Recent AI advances have made it possible to retrieve specific moments from long-form videos using natural language queries. However, existing systems can struggle to align retrieval results with user intent due to the lack of means for users to express their intents in simple natural language text. Moreover, there is limited support for helping users express or refine their intents interactively. We present FuzzySeek, a video moment retrieval interface that supports the expression and specification of imprecise or broad exploratory queries through multimodal interaction. FuzzySeek proposes three key components (1) Multimodality-blended text querying to improve expressivity, enabling users to directly anchor multimodal content within their textual queries, (2) Proactive Multimodal Guidance, which identifies imprecise/broad terms and phrases and surfaces targeted clarifications across modalities to improve query specificity and, (3) Query rollback to enable iterative back and forth exploration to enable direct or exploratory searches. Through a technical evaluation, multiple illustrative use cases and a user study with 11 participants, we show that FuzzySeek improves clarification efficiency, reduces cognitive load, and better supports video moment retrieval for imprecise queries compared to a baseline system without such support.

Large language models (LLMs) have gained widespread popularity due to their ability to perform ad-hoc natural language processing (NLP) tasks with simple natural language prompts. Part of the appeal for LLMs is their approachability to the general public, including individuals with little technical expertise in NLP. However, prompts can vary significantly in terms of their linguistic structure, context, and other semantics, and modifying one or more of these aspects can result in significant differences in task performance. Non-expert users may find it challenging to identify the changes needed to improve a prompt, especially when they lack domain-specific knowledge and appropriate feedback. To address this challenge, we present PromptAid, a visual analytics system designed to interactively create, refine, and test prompts through exploration, perturbation, testing, and iteration. PromptAid uses coordinated visualizations which allow users to improve prompts via three strategies: keyword perturbations, paraphrasing perturbations, and obtaining the best set of in-context few-shot examples. PromptAid was designed through a pre-study involving NLP experts, and evaluated via a robust mixed-methods user study. Our findings indicate that PromptAid helps users to iterate over prompts with less cognitive overhead, generate diverse prompts with the help of recommendations, and analyze the performance of the generated prompts while surpassing existing state-of-the-art prompting interfaces in performance.

Traditional deep learning interpretability methods which are suitable for model users cannot explain network behaviors at the global level and are inflexible at providing fine-grained explanations. As a solution, concept-based explanations are gaining attention due to their human intuitiveness and their flexibility to describe both global and local model behaviors. Concepts are groups of similarly meaningful pixels that express a notion, embedded within the network's latent space and have commonly been hand-generated, but have recently been discovered by automated approaches. Unfortunately, the magnitude and diversity of discovered concepts makes it difficult to navigate and make sense of the concept space. Visual analytics can serve a valuable role in bridging these gaps by enabling structured navigation and exploration of the concept space to provide concept-based insights of model behavior to users. To this end, we design, develop, and validate ConceptExplainer, a visual analytics system that enables people to interactively probe and explore the concept space to explain model behavior at the instance/class/global level. The system was developed via iterative prototyping to address a number of design challenges that model users face in interpreting the behavior of deep learning models. Via a rigorous user study, we validate how ConceptExplainer supports these challenges. Likewise, we conduct a series of usage scenarios to demonstrate how the system supports the interactive analysis of model behavior across a variety of tasks and explanation granularities, such as identifying concepts that are important to classification, identifying bias in training data, and understanding how concepts can be shared across diverse and seemingly dissimilar classes.

Visual data storytelling is gaining importance as a means of presenting data-driven information or analysis results, especially to the general public. This has resulted in design principles being proposed for data-driven storytelling, and new authoring tools being created to aid such storytelling. However, data analysts typically lack sufficient background in design and storytelling to make effective use of these principles and authoring tools. To assist this process, we present ChartStory for crafting data stories from a collection of user-created charts, using a style akin to comic panels to imply the underlying sequence and logic of data-driven narratives. Our approach is to operationalize established design principles into an advanced pipeline that characterizes charts by their properties and similarities to each other, and recommends ways to partition, layout, and caption story pieces to serve a narrative. ChartStory also augments this pipeline with intuitive user interactions for visual refinement of generated data comics. We extensively and holistically evaluate ChartStory via a trio of studies. We first assess how the tool supports data comic creation in comparison to a manual baseline tool. Data comics from this study are subsequently compared and evaluated to ChartStory's automated recommendations by a team of narrative visualization practitioners. This is followed by a pair of interview studies with data scientists using their own datasets and charts who provide an additional assessment of the system. We find that ChartStory provides cogent recommendations for narrative generation, resulting in data comics that compare favorably to manually-created ones.

When a newsworthy event occurs, media articles that report on the event can vary widely-a concept known as coverage diversity. To help investigate coverage diversity in event reporting, we de-velop a visual analytics system called News Kaleidoscope. News Kaleidoscope combines several backend language processing techniques with a coordinated visualization interface. Notably, News Kaleidoscope is tailored for visualization non-experts, and adopts an analytic workflow based around subselection analysis, whereby second-level features of articles are extracted to provide a more detailed and nuanced analysis of coverage diversity. To robustly evaluate News Kaleidoscope, we conduct a trio of user studies. (1) A study with news experts assesses the insights promoted for our targeted journalism-savvy users. (2) A follow-up study with news novices assesses the overall system and the specific insights pro-moted for journalism-agnostic users. (3) Based on identified system limitations in these two studies, we refine News Kaleidoscope's design and conduct a third study to validate these improvements. Results indicate that, for both news novice and experts, News Kalei-doscope supports an effective, task-driven workflow for analyzing the diversity of news coverage about events, though journalism expertise has a significant influence on the user's insights and take-aways. Our insights developing and evaluating News Kaleidoscope can aid future tools that combine visualization with natural language processing to analyze coverage diversity in news event reporting.

Reinforcement learning (RL) is used in many domains, including autonomous driving, robotics, stock trading, and video games. Unfortunately, the black box nature of RL agents, combined with legal and ethical considerations, makes it increasingly important that humans (including those are who not experts in RL) understand the reasoning behind the actions taken by an RL agent, particularly in safety-critical domains. To help address this challenge, we introduce PolicyExplainer, a visual analytics interface which lets the user directly query an autonomous agent. PolicyExplainer visualizes the states, policy, and expected future rewards for an agent, and supports asking and answering questions such as: “Why take this action? Why not take this other action? When is this action taken?” PolicyExplainer is designed based upon a domain analysis with RL researchers, and is evaluated via qualitative and quantitative assessments on a trio of domains: taxi navigation, a stack bot domain, and drug recommendation for HIV patients. We find that PolicyExplainer's visual approach promotes trust and understanding of agent decisions better than a state-of-the-art text-based explanation approach. Interviews with domain practitioners provide further validation for PolicyExplainer as applied to safety-critical domains. Our results help demonstrate how visualization-based approaches can be leveraged to decode the behavior of autonomous RL agents, particularly for RL non-experts.

We conduct an eye tracking study to investigate perception text-embellished narrative visualizations under different task conditions. Study stimuli are data visualizations embellished with text-based elements: annotations, captions, labels, and descriptive text. We consider three common viewing tasks that occur when these types of graphics are viewed: (1) simple observation, (2) active search to answer a query, and (3) information memorization for later recall. The overarching goal is to understand, at a perceptual level, if and how task affects how these visualizations are interacted with. By analyzing collected gaze data and conducting advanced semantic scanpath analysis, we find, at a high level, diverse patterns of gaze behavior: simple observation and information memorization lead to similar optical viewing strategies, while active search significantly diverges, both in regards to which areas of the visualization are focused upon and how often embellishments are interacted with. We discuss study outcomes in the context of embellishing visualizations with text for various usage scenarios.