Engineering Papers⌕ Search

Engineering topics

Endert, Alexander

Publications and source records attributed to Endert, Alexander.

At least 19 records

VAINE: Visualization and AI for Natural Experiments

Natural experiments are observational studies where the assignment of treatment conditions to different populations occur by chance ``in the wild''. Researchers from fields such as economics, healthcare, and the social sciences leverage natural experiments to conduct hypothesis testing and causal effect estimation for treatment and outcome variables that would otherwise be costly, infeasible, or unethical. In this paper, we introduce VAINE (Visualization and AI for Natural Experiments), a visual analytics tool for identifying and understanding natural experiments from observational data. We then demonstrate how VAINE can be used to validate causal relationships, estimate average treatment effects, and identify statistical phenomena such as Simpson’s paradox through two use cases.

Guo, Grace↗

TexTonic: Interactive Visualization for Exploration and discovery of Very Large Text Collections

TexTonic is a visual analytic system for interactive exploration of very large unstructured text collections. TexTonic visualizes hierarchical clusters of representative terms, snippets, and documents in a single, multi-scale spatial layout. Exploration is supported by interacting with the visualization and directly manipulating the terms in the visualization using semantic interactions. These semantic interactions steer the underlying analytic model by translating user interactions within the visualization to contextual updates to the supporting data model. The combination of semantic interactions and information visualization at multiple levels of the data hierarchy helps users manage information overload so that they can more effectively explore very large text collections. In this paper we describe TexTonic’s data processing and analytic pipeline, user interface and interaction design principles, and the results of a user study conducted mid-development with experienced data analysts. We also discuss the implications TexTonic could have on visual exploration and discovery tasks

human centered computing, Visual analytics, Inform↗

Method and system for information retrieval and aggregation from inferred user reasoning

The visual analytic system enables information retrieval within large text collections. Typically, users have to directly and explicitly query information to retrieve it. With this system and process, the reasoning of the user is inferred from the user interaction they perform in a visual analytic tool, and the appropriate information to query, process, and visualize is systematically determined.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Four Perspectives on Human Bias in Visual Analytics

Mixed-initiative visual analytic systems steer analytical models and adapt views by making inferences from users' behavioral patterns with the system. Because such systems rely on incorporating implicit and explicit user feedback, they are particularly susceptible to the injection and propagation of human biases. To ultimately guard against the potentially negative effects of systems biased by human users, we must first qualify what we mean by the term bias. Thus, in this paper we describe four different perspectives on human bias that are particularly relevant to visual analytics. We discuss the interplay of human and computer system biases, particularly their roles in mixed-initiative systems. Given that the term bias is used to describe several different concepts, our goal is to encourage mindful consideration of which perspective on bias researchers take in their work to facilitate a common language in research and development efforts going forward.

visual analytics, mixed-initiative systems, cognit↗

The Impact of Streaming Data on Sensemaking with Mixed-Initative Visual Analytics

Visual data analysis helps people gain insights into data via interactive visualizations. People generate and test hypotheses and questions about data in context of the domain. This process can generally be referred to as sensemaking. Much of the work on studying sensemaking (and creating visual analytic techniques in support of it) has been focused on static datasets. However, how do the cognitive processes of sensemaking change when data are changing? Further, what implication for design does this create for mixed-initiative visual analytics systems? This paper presents the results of a user study analyzing the impact of streaming data on sensemaking. To perform this study, we developed a mixed-initiative visual analytic prototype, the Streaming Canvas, that affords the analysis of streaming text data. We compare the sensemaking process of people using this tool for a static and streaming dataset. We present the results of this study and discuss the implications on future visual analytic systems that combine machine learning and interactive visualization to help people make sense of streaming data.

visualization↗

Mixed Initiative Visual Analytics Using Task-Driven Recommendations

Visual data analysis is composed of a collection of cognitive actions and tasks to decompose, internalize, and recombine data to produce knowledge and insight. Visual analytic tools provide interactive visual interfaces to data to support tasks involved in discovery and sensemaking, including forming hypotheses, asking questions, and evaluating and organizing evidence. Myriad analytic models can be incorporated into visual analytic systems, at the cost of increasing complexity in the analytic discourse between user and system. Techniques exist to increase the usability of interacting with such analytic models, such as inferring data models from user interactions to steer the underlying models of the system via semantic interaction, shielding users from having to do so explicitly. Such approaches are often also referred to as mixed-initiative systems. Researchers studying the sensemaking process have called for development of tools that facilitate analytic sensemaking through a combination of human and automated activities. However, design guidelines do not exist for mixed-initiative visual analytic systems to support iterative sensemaking. In this paper, we present a candidate set of design guidelines and introduce the Active Data Environment (ADE) prototype, a spatial workspace supporting the analytic process via task recommendations invoked by inferences on user interactions within the workspace. ADE recommends data and relationships based on a task model, enabling users to co-reason with the system about their data in a single, spatial workspace. This paper provides an illustrative use case, a technical description of ADE, and a discussion of the strengths and limitations of the approach.

active data↗

7 Key Challenges for Visualization in Cyber Network Defense

In this paper we present seven challenges, informed by two user studies, to be considered when developing a visualization for cyber security purposes. Cyber security visualizations must go beyond isolated solutions and “pretty picture” visualizations in order to make impact to users. We provide an example prototype that addresses the challenges with a description of how they are met. Our aim is to assist in increasing utility and adoption rates for visualization capabilities in cyber security.

Cyber security, visualization, network defense↗

Toward Usable Interactive Analytics: Coupling Cognition and Computation

Interactive analytics provide users a myriad of computational means to aid in extracting meaningful information from large and complex datasets. Much prior work focuses either on advancing the capabilities of machine-centric approaches by the data mining and machine learning communities, or human-driven methods by the visualization and CHI communities. However, these methods do not yet support a true human-machine symbiotic relationship where users and machines work together collaboratively and adapt to each other to advance an interactive analytic process. In this paper we discuss some of the inherent issues, outlining what we believe are the steps toward usable interactive analytics that will ultimately increase the effectiveness for both humans and computers to produce insights.

semantic interaction↗

User-Centered Design Guidelines for Collaborative Software for Intelligence Analysis

In this position paper we discuss the necessity of using User-Centered Design (UCD) methods in order to design collaborative software for the intelligence community. We present some standing issues in collaborative software based on existing work within the intelligence community. Based on this information we present opportunities to address some of these challenges.

collaboration↗

Modeling in Big Data Environments

Human-Centered Big Data Research (HCBDR) is an area of work that focuses on the methodologies and research areas focused on understanding how humans interact with “big data”. In the context of this paper, we refer to “big data” in a holistic sense, including most (if not all) the dimensions defining the term, such as complexity, variety, velocity, veracity, etc. Simply put, big data requires us as researchers of to question and reconsider existing approaches, with the opportunity to illuminate new kinds of insights that were traditionally out of reach to humans. The purpose of this article is to summarize the discussions and ideas about the role of models in HCBDR at a recent workshop. Models, within the context of this paper, include both computational and conceptual mental models. As such, the discussions summarized in this article seek to understand the connection between these two categories of models.

big data↗

Semantic Interaction for Visual Analytics: Toward Coupling Cognition and Computation

The dissertation discussed in this article [1] was written in the midst of an era of digitization. The world is becoming increasingly instrumented with sensors, monitoring, and other methods for generating data describing social, physical, and natural phenomena. Thus, data exist with the potential of being analyzed to uncover, or discover, the phenomena from which it was created. However, as the analytic models leveraged to analyze these data continue to increase in complexity and computational capability, how can visualizations and user interaction methodologies adapt and evolve to continue to foster discovery and sensemaking?

semantic interaction↗

From Streaming Data to Streaming Insights: The Impact of Data Velocities on Mental Models

The rise of Big Data has influenced the design and technical implementation of visual analytic tools required to handle the increased volumes, velocities, and varieties of data. This has required a set of data management and computational advancements to allow us to store and compute on such datasets. However, as the ultimate goal of visual analytic technology is to enable the discovery and creation of insights from the users, an under-explored area is understanding how these datasets impact their mental models. That is, how have the analytic processes and strategies of users changed? How have users changed their perception of how to leverage, and ask questions of, these datasets?

analysis in motion↗

The Human is the Loop: New Directions for Visual Analytics

Visual analytics is the science of marrying interactive visualizations and analytic algorithms to support exploratory knowledge discovery in large datasets. We argue for a shift from a ‘human in the loop’ philosophy for visual analytics to a ‘human is the loop’ viewpoint, where the focus is on recognizing analysts’ work processes, and seamlessly fitting analytics into that existing interactive process. We survey a range of projects that provide visual analytic support contextually in the sensemaking loop, and outline a research agenda along with future challenges.

data mining↗

Typograph: Multiscale Spatial Exploration of Text Documents

Visualizing large document collections using a spatial layout of terms can enable quick overviews of information. However, these metaphors (e.g., word clouds, tag clouds, etc.) often lack interactivity to explore the information and the location and rendering of the terms are often not based on mathematical models that maintain relative distances from other information based on similarity metrics. Further, transitioning between levels of detail (i.e., from terms to full documents) can be challanging. In this paper, we present Typograph, a multi-scale spatial exploration visualization for large document collections. Based on the term-based visualization methods, Typograh enables multipel levels of detail (terms, phrases, snippets, and full documents) within the single spatialization. Further, the information is placed based on their relative similarity to other information to create the “near = similar” geography metaphor. This paper discusses the design principles and functionality of Typograph and presents a use case analyzing Wikipedia to demonstrate usage.

sensemaking↗

MultiFacet: A Faceted Interface for Browsing Large Multimedia Collections

Faceted browsing is a common technique for exploring collections where the data can be grouped into a number of pre-defined categories, most often generated from textual metadata. Historically, faceted browsing has been applied to a single data type such as text or image data. However, typical collections contain multiple data types, such as information from web pages that contain text, images, and video. Additionally, when browsing a collection of images and video, facets are often created based on the metadata which may be incomplete, inaccurate, or missing altogether instead of the actual visual content contained within those images and video. In this work we address these limitations by presenting MultiFacet, a faceted browsing interface that supports multiple data types. MultiFacet constructs facets for images and video in a collection from the visual content using computer vision techniques. These visual facets can then be browsed in conjunction with text facets within a single interface to reveal relationships and phenomena within multimedia collections. Additionally, we present a use case based on real-world data, demonstrating the utility of this approach towards browsing a large multimedia data collection.

content-based image retrieval↗

Large High Resolution Displays for Co-Located Collaborative Sensemaking: Display Usage and Territoriality

Large, high-resolution vertical displays carry the potential to increase the accuracy of collaborative sensemaking, given correctly designed visual analytics tools. From an exploratory user study using a fictional textual intelligence analysis task, we investigated how users interact with the display to construct spatial schemas and externalize information, as well as how they establish shared and private territories. We investigated the space management strategies of users partitioned by type of tool philosophy followed (visualization- or text-centric). We classified the types of territorial behavior exhibited in terms of how the users interacted with information on the display (integrated or independent workspaces). Next, we examined how territorial behavior impacted the common ground between the pairs of users. Finally, we offer design suggestions for building future co-located collaborative visual analytics tools specifically for use on large, high-resolution vertical displays.

co-located collaborative sensemaking↗

Beyond Control Panels: Direct Manipulation for Visual Analytics

Information Visualization strives to provide visual representations through which users can think about and gain insight into information. By leveraging the visual and cognitive systems of humans, complex relationships and phenomena occurring within datasets can be uncovered by exploring information visually. Interaction metaphors for such visualizations are designed to enable users direct control over the filters, queries, and other parameters controlling how the data is visually represented. Through the evolution of information visualization, more complex mathematical and data analytic models are being used to visualize relationships and patterns in data – creating the field of Visual Analytics. However, the expectations for how users interact with these visualizations has remained largely unchanged – focused primarily on the direct manipulation of parameters of the underlying mathematical models. In this article we present an opportunity to evolve the methodology for user interaction from the direct manipulation of parameters through visual control panels, to interactions designed specifically for visual analytic systems. Instead of focusing on traditional direct manipulation of mathematical parameters, the evolution of the field can be realized through direct manipulation within the visual representation – where users can not only gain insight, but also interact. This article describes future directions and research challenges that fundamentally change the meaning of direct manipulation with regards to visual analytics, advancing the Science of Interaction.

user interaction↗

How Analysts Cognitively “Connect the Dots”

As analysts attempt to make sense of a collection of documents, such as intelligence analysis reports, they may wish to “connect the dots” between pieces of information that may initially seem unrelated. This process of synthesizing information between information requires users to make connections between pairs of documents, creating a conceptual story. We conducted a user study to analyze the process by which users connect pairs of documents and how they spatially arrange information. Users created conceptual stories that connected the dots using organizational strategies that ranged in complexity. We propose taxonomies for cognitive connections and physical structures used when trying to “connect the dots” between two documents. We compared the user-created stories with a data-mining algorithm that constructs chains of documents using co-occurrence metrics. Using the insight gained into the storytelling process, we offer design considerations for the existing data mining algorithm and corresponding tools to combine the power of data mining and the complex cognitive processing of analysts.

data mining↗