Visual Analytics Community Research Articles

Human–Computer Collaboration for Visual Analytics: an Agent‐based Framework

AbstractThe visual analytics community has long aimed to understand users better and assist them in their analytic endeavors. As a result, numerous conceptual models of visual analytics aim to formalize common workflows, techniques, and goals leveraged by analysts. While many of the existing approaches are rich in detail, they each are specific to a particular aspect of the visual analytic process. Furthermore, with an ever‐expanding array of novel artificial intelligence techniques and advances in visual analytic settings, existing conceptual models may not provide enough expressivity to bridge the two fields. In this work, we propose an agent‐based conceptual model for the visual analytic process by drawing parallels from the artificial intelligence literature. We present three examples from the visual analytics literature as case studies and examine them in detail using our framework. Our simple yet robust framework unifies the visual analytic pipeline to enable researchers and practitioners to reason about scenarios that are becoming increasingly prominent in the field, namely mixed‐initiative, guided, and collaborative analysis. Furthermore, it will allow us to characterize analysts, visual analytic settings, and guidance from the lenses of human agents, environments, and artificial agents, respectively.

A Unified Comparison of User Modeling Techniques for Predicting Data Interaction and Detecting Exploration Bias.

The visual analytics community has proposed several user modeling algorithms to capture and analyze users' interaction behavior in order to assist users in data exploration and insight generation. For example, some can detect exploration biases while others can predict data points that the user will interact with before that interaction occurs. Researchers believe this collection of algorithms can help create more intelligent visual analytics tools. However, the community lacks a rigorous evaluation and comparison of these existing techniques. As a result, there is limited guidance on which method to use and when. Our paper seeks to fill in this missing gap by comparing and ranking eight user modeling algorithms based on their performance on a diverse set of four user study datasets. We analyze exploration bias detection, data interaction prediction, and algorithmic complexity, among other measures. Based on our findings, we highlight open challenges and new directions for analyzing user interactions and visualization provenance.

A Grammar‐Based Approach for Applying Visualization Taxonomies to Interaction Logs

AbstractResearchers collect large amounts of user interaction data with the goal of mapping user's workflows and behaviors to their high‐level motivations, intuitions, and goals. Although the visual analytics community has proposed numerous taxonomies to facilitate this mapping process, no formal methods exist for systematically applying these existing theories to user interaction logs. This paper seeks to bridge the gap between visualization task taxonomies and interaction log data by making the taxonomies more actionable for interaction log analysis. To achieve this, we leverage structural parallels between how people express themselves through interactions and language by reformulating existing theories as regular grammars. We represent interactions as terminals within a regular grammar, similar to the role of individual words in a language, and patterns of interactions or non‐terminals as regular expressions over these terminals to capture common language patterns. To demonstrate our approach, we generate regular grammars for seven existing visualization taxonomies and develop code to apply them to three public interaction log datasets. In analyzing these regular grammars, we find that the taxonomies at the low‐level (i.e., terminals) show mixed results in expressing multiple interaction log datasets, and taxonomies at the high‐level (i.e., regular expressions) have limited expressiveness, due to primarily two challenges: inconsistencies in interaction log dataset granularity and structure, and under‐expressiveness of certain terminals. Based on our findings, we suggest new research directions for the visualization community to augment existing taxonomies, develop new ones, and build better interaction log recording processes to facilitate the data‐driven development of user behavior taxonomies.

Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics.

Machine learning models are currently being deployed in a variety of real-world applications where model predictions are used to make decisions about healthcare, bank loans, and numerous other critical tasks. As the deployment of artificial intelligence technologies becomes ubiquitous, it is unsurprising that adversaries have begun developing methods to manipulate machine learning models to their advantage. While the visual analytics community has developed methods for opening the black box of machine learning models, little work has focused on helping the user understand their model vulnerabilities in the context of adversarial attacks. In this paper, we present a visual analytics framework for explaining and exploring model vulnerabilities to adversarial attacks. Our framework employs a multi-faceted visualization scheme designed to support the analysis of data poisoning attacks from the perspective of models, data instances, features, and local structures. We demonstrate our framework through two case studies on binary classifiers and illustrate model vulnerabilities with respect to varying attack strategies.

A human cognition framework for information visualization

We present a human cognition framework for information visualization. This framework emphasizes how top-down cognitive processing enables the induction of insight, reasoning, and understanding, which are key goals of the visual analytics community. Specifically, we present a set of six leverage points that can be exploited by visualization designers in order to measurably influence certain aspects of human cognition: (1) exogenous attention; (2) endogenous attention; (3) chunking; (4) reasoning with mental models; (5) analogical reasoning; and (6) implicit learning.

The beneficial role of the VAST Challenges in the evolution of GeoTime and nSpace2

Oculus participated in the first VAST Challenge in 2006 and in every subsequent year except one. Although we have won 5 awards in the last 7 years, they are not the main reason we spend much time and effort preparing our submission each year. The VAST Challenge has proven to be a valuable exercise in evaluating and refining our tools and our thinking. No organization that has the desire to create the best possible analytic tools should pass by the unique opportunity to work on a realistic set of tasks, against nontoy datasets containing ground truth, and to be evaluated by both senior analysts and experts within the visual analytics community. Oculus staff and products have benefited from the experience as have the whole visual analytics community researchers and practitioners.

Toward a deeper understanding of the relationship between interaction constraints and visual isomorphs

Interaction and manual manipulation have been shown in cognitive science literature to play a critical role in problem solving. Given different types of interactions or constraints on interactions, a problem can appear to have different degrees of difficulty. While this relationship between interaction and problem solving has been well studied in the cognitive science literatures, the visual analytics community has yet to exploit this understanding for analytical problem solving. In this paper, we hypothesize that constraints on interactions and constraints encoded in visual representations can lead to strategies of varying effectiveness during problem solving. To test our hypothesis, we conducted a user study in which participants were given different levels of interaction constraints when solving a simple mathematic game called number scrabble. Number scrabble is known to have an optimal visual problem isomorph, and the goal of this study is to learn if and how the participants could derive the isomorph and to analyze the strategies that the participants utilize in solving the problem. Our results indicate that constraints on interactions do affect problem solving, and that although the optimal visual isomorph is difficult to derive, certain interaction constraints can lead to a higher chance of deriving the isomorph.

Developing guidelines for assessing visual analytics environments

In this article, we develop guidelines for evaluating visual analytics environments based on a synthesis of reviews for the entries to the 2009 Visual Analytics Science and Technology (VAST) Symposium Challenge and from a user study with professional intelligence analysts. By analyzing the 2009 VAST Challenge reviews, we gained a better understanding of what is important to our reviewers, both visualization researchers and professional analysts. We also report on a small user study with professional analysts to determine the important factors that they use in evaluating visual analysis systems. We also looked at guidelines developed by researchers in various domains and synthesized the results from these three efforts into an initial set for use by others in the community. One challenge for future visual analytics systems is to help in the generation of reports. In our user study, we also worked with analysts to understand the criteria they used to evaluate the quality of analytic reports. We propose that this knowledge will be useful as researchers look at systems to automate some of the report generation.1 From these two efforts, we produced some initial guidelines for evaluating visual analytics environments and for the evaluation of analytic reports. It is important to understand that these guidelines are initial drafts and are limited in scope as the visual analytics systems we evaluated were used in specific tasks. We propose these guidelines as a starting point for the Visual Analytics Community.

Visual Analytics: Building a Vibrant and Resilient National Science

Five years after the science of visual analytics was formally established, we attempt to use two different studies to assess the current state of the community and evaluate the progress the community has made in the past few years. The first study involves a comparison analysis of intellectual and scholastic accomplishments recently made by the visual analytics community with two other visualization communities. The second study aims to measure the degree of community reach and internet penetration of visual-analytics-related resources. This article describes our efforts to harvest the study data, conduct analysis and make interpretations based on parallel comparisons with five other established computer science areas.