Visualization recommendation systems make understanding data more accessible to users of all skill levels by automatically generating visualizations for users to explore. However, most existing visualization recommendation systems focus on ranking all possible visualizations based on the attributes or encodings, which makes it difficult to find the most interesting or relevant insights. We therefore introduce a novel class of visualization recommendation systems that automatically rank and recommend both groups of related insights and the most important insights within each group. Our approach combines results across different learning-based methods to discover insights automatically and generalizes to a variety of attribute types (e.g., categorical, numerical, and temporal), including non-trivial combinations of these attribute types. We then implemented a new insight-centric visualization recommendation system, SpotLight, which ranks annotated visualizations in visual insight groups. Finally, we conducted a user study which showed that users are able to quickly understand and find relevant insights in unfamiliar data.

Although we have seen a proliferation of algorithms for recommending visualizations, these algorithms are rarely compared with one another, making it difficult to ascertain which algorithm is best for a given visual analysis scenario. Though several formal frameworks have been proposed in response, we believe this issue persists because visualization recommendation algorithms are inadequately specified from an evaluation perspective. In this paper, we propose an evaluation-focused framework to contextualize and compare a broad range of visualization recommendation algorithms. We present the structure of our framework, where algorithms are specified using three components: (1) a graph representing the full space of possible visualization designs, (2) the method used to traverse the graph for potential candidates for recommendation, and (3) an oracle used to rank candidate designs. To demonstrate how our framework guides the formal comparison of algorithmic performance, we not only theoretically compare five existing representative recommendation algorithms, but also empirically compare four new algorithms generated based on our findings from the theoretical comparison. Our results show that these algorithms behave similarly in terms of user performance, highlighting the need for more rigorous formal comparisons of recommendation algorithms to further clarify their benefits in various analysis scenarios.

Visualization recommendation work has focused solely on scoring visualizations based on the underlying dataset, and not the actualuserand their past visualization feedback. These systems recommend the same visualizations for every user, despite that the underlying user interests, intent, and visualization preferences are likely to be fundamentally different, yet vitally important. In this work, we formally introduce the problem ofpersonalized visualization recommendationand present a generic learning framework for solving it. In particular, we focus on recommending visualizations personalized for each individual user based on their past visualization interactions (e.g., viewed, clicked, manually created) along with the data from those visualizations. More importantly, the framework can learn from visualizations relevant to other users, even if the visualizations are generated from completely different datasets. Experiments demonstrate the effectiveness of the approach as it leads to higher quality visualization recommendations tailored to the specific user intent and preferences. To support research on this new problem, we release our user-centric visualization corpus consisting of 17.4k users exploring 94k datasets with 2.3 million attributes and 32k user-generated visualizations.

Visualization recommendation is important for exploratory analysis and making sense of the data quickly by automatically recommending relevant visualizations to the user. In this work, we propose the first end-to-end ML-based visualization recommendation system that leverages a large corpus of datasets and their relevant visualizations to learn a visualization recommendation model automatically. Then, given a new unseen dataset from an arbitrary user, the model automatically generates visualizations for that new dataset, derives scores for the visualizations, and outputs a list of recommended visualizations to the user ordered by effectiveness. We also describe an evaluation framework to quantitatively evaluate visualization recommendation models learned from a large corpus of visualizations and datasets. Through quantitative experiments, a user study, and qualitative analysis, we show that our end-to-end ML-based system recommends more effective and useful visualizations compared to existing state-of-the-art rule-based systems.

Scientific-style figures are commonly used on the web to present numerical information. Captions that tell accurate figure information and sound natural would significantly improve figure accessibility. In this paper, we present promising results on machine figure captioning. A recent corpus analysis of real-world captions reveals that machine figure captioning systems should start by generating accurate caption units. We formulate the caption unit generation problem as a controlled captioning problem. Given a caption unit type as a control signal, a model generates an accurate caption unit of that type. As a proof-of-concept on single bar charts, we propose a model, FigJAM, that achieves this goal through utilizing metadata information and a joint static and dynamic dictionary. Quantitative evaluations with two datasets from the figure question answering task show that our model can generate more accurate caption units than competitive baseline models. A user study with ten human experts confirms the value of machine-generated caption units in their standalone accuracy and naturalness. Finally, a post-editing simulation study demonstrates the potential for models to paraphrase and stitch together single-type caption units into multi-type captions by learning from data.

While decision makers have begun to employ machine learning, machine learning models may make predictions that bias against certain demographic groups. Semi-automated bias detection tools often present reports of automatically-detected biases using a recommendation list or visual cues. However, there is a lack of guidance concerning which presentation style to use in what scenarios. We conducted a small lab study with 16 participants to investigate how presentation style might affect user behaviors in reviewing bias reports. Participants used both a prototype with a recommendation list and a prototype with visual cues for bias detection. We found that participants often wanted to investigate the performance measures that were not automatically detected as biases. Yet, when using the prototype with a recommendation list, they tended to give less consideration to such measures. Grounded in the findings, we propose information load and comprehensiveness as two axes for characterizing bias detection tasks and illustrate how the two axes could be adopted to reason about when to use a recommendation list or visual cues.

Data analysts apply machine learning and statistical methods to timestamped event sequences to tackle various problems but face unique challenges when interpreting the results. Especially in event sequence prediction, it is difficult to convey uncertainty and possible alternative paths or outcomes. In this work, informed by interviews with five machine learning practitioners, we iteratively designed a novel visualization for exploring event sequence predictions of multiple records where users are able to review the most probable predictions and possible alternatives alongside uncertainty information. Through a controlled study with 18 participants, we found that users are more confident in making decisions when alternative predictions are displayed and they consider the alternatives more when deciding between two options with similar top predictions.

Exploring event sequences by defining queries alone or by using mining algorithms alone is often not sufficient to support analysis. Analysts often interweave querying and mining in a recursive manner during event sequence analysis: sequences extracted as query results are used for mining patterns, patterns generated are incorporated into a new query for segmenting the sequences, and the resulting segments are mined or queried again. To support flexible analysis, we propose a framework that describes the process of interwoven querying and mining. Based on this framework, we developed MAQUI, a Mining And Querying User Interface that enables recursive event sequence exploration. To understand the efficacy of MAQUI, we conducted two case studies with domain experts. The findings suggest that the capability of interweaving querying and mining helps the participants articulate their questions and gain novel insights from their data.

The growing volume and variety of data presents both opportunities and challenges for visual analytics. Addressing these challenges is needed for big data to provide valuable insights and novel solutions for business, security, social media, and healthcare. In the case of temporal event sequence analytics it is the number of events in the data and variety of temporal sequence patterns that challenges users of visual analytic tools. This paper describes 15 strategies for sharpening analytic focus that analysts can use to reduce the data volume and pattern variety. Four groups of strategies are proposed: (1) extraction strategies, (2) temporal folding, (3) pattern simplification strategies, and (4) iterative strategies. For each strategy, we provide examples of the use and impact of this strategy on volume and/or variety. Examples are selected from 20 case studies gathered from either our own work, the literature, or based on email interviews with individuals who conducted the analyses and developers who observed analysts using the tools. Finally, we discuss how these strategies might be combined and report on the feedback from 10 senior event sequence analysts.

Cohort comparison studies have traditionally been hypothesis driven and conducted in carefully controlled environments (such as clinical trials). Given two groups of event sequence data, researchers test a single hypothesis (e.g., does the group taking Medication A exhibit more deaths than the group taking Medication B?). Recently, however, researchers have been moving toward more exploratory methods of retrospective analysis with existing data. In this article, we begin by showing that the task of cohort comparison is specific enough to support automatic computation against a bounded set of potential questions and objectives, a method that we refer to as High-Volume Hypothesis Testing (HVHT). From this starting point, we demonstrate that the diversity of these objectives, both across and within different domains, as well as the inherent complexities of real-world datasets, still requires human involvement to determine meaningful insights. We explore how visualization and interaction better support the task of exploratory data analysis and the understanding of HVHT results (how significant they are, why they are meaningful, and whether the entire dataset has been exhaustively explored). Through interviews and case studies with domain experts, we iteratively design and implement visualization and interaction techniques in a visual analytics tool, CoCo. As a result of our evaluation, we propose six design guidelines for enabling users to explore large result sets of HVHT systematically and flexibly in order to glean meaningful insights more quickly. Finally, we illustrate the utility of this method with three case studies in the medical domain.

Finding the differences and similarities between two datasets is a common analytics task. With temporal event sequence data, this task is complex because of the many ways single events and event sequences can differ between the two datasets (or cohorts) of records: the structure of the event sequences (e.g., event order, co-occurring events, or event frequencies), the attributes of events and records (e.g., patient gender), or metrics about the timestamps themselves (e.g., event duration). In exploratory analyses, running statistical tests to cover all cases is time-consuming and determining which results are significant becomes cumbersome. Current analytics tools for comparing groups of event sequences emphasize a purely statistical or purely visual approach for comparison. This paper presents a taxonomy of metrics for comparing cohorts of temporal event sequences, showing that the problem-space is bounded. We also present a visual analytics tool, CoCo (for "Cohort Comparison"), which implements balanced integration of automated statistics with an intelligent user interface to guide users to significant, distinguishing features between the cohorts. Lastly, we describe two early case studies: the first with a research team studying medical team performance in the emergency department and the second with pharmacy researchers.

Social media, particularly Twitter, provides an abundance of real-time data. To account for this volume, researchers often use automated analysis and visualization techniques to produce a high-level overview of a Twitter stream. Existing techniques for understanding Twitter data make use of hashtags or word-pairs and may ignore the complex trends in discussions over time. To remedy this, we present an application of statistical topic modeling and alignment (binned topic models) to group related tweets into automatically generated topics and TopicFlow, an interactive tool to visualize the evolution of these topics. The effectiveness of this visualization for reasoning about large data sets is demonstrated by a usability study with 18 participants.

To aid program comprehension, programmers choose identifiers for methods, classes, fields and other program elements primarily by following naming conventions in software. These software “naming conventions” follow systematic patterns which can convey deep natural language clues that can be leveraged by software engineering tools. For example, they can be used to increase the accuracy of software search tools, improve the ability of program navigation tools to recommend related methods, and raise the accuracy of other program analyses. After splitting multi-word names into their component words, the next step to extracting accurate natural language information is tagging each word with its part of speech (POS) and then chunking the name into natural language phrases. State-of-theart approaches, most of which rely on “traditional POS taggers” trained on natural language documents, do not capture the syntactic structure of program elements. In this paper, we present a POS tagger and syntactic chunker for source code names that takes into account programmers' naming conventions to understand the regular, systematic ways a program element is named. We studied the naming conventions used in Object Oriented Programming and identified different grammatical constructions that characterize a large number of program identifiers. This study then informed the design of our POS tagger and chunker. Our evaluation results show a significant improvement in accuracy(11%-20%) of POS tagging of identifiers, over the current approaches. With this improved accuracy, both automated software engineering tools and developers will be able to better capture and understand the information available in code.