Abstract Existing visualization recommendation systems commonly rely on a single snapshot of a dataset to suggest visualizations to users. However, exploratory data analysis involves a series of related interactions with a dataset over time rather than one‐off analytical steps. We present Solas, a tool that tracks the history of a user's data analysis, models their interest in each column, and uses this information to provide visualization recommendations, all within the user's native analytical environment. Recommending with analysis history improves visualizations in three primary ways: task‐specific visualizations use the provenance of data to provide sensible encodings for common analysis functions, aggregated history is used to rank visualizations by our model of a user's interest in each column, and column data types are inferred based on applied operations. We present a usage scenario and a user evaluation demonstrating how leveraging analysis history improves in situ visualization recommendations on real‐world analysis tasks.

Visualization recommendation (VisRec) systems provide users with suggestions for potentially interesting and useful next steps during exploratory data analysis. These recommendations are typically organized into categories based on their analytical actions, i.e., operations employed to transition from the current exploration state to a recommended visualization. However, despite the emergence of a plethora of VisRec systems in recent work, the utility of the categories employed by these systems in analytical workflows has not been systematically investigated. Our article explores the efficacy of recommendation categories by formalizing a taxonomy of common categories and developing a system, Frontier, that implements these categories. Using Frontier, we evaluate workflow strategies adopted by users and how categories influence those strategies. Participants found recommendations that add attributes to enhance the current visualization and recommendations that filter to sub-populations to be comparatively most useful during data exploration. Our findings pave the way for next-generation VisRec systems that are adaptive and personalized via carefully chosen, effective recommendation categories.

Efforts to make machine learning more widely accessible have led to a rapid increase in Auto-ML tools that aim to automate the process of training and deploying machine learning. To understand how Auto-ML tools are used in practice today, we performed a qualitative study with participants ranging from novice hobbyists to industry researchers who use Auto-ML tools. We present insights into the benefits and deficiencies of existing tools, as well as the respective roles of the human and automation in ML workflows. Finally, we discuss design implications for the future of Auto-ML tool development. We argue that instead of full automation being the ultimate goal of Auto-ML, designers of these tools should focus on supporting a partnership between the user and the Auto-ML tool. This means that a range of Auto-ML tools will need to be developed to support varying user goals such as simplicity, reproducibility, and reliability.

Natural-language interfaces are gaining popularity due to their potential to democratize access to data and insights by making the interaction with data more natural and accessible for a wide range of business users. To fully embrace the goal of democratization, it is also necessary to provide effective and continuous guidance support for data exploration. Conversational interfaces enable exploration of the data and insights search space in small incremental steps as the conversation with the data progresses. In this demo, we describe Boomerang, a system that recommends data-driven insights to guide exploration of datasets through a conversational interface. Boomerang aggregates recommendations from a variety of statistical, collaborative, and content-based recommenders, and selects insights that match closely to the user's current state of data exploration, represented as the \em conversational context. Boomerang combines various metrics, such as \em relevance, \em interestingness and \em timeliness, to rank the insights and recommends the insights based on current conversational context. In the demo, we will show how Boomerang enables guided data exploration on a sales dataset, containing information about products, retailers, sales, orders, inventory levels and regions.

Exploratory data science largely happens in computational notebooks with dataframe APIs, such as pandas, that support flexible means to transform, clean, and analyze data. Yet, visually exploring data in dataframes remains tedious, requiring substantial programming effort for visualization and mental effort to determine what analysis to perform next. We propose Lux, an always-on framework for accelerating visual insight discovery in dataframe workflows. When users print a dataframe in their notebooks, Lux recommends visualizations to provide a quick overview of the patterns and trends and suggests promising analysis directions. Lux features a high-level language for generating visualizations on demand to encourage rapid visual experimentation with data. We demonstrate that through the use of a careful design and three system optimizations, Lux adds no more than two seconds of overhead on top of pandas for over 98% of datasets in the UCI repository. We evaluate Lux in terms of usability via interviews with early adopters, finding that Lux helps fulfill the needs of data scientists for visualization support within their dataframe workflows. Lux has already been embraced by data science practitioners, with over 3.1k stars on Github.

Computational notebooks have emerged as the platform of choice for data science and analytical workflows, enabling rapid iteration and exploration. By keeping intermediate program state in memory and segmenting units of execution into so-called "cells", notebooks allow users to enjoy particularly tight feedback. However, as cells are added, removed, reordered, and rerun, this hidden intermediate state accumulates, making execution behavior difficult to reason about, and leading to errors and lack of reproducibility. We present nbsafety, a custom Jupyter kernel that uses runtime tracing and static analysis to automatically manage lineage associated with cell execution and global notebook state. nbsafety detects and prevents errors that users make during unaided notebook interactions, all while preserving the flexibility of existing notebook semantics. We evaluate nbsafety's ability to prevent erroneous interactions by replaying and analyzing 666 real notebook sessions. Of these, nbsafety identified 117 sessions with potential safety errors, and in the remaining 549 sessions, the cells that nbsafety identified as resolving safety issues were more than 7X more likely to be selected by users for re-execution compared to a random baseline, even though the users were not using nbsafety and were therefore not influenced by its suggestions.

Visual query systems (VQSs) empower users to interactively search for line charts with desired visual patterns, typically specified using intuitive sketch-based interfaces. Despite decades of past work on VQSs, these efforts have not translated to adoption in practice, possibly because VQSs are largely evaluated in unrealistic lab-based settings. To remedy this gap in adoption, we collaborated with experts from three diverse domains-astronomy, genetics, and material science-via a year-long user-centered design process to develop a VQS that supports their workflow and analytical needs, and evaluate how VQSs can be used in practice. Our study results reveal that ad-hoc sketch-only querying is not as commonly used as prior work suggests, since analysts are often unable to precisely express their patterns of interest. In addition, we characterize three essential sensemaking processes supported by our enhanced VQS. We discover that participants employ all three processes, but in different proportions, depending on the analytical needs in each domain. Our findings suggest that all three sensemaking processes must be integrated in order to make future VQSs useful for a wide range of analytical inquiries.

As datasets continue to grow in size and complexity, exploring multi-dimensional datasets remain challenging for analysts. A common operation during this exploration is drill-down-understanding the behavior of data subsets by progressively adding filters. While widely used, in the absence of careful attention towards confounding factors, drill-downs could lead to inductive fallacies. Specifically, an analyst may end up being "deceived" into thinking that a deviation in trend is attributable to a local change, when in fact it is a more general phenomenon; we term this the drill-down fallacy. One way to avoid falling prey to drill-down fallacies is to exhaustively explore all potential drill-down paths, which quickly becomes infeasible on complex datasets with many attributes. We present VisPilot, an accelerated visual data exploration tool that guides analysts through the key insights in a dataset, while avoiding drill-down fallacies. Our user study results show that VisPilot helps analysts discover interesting visualizations, understand attribute importance, and predict unseen visualizations better than other multidimensional data analysis baselines.

Skintillates is a wearable technology that mimics tattoos - the oldest and most commonly used on-skin displays in human culture. We demonstrate that by fabricating electrical traces and thin electronics on temporary tattoo paper, a wide array of displays and sensors can be created. Just like the traditional temporary tattoos often worn by children and adults alike, Skintillates flex naturally with the user's skin. Our simple fabrication technique also enables users to freely design and print with a full range of colors to create application-specific customized designs. We demonstrate the technical capabilities of Skintillates as sensors and as expressive personal and private displays through a series of application examples. Finally, we detail the results of a set of user studies that highlight the user experience, comfort, durability, acceptability, and application potential for Skintillates.

This paper explores the role dynamic textile displays play in relation to personal style: What does it mean to wear computationally responsive clothing and why would one be motivated to do so? We developed a novel textile display technology, called Ebb, and created several woven and crochet fabric swatches that explored clothing-specific design possibilities. We engaged fashion designers and non-designers in imagining how Ebb would integrate into their design practice or personal style of dressing. Participants evaluated the appeal and utility of clothing-based displays according to a very different set of criteria than traditional screen-based computational displays. Specifically, the slowness, low-resolution, and volatility of Ebb tended to be seen as assets as opposed to technical limitations in the context of personal style. Additionally, participants envisioned various ways that ambiguous, ambient, and abstract displays of information could prompt new experiences in their everyday lives. Our paper details the complex relationships between display and personal style and offers a new design metaphor and extension of Gaver et al.'s original descriptions of ambiguity in order to guide the design of clothing-based displays for everyday life.

In this paper, we introduce Crowdclass, a novel framework that integrates the learning of advanced scientific concepts with the crowdsourcing microtask of image classification. In Crowdclass, we design questions to serve as both a learning experience and a scientific classification. This is different from conventional citizen science platforms which decompose high level questions into a series of simple microtasks that require no scientific background knowledge to complete. We facilitate learning within the microtask by providing content that is appropriate for the participant’s level of knowledge through scaffolding learning. We conduct a between-group study of 93 participants on Amazon Mechanical Turk comparing Crowdclass to the popular citizen science project Galaxy Zoo. We find that the scaffolding presentation of content enables learning of more challenging concepts. By understanding the relationship between user motivation, learning, and performance, we draw general design principles for learning-as-an-incentive interventions applicable to other crowdsourcing applications.