were more receptive to proposed alterations of the visualization design. We discovered that participants were willing to accept more than 60% of the proposed adjustments in the persuasiveness assessment. Nevertheless, we found no significant differences among different explanation methods in convincing participants to accept the modifications., Comment: To be presented at IEEE VIS 2023

Vocabulary learning support tools have widely exploited existing materials, e.g., stories or video clips, as contexts to help users memorize each target word. However, these tools could not provide a coherent context for any target words of learners' interests, and they seldom help practice word usage. In this paper, we work with teachers and students to iteratively develop Storyfier, which leverages text generation models to enable learners to read a generated story that covers any target words, conduct a story cloze test, and use these words to write a new story with adaptive AI assistance. Our within-subjects study (N=28) shows that learners generally favor the generated stories for connecting target words and writing assistance for easing their learning workload. However, in the read-cloze-write learning sessions, participants using Storyfier perform worse in recalling and using target words than learning with a baseline tool without our AI features. We discuss insights into supporting learning tasks with generative models., Comment: To appear at the 2023 ACM Symposium on User Interface Software and Technology (UIST); 16 pages (7 figures, 23 tables)

Constructing supervised machine learning models for real-world video analysis require substantial labeled data, which is costly to acquire due to scarce domain expertise and laborious manual inspection. While data programming shows promise in generating labeled data at scale with user-defined labeling functions, the high dimensional and complex temporal information in videos poses additional challenges for effectively composing and evaluating labeling functions. In this paper, we propose VideoPro, a visual analytics approach to support flexible and scalable video data programming for model steering with reduced human effort. We first extract human-understandable events from videos using computer vision techniques and treat them as atomic components of labeling functions. We further propose a two-stage template mining algorithm that characterizes the sequential patterns of these events to serve as labeling function templates for efficient data labeling. The visual interface of VideoPro facilitates multifaceted exploration, examination, and application of the labeling templates, allowing for effective programming of video data at scale. Moreover, users can monitor the impact of programming on model performance and make informed adjustments during the iterative programming process. We demonstrate the efficiency and effectiveness of our approach with two case studies and expert interviews., Comment: 11 pages, 7 figures

With appealing visual effects, kinetic typography (animated text) has prevailed in movies, advertisements, and social media. However, it remains challenging and time-consuming to craft its animation scheme. We propose an automatic framework to transfer the animation scheme of a rigid body on a given meme GIF to text in vector format. First, the trajectories of key points on the GIF anchor are extracted and mapped to the text's control points based on local affine transformation. Then the temporal positions of the control points are optimized to maintain the text topology. We also develop an authoring tool that allows intuitive human control in the generation process. A questionnaire study provides evidence that the output results are aesthetically pleasing and well preserve the animation patterns in the original GIF, where participants were impressed by a similar emotional semantics of the original GIF. In addition, we evaluate the utility and effectiveness of our approach through a workshop with general users and designers., Comment: Accepted in the 36th Annual ACM Symposium on User Interface Software and Technology (UIST'23)

Food waste presents a substantial challenge with significant environmental and economic ramifications, and its severity on campus environments is of particular concern. In response to this, we introduce FoodWise, a dual-component system tailored to inspire and incentivize campus communities to reduce food waste. The system consists of a data storytelling dashboard that graphically displays food waste information from university canteens, coupled with a mobile web application that encourages users to log their food waste reduction actions and rewards active participants for their efforts. Deployed during a two-week food-saving campaign at The Hong Kong University of Science and Technology (HKUST) in March 2023, FoodWise engaged over 200 participants from the university community, resulting in the logging of over 800 daily food-saving actions. Feedback collected post-campaign underscores the system's efficacy in elevating user consciousness about food waste and prompting behavioral shifts towards a more sustainable campus. This paper also provides insights for enhancing our system, contributing to a broader discourse on sustainable campus initiatives., Comment: Accepted in ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies (COMPASS) 2023

Recently, large pretrained language models have achieved compelling performance on commonsense benchmarks. Nevertheless, it is unclear what commonsense knowledge the models learn and whether they solely exploit spurious patterns. Feature attributions are popular explainability techniques that identify important input concepts for model outputs. However, commonsense knowledge tends to be implicit and rarely explicitly presented in inputs. These methods cannot infer models' implicit reasoning over mentioned concepts. We present CommonsenseVIS, a visual explanatory system that utilizes external commonsense knowledge bases to contextualize model behavior for commonsense question-answering. Specifically, we extract relevant commonsense knowledge in inputs as references to align model behavior with human knowledge. Our system features multi-level visualization and interactive model probing and editing for different concepts and their underlying relations. Through a user study, we show that CommonsenseVIS helps NLP experts conduct a systematic and scalable visual analysis of models' relational reasoning over concepts in different situations., Comment: This paper is accepted by IEEE VIS, 2023. To appear in IEEE Transactions on Visualization and Computer Graphics (IEEE TVCG). 14 pages, 11 figures

Multiplayer Online Battle Arenas (MOBAs) have garnered a substantial player base worldwide. Nevertheless, the presence of noxious players, commonly referred to as "actors", can significantly compromise game fairness by exhibiting negative behaviors that diminish their team's competitive edge. Furthermore, high-level actors tend to engage in more egregious conduct to evade detection, thereby causing harm to the game community and necessitating their identification. To tackle this urgent concern, a partnership was formed with a team of game specialists from a prominent company to facilitate the identification and labeling of high-level actors in MOBA games. We first characterize the problem and abstract data and events from the game scene to formulate design requirements. Subsequently, ActorLens, a visual analytics system, was developed to exclude low-level actors, detect potential high-level actors, and assist users in labeling players. ActorLens furnishes an overview of players' status, summarizes behavioral patterns across three player cohorts (namely, focused players, historical matches of focused players, and matches of other players who played the same hero), and synthesizes key match events. By incorporating multiple views of information, users can proficiently recognize and label high-level actors in MOBA games. We conducted case studies and user studies to demonstrate the efficacy of the system., Comment: 15 pages, 9 figures

Computational notebooks have become increasingly popular for exploratory data analysis due to their ability to support data exploration and explanation within a single document. Effective documentation for explaining chart findings during the exploration process is essential as it helps recall and share data analysis. However, documenting chart findings remains a challenge due to its time-consuming and tedious nature. While existing automatic methods alleviate some of the burden on users, they often fail to cater to users' specific interests. In response to these limitations, we present InkSight, a mixed-initiative computational notebook plugin that generates finding documentation based on the user's intent. InkSight allows users to express their intent in specific data subsets through sketching atop visualizations intuitively. To facilitate this, we designed two types of sketches, i.e., open-path and closed-path sketch. Upon receiving a user's sketch, InkSight identifies the sketch type and corresponding selected data items. Subsequently, it filters data fact types based on the sketch and selected data items before employing existing automatic data fact recommendation algorithms to infer data facts. Using large language models (GPT-3.5), InkSight converts data facts into effective natural language documentation. Users can conveniently fine-tune the generated documentation within InkSight. A user study with 12 participants demonstrated the usability and effectiveness of InkSight in expressing user intent and facilitating chart finding documentation., Comment: Accepted by VIS23

Visualizing data in sports videos is gaining traction in sports analytics, given its ability to communicate insights and explicate player strategies engagingly. However, augmenting sports videos with such data visualizations is challenging, especially for sports analysts, as it requires considerable expertise in video editing. To ease the creation process, we present a design space that characterizes augmented sports videos at an element-level (what the constituents are) and clip-level (how those constituents are organized). We do so by systematically reviewing 233 examples of augmented sports videos collected from TV channels, teams, and leagues. The design space guides selection of data insights and visualizations for various purposes. Informed by the design space and close collaboration with domain experts, we design VisCommentator, a fast prototyping tool, to eases the creation of augmented table tennis videos by leveraging machine learning-based data extractors and design space-based visualization recommendations. With VisCommentator, sports analysts can create an augmented video by selecting the data to visualize instead of manually drawing the graphical marks. Our system can be generalized to other racket sports (e.g., tennis, badminton) once the underlying datasets and models are available. A user study with seven domain experts shows high satisfaction with our system, confirms that the participants can reproduce augmented sports videos in a short period, and provides insightful implications into future improvements and opportunities.

We propose emordle, a conceptual design that animates wordles (compact word clouds) to deliver their emotional context to the audiences. To inform the design, we first reviewed online examples of animated texts and animated wordles, and summarized strategies for injecting emotion into the animations. We introduced a composite approach that extends an existing animation scheme for one word to multiple words in a wordle with two global factors: the randomness of text animation (entropy) and the animation speed (speed). To create an emordle, general users can choose one predefined animated scheme that matches the intended emotion class and fine-tune the emotion intensity with the two parameters. We designed proof-of-concept emordle examples for four basic emotion classes, namely happiness, sadness, anger, and fear. We conducted two controlled crowdsourcing studies to evaluate our approach. The first study confirmed that people generally agreed on the conveyed emotions from well-crafted animations, and the second one demonstrated that our identified factors helped fine-tune the delivered emotion extent. We also invited general users to create emordles on their own based on our proposed framework. Through this user study, we confirmed the effectiveness of the approach. We concluded with implications for future research opportunities of supporting emotion expression in visualizations., Comment: Accepted in IEEE Transactions on Visualization and Computer Graphics

Data storytelling plays an important role in data workers' daily jobs since it boosts team collaboration and public communication. However, to make an appealing data story, data workers spend tremendous efforts on various tasks, including outlining and styling the story. Recently, a growing research trend has been exploring how to assist data storytelling with advanced artificial intelligence (AI). However, existing studies may focus on individual tasks in the workflow of data storytelling and do not reveal a complete picture of humans' preference for collaborating with AI. To better understand real-world needs, we interviewed eighteen data workers from both industry and academia to learn where and how they would like to collaborate with AI. Surprisingly, though the participants showed excitement about collaborating with AI, many of them also expressed reluctance and pointed out nuanced reasons. Based on their responses, we first characterize stages and tasks in the practical data storytelling workflows and the desired roles of AI. Then the preferred collaboration patterns in different tasks are identified. Next, we summarize the interviewees' reasons why and why not they would like to collaborate with AI. Finally, we provide suggestions for human-AI collaborative data storytelling to hopefully shed light on future related research.

Data videos are becoming increasingly popular in society and academia. Yet little is known about how to create endings that strengthen a lasting impression and persuasion. To fulfill the gap, this work aims to develop guidelines for data video endings by drawing inspiration from cinematic arts. To contextualize cinematic endings in data videos, 111 film endings and 105 data video endings are first analyzed to identify four common styles using the framework of ending punctuation marks. We conducted expert interviews (N=11) and formulated 20 guidelines for creating cinematic endings in data videos. To validate our guidelines, we conducted a user study where 24 participants were invited to design endings with and without our guidelines, which are evaluated by experts and the general public. The participants praise the clarity and usability of the guidelines, and results show that the endings with guidelines are perceived to be more understandable, impressive, and reflective.

This paper introduces semi-automatic data tours to aid the exploration of complex networks. Exploring networks requires significant effort and expertise and can be time-consuming and challenging. Distinct from guidance and recommender systems for visual analytics, we provide a set of goal-oriented tours for network overview, ego-network analysis, community exploration, and other tasks. Based on interviews with five network analysts, we developed a user interface (NetworkNarratives) and 10 example tours. The interface allows analysts to navigate an interactive slideshow featuring facts about the network using visualizations and textual annotations. On each slide, an analyst can freely explore the network and specify nodes, links, or subgraphs as seed elements for follow-up tours. Two studies, comprising eight expert and 14 novice analysts, show that data tours reduce exploration effort, support learning about network exploration, and can aid the dissemination of analysis results. NetworkNarratives is available online, together with detailed illustrations for each tour., Comment: 15 pages. Published as a conference paper at the ACM Conference on Human Factors in Computing Systems (CHI) 2023

In geographic data videos, camera movements are frequently used and combined to present information from multiple perspectives. However, creating and editing camera movements requires significant time and professional skills. This work aims to lower the barrier of crafting diverse camera movements for geographic data videos. First, we analyze a corpus of 66 geographic data videos and derive a design space of camera movements with a dimension for geospatial targets and one for narrative purposes. Based on the design space, we propose a set of adaptive camera shots and further develop an interactive tool called GeoCamera. This interactive tool allows users to flexibly design camera movements for geographic visualizations. We verify the expressiveness of our tool through case studies and evaluate its usability with a user study. The participants find that the tool facilitates the design of camera movements., Comment: 15 pages. Published as a conference paper at the ACM Conference on Human Factors in Computing Systems (CHI) 2023

Computational notebooks are widely used for data analysis. Their interleaved displays of code and execution results (e.g., visualizations) are welcomed since they enable iterative analysis and preserve the exploration process. However, the communication of data findings remains challenging in computational notebooks. Users have to carefully identify useful findings from useless ones, document them with texts and visual embellishments, and then organize them in different tools. Such workflow greatly increases their workload, according to our interviews with practitioners. To address the challenge, we designed Notable to offer on-the-fly assistance for data storytelling in computational notebooks. It provides intelligent support to minimize the work of documenting and organizing data findings and diminishes the cost of switching between data exploration and storytelling. To evaluate Notable, we conducted a user study with 12 data workers. The feedback from user study participants verifies its effectiveness and usability., Comment: To appear in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI 2023)

Delivering customer services through video communications has brought new opportunities to analyze customer satisfaction for quality management. However, due to the lack of reliable self-reported responses, service providers are troubled by the inadequate estimation of customer services and the tedious investigation into multimodal video recordings. We introduce Anchorage, a visual analytics system to evaluate customer satisfaction by summarizing multimodal behavioral features in customer service videos and revealing abnormal operations in the service process. We leverage the semantically meaningful operations to introduce structured event understanding into videos which help service providers quickly navigate to events of their interest. Anchorage supports a comprehensive evaluation of customer satisfaction from the service and operation levels and efficient analysis of customer behavioral dynamics via multifaceted visualization views. We extensively evaluate Anchorage through a case study and a carefully-designed user study. The results demonstrate its effectiveness and usability in assessing customer satisfaction using customer service videos. We found that introducing event contexts in assessing customer satisfaction can enhance its performance without compromising annotation precision. Our approach can be adapted in situations where unlabelled and unstructured videos are collected along with sequential records., Comment: 13 pages. A preprint version of a publication at IEEE Transactions on Visualization and Computer Graphics (TVCG), 2023

This paper provided empirical knowledge of the user experience for using collaborative visualization in a distributed asymmetrical setting through controlled user studies. With the ability to access various computing devices, such as Virtual Reality (VR) head-mounted displays, scenarios emerge when collaborators have to or prefer to use different computing environments in different places. However, we still lack an understanding of using VR in an asymmetric setting for collaborative visualization. To get an initial understanding and better inform the designs for asymmetric systems, we first conducted a formative study with 12 pairs of participants. All participants collaborated in asymmetric (PC-VR) and symmetric settings (PC-PC and VR-VR). We then improved our asymmetric design based on the key findings and observations from the first study. Another ten pairs of participants collaborated with enhanced PC-VR and PC-PC conditions in a follow-up study. We found that a well-designed asymmetric collaboration system could be as effective as a symmetric system. Surprisingly, participants using PC perceived less mental demand and effort in the asymmetric setting (PC-VR) compared to the symmetric setting (PC-PC). We provided fine-grained discussions about the trade-offs between different collaboration settings., Comment: 11 pages, 12 figures, accepted at IEEE VR 2023

Natural language interfaces (NLIs) enable users to flexibly specify analytical intentions in data visualization. However, diagnosing the visualization results without understanding the underlying generation process is challenging. Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries. We present XNLI, an explainable NLI system for visual data analysis. The system introduces a Provenance Generator to reveal the detailed process of visual transformations, a suite of interactive widgets to support error adjustments, and a Hint Generator to provide query revision hints based on the analysis of user queries and interactions. Two usage scenarios of XNLI and a user study verify the effectiveness and usability of the system. Results suggest that XNLI can significantly enhance task accuracy without interrupting the NLI-based analysis process., Comment: 14 pages, 7 figures. A preprint version of a publication at IEEE Transactions on Visualization and Computer Graphics (TVCG), 2023

Visual analytics (VA) systems have been widely used in various application domains. However, VA systems are complex in design, which imposes a serious problem: although the academic community constantly designs and implements new designs, the designs are difficult to query, understand, and refer to by subsequent designers. To mark a major step forward in tackling this problem, we index VA designs in an expressive and accessible way, transforming the designs into a structured format. We first conducted a workshop study with VA designers to learn user requirements for understanding and retrieving professional designs in VA systems. Thereafter, we came up with an index structure VAID to describe advanced and composited visualization designs with comprehensive labels about their analytical tasks and visual designs. The usefulness of VAID was validated through user studies. Our work opens new perspectives for enhancing the accessibility and reusability of professional visualization designs.

Dashboards, which comprise multiple views on a single display, help analyze and communicate multiple perspectives of data simultaneously. However, creating effective and elegant dashboards is challenging since it requires careful and logical arrangement and coordination of multiple visualizations. To solve the problem, we propose a data-driven approach for mining design rules from dashboards and automating dashboard organization. Specifically, we focus on two prominent aspects of the organization: arrangement, which describes the position, size, and layout of each view in the display space; and coordination, which indicates the interaction between pairwise views. We build a new dataset containing 854 dashboards crawled online, and develop feature engineering methods for describing the single views and view-wise relationships in terms of data, encoding, layout, and interactions. Further, we identify design rules among those features and develop a recommender for dashboard design. We demonstrate the usefulness of DMiner through an expert study and a user study. The expert study shows that our extracted design rules are reasonable and conform to the design practice of experts. Moreover, a comparative user study shows that our recommender could help automate dashboard organization and reach human-level performance. In summary, our work offers a promising starting point for design mining visualizations to build recommenders., Comment: in IEEE Transactions on Visualization and Computer Graphics

Data privacy is an essential issue in publishing data visualizations. However, it is challenging to represent multiple data patterns in privacy-preserving visualizations. The prior approaches target specific chart types or perform an anonymization model uniformly without considering the importance of data patterns in visualizations. In this paper, we propose a visual analytics approach that facilitates data custodians to generate multiple private charts while maintaining user-preferred patterns. To this end, we introduce pattern constraints to model users' preferences over data patterns in the dataset and incorporate them into the proposed Bayesian network-based Differential Privacy (DP) model PriVis. A prototype system, DPVisCreator, is developed to assist data custodians in implementing our approach. The effectiveness of our approach is demonstrated with quantitative evaluation of pattern utility under the different levels of privacy protection, case studies, and semi-structured expert interviews., Comment: 9 pages, 5 figures

This paper presents a design space of interaction techniques to engage with visualizations that are printed on paper and augmented through Augmented Reality. Paper sheets are widely used to deploy visualizations and provide a rich set of tangible affordances for interactions, such as touch, folding, tilting, or stacking. At the same time, augmented reality can dynamically update visualization content to provide commands such as pan, zoom, filter, or detail on demand. This paper is the first to provide a structured approach to mapping possible actions with the paper to interaction commands. This design space and the findings of a controlled user study have implications for future designs of augmented reality systems involving paper sheets and visualizations. Through workshops (N=20) and ideation, we identified 81 interactions that we classify in three dimensions: 1) commands that can be supported by an interaction, 2) the specific parameters provided by an (inter)action with paper, and 3) the number of paper sheets involved in an interaction. We tested user preference and viability of 11 of these interactions with a prototype implementation in a controlled study (N=12, HoloLens 2) and found that most of the interactions are intuitive and engaging to use. We summarized interactions (e.g., tilt to pan) that have strong affordance to complement "point" for data exploration, physical limitations and properties of paper as a medium, cases requiring redundancy and shortcuts, and other implications for design., Comment: 11 pages, 9 figures, 1 table, accepted at IEEE VIS 2022

In history research, cohort analysis seeks to identify social structures and figure mobilities by studying the group-based behavior of historical figures. Prior works mainly employ automatic data mining approaches, lacking effective visual explanation. In this paper, we present CohortVA, an interactive visual analytic approach that enables historians to incorporate expertise and insight into the iterative exploration process. The kernel of CohortVA is a novel identification model that generates candidate cohorts and constructs cohort features by means of pre-built knowledge graphs constructed from large-scale history databases. We propose a set of coordinated views to illustrate identified cohorts and features coupled with historical events and figure profiles. Two case studies and interviews with historians demonstrate that CohortVA can greatly enhance the capabilities of cohort identifications, figure authentications, and hypothesis generation.

Benchmark datasets play an important role in evaluating Natural Language Understanding (NLU) models. However, shortcuts -- unwanted biases in the benchmark datasets -- can damage the effectiveness of benchmark datasets in revealing models' real capabilities. Since shortcuts vary in coverage, productivity, and semantic meaning, it is challenging for NLU experts to systematically understand and avoid them when creating benchmark datasets. In this paper, we develop a visual analytics system, ShortcutLens, to help NLU experts explore shortcuts in NLU benchmark datasets. The system allows users to conduct multi-level exploration of shortcuts. Specifically, Statistics View helps users grasp the statistics such as coverage and productivity of shortcuts in the benchmark dataset. Template View employs hierarchical and interpretable templates to summarize different types of shortcuts. Instance View allows users to check the corresponding instances covered by the shortcuts. We conduct case studies and expert interviews to evaluate the effectiveness and usability of the system. The results demonstrate that ShortcutLens supports users in gaining a better understanding of benchmark dataset issues through shortcuts, inspiring them to create challenging and pertinent benchmark datasets., Comment: 15 pages, 6 figures

Analytical dashboards are popular in business intelligence to facilitate insight discovery with multiple charts. However, creating an effective dashboard is highly demanding, which requires users to have adequate data analysis background and be familiar with professional tools, such as Power BI. To create a dashboard, users have to configure charts by selecting data columns and exploring different chart combinations to optimize the communication of insights, which is trial-and-error. Recent research has started to use deep learning methods for dashboard generation to lower the burden of visualization creation. However, such efforts are greatly hindered by the lack of large-scale and high-quality datasets of dashboards. In this work, we propose using deep reinforcement learning to generate analytical dashboards that can use well-established visualization knowledge and the estimation capacity of reinforcement learning. Specifically, we use visualization knowledge to construct a training environment and rewards for agents to explore and imitate human exploration behavior with a well-designed agent network. The usefulness of the deep reinforcement learning model is demonstrated through ablation studies and user studies. In conclusion, our work opens up new opportunities to develop effective ML-based visualization recommenders without beforehand training datasets.

Data visualization is powerful in persuading an audience. However, when it is done poorly or maliciously, a visualization may become misleading or even deceiving. Visualizations give further strength to the dissemination of misinformation on the Internet. The visualization research community has long been aware of visualizations that misinform the audience, mostly associated with the terms "lie" and "deceptive." Still, these discussions have focused only on a handful of cases. To better understand the landscape of misleading visualizations, we open-coded over one thousand real-world visualizations that have been reported as misleading. From these examples, we discovered 74 types of issues and formed a taxonomy of misleading elements in visualizations. We found four directions that the research community can follow to widen the discussion on misleading visualizations: (1) informal fallacies in visualizations, (2) exploiting conventions and data literacy, (3) deceptive tricks in uncommon charts, and (4) understanding the designers' dilemma. This work lays the groundwork for these research directions, especially in understanding, detecting, and preventing them., Comment: To be presented at EuroVis 2022. Appendix available at https://github.com/leoyuholo/bad-vis-browser/blob/master/misinformed_by_visualization_appendix.pdf

Appropriate gestures can enhance message delivery and audience engagement in both daily communication and public presentations. In this paper, we contribute a visual analytic approach that assists professional public speaking coaches in improving their practice of gesture training through analyzing presentation videos. Manually checking and exploring gesture usage in the presentation videos is often tedious and time-consuming. There lacks an efficient method to help users conduct gesture exploration, which is challenging due to the intrinsically temporal evolution of gestures and their complex correlation to speech content. In this paper, we propose GestureLens, a visual analytics system to facilitate gesture-based and content-based exploration of gesture usage in presentation videos. Specifically, the exploration view enables users to obtain a quick overview of the spatial and temporal distributions of gestures. The dynamic hand movements are firstly aggregated through a heatmap in the gesture space for uncovering spatial patterns, and then decomposed into two mutually perpendicular timelines for revealing temporal patterns. The relation view allows users to explicitly explore the correlation between speech content and gestures by enabling linked analysis and intuitive glyph designs. The video view and dynamic view show the context and overall dynamic movement of the selected gestures, respectively. Two usage scenarios and expert interviews with professional presentation coaches demonstrate the effectiveness and usefulness of GestureLens in facilitating gesture exploration and analysis of presentation videos., Comment: 14 pages, 6 figures. A preprint version of a publication at IEEE Transactions on Visualization and Computer Graphics (TVCG), 2022

Persuading people to change their opinions is a common practice in online discussion forums on topics ranging from political campaigns to relationship consultation. Enhancing people's ability to write persuasive arguments could not only practice their critical thinking and reasoning but also contribute to the effectiveness and civility in online communication. It is, however, not an easy task in online discussion settings where written words are the primary communication channel. In this paper, we derived four design goals for a tool that helps users improve the persuasiveness of arguments in online discussions through a survey with 123 online forum users and interviews with five debating experts. To satisfy these design goals, we analyzed and built a labeled dataset of fine-grained persuasive strategies (i.e., logos, pathos, ethos, and evidence) in 164 arguments with high ratings on persuasiveness from ChangeMyView, a popular online discussion forum. We then designed an interactive visual system, Persua, which provides example-based guidance on persuasive strategies to enhance the persuasiveness of arguments. In particular, the system constructs portfolios of arguments based on different persuasive strategies applied to a given discussion topic. It then presents concrete examples based on the difference between the portfolios of user input and high-quality arguments in the dataset. A between-subjects study shows suggestive evidence that Persua encourages users to submit more times for feedback and helps users improve more on the persuasiveness of their arguments than a baseline system. Finally, a set of design considerations was summarized to guide future intelligent systems that improve the persuasiveness in text., Comment: This paper will appear in CSCW 2022

Data visualizations are created and shared on the web at an unprecedented speed, raising new needs and questions for processing and analyzing visualizations after they have been generated and digitized. However, existing formalisms focus on operating on a single visualization instead of multiple visualizations, making it challenging to perform analysis tasks such as sorting and clustering visualizations. Through a systematic analysis of previous work, we abstract visualization-related tasks into mathematical operators such as union and propose a design space of visualization operations. We realize the design by developing ComputableViz, a library that supports operations on multiple visualization specifications. To demonstrate its usefulness and extensibility, we present multiple usage scenarios concerning processing and analyzing visualization, such as generating visualization embeddings and automatically making visualizations accessible. We conclude by discussing research opportunities and challenges for managing and exploiting the massive visualizations on the web., Comment: 15 pages, 12 figures. In the ACM Conference on Human Factors in Computing Systems (CHI) 2022

With the wide usage of data visualizations, a huge number of Scalable Vector Graphic (SVG)-based visualizations have been created and shared online. Accordingly, there has been an increasing interest in exploring how to retrieve perceptually similar visualizations from a large corpus, since it can benefit various downstream applications such as visualization recommendation. Existing methods mainly focus on the visual appearance of visualizations by regarding them as bitmap images. However, the structural information intrinsically existing in SVG-based visualizations is ignored. Such structural information can delineate the spatial and hierarchical relationship among visual elements, and characterize visualizations thoroughly from a new perspective. This paper presents a structure-aware method to advance the performance of visualization retrieval by collectively considering both the visual and structural information. We extensively evaluated our approach through quantitative comparisons, a user study and case studies. The results demonstrate the effectiveness of our approach and its advantages over existing methods., Comment: Accepted to the 2022 CHI Conference on Human Factors in Computing Systems (CHI 22)

Data videos are an increasingly popular storytelling form. The opening of a data video critically influences its success as the opening either attracts the audience to continue watching or bores them to abandon watching. However, little is known about how to create an attractive opening. We draw inspiration from the openings of famous films to facilitate designing data video openings. First, by analyzing over 200 films from several sources, we derived six primary cinematic opening styles adaptable to data videos. Then, we consulted eight experts from the film industry to formulate 28 guidelines. To validate the usability and effectiveness of the guidelines, we asked participants to create data video openings with and without the guidelines, which were then evaluated by experts and the general public. Results showed that the openings designed with the guidelines were perceived to be more attractive, and the guidelines were praised for clarity and inspiration., Comment: In Proceedings of CHI Conference on Human Factors in Computing Systems (CHI '22), April 29-May 5, 2022, New Orleans, LA, USA