Guided Data Discovery in Interactive Visualizations via Active Search

Monadjemi, Shayan; Ha, Sunwoo; Nguyen, Quan; Chai, Henry; Garnett, Roman; Ottley, Alvitta

doi:10.1109/vis54862.2022.00023

Cited by 6 publications

(19 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another example is the active search algorithm [JMC * 17] which defines utility as the total number of relevant data points discovered by the end of a session, where members of a given class are deemed to be relevant. Active search has recently been augmented into visual analytic workflows for data foraging [MHN * 22]. Recently, va researchers have investigated utility functions from human‐centric and data‐centric perspectives.…”

Section: Discussion and Future Workmentioning

confidence: 99%

“…For example, the information foraging theory states analysts' desire to maximize information intake while minimizing effort [PC99]. This example applies to visual analytic settings where analysts wish to identify as many relevant points as possible while minimizing distractions with irrelevant points [MHN * 22]. In Scenario 2, for example, Bob has a mental utility function which ranks some houses higher than others based on a combination of their characteristics.…”

Section: Types Of Behavior In Visual Analytic Agentsmentioning

confidence: 99%

“…At the same time, larger amounts of data and the growing number of analytic techniques have resulted in more complex va scenarios than before. These advances in ai and rising complexities in va settings have further ignited the desire to design mixed‐initiative visual analytic systems which identify the user's analytic intents (e.g., [OGW19, MGO20]) and take actions to contribute to the process (e.g., [KCD * 19, SSKEA21, WDC * 17, MHN * 22]). While existing frameworks of va are rich in detail, we argue that they lack expressivity to reason about the entire mixed‐initiative va pipeline.…”

Section: Introductionmentioning

confidence: 99%

“…We believe recent advances in mixed‐initiative va systems fit this perspective. For example, user modeling techniques enable artificial agents to reason about analysts by observing their low‐level interactions [HMGO22] and recommendation systems take actions to assist analysts in exploration [SSKEA21, MHN * 22].…”

Section: Introductionmentioning

confidence: 99%

“…For example, some have focused on the complex cognitive processes humans exhibit while making decisions (e.g., [KKGMH21,WBFE17,LCO20, CWCO19, Ott20]), whereas others have focused on improving machine intelligence with the help of humans (e.g. [KHB21,CEH * 19, MHN * 22, HMGO22]). In this work, we focus on mixed‐initiative visual analytic settings where the system learns from the user's interactions and assists them in their analytic task.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Monadjemi

Guo

Gotz

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

The 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.

show abstract

Section: Discussion and Future Workmentioning

confidence: 99%

Section: Types Of Behavior In Visual Analytic Agentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Monadjemi

Guo

Gotz

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

Confides: A Visual Analytics Solution for Automated Speech Recognition Analysis and Exploration

Ha,

Lim,

Crouser

et al. 2024

2024 IEEE Visualization and Visual Analytics (VIS)

View full text Add to dashboard Cite

Guided By AI: Navigating Trust, Bias, and Data Exploration in AI‐Guided Visual Analytics

Ha,

Monadjemi,

Ottley

2024

Computer Graphics Forum

View full text Add to dashboard Cite

The increasing integration of artificial intelligence (AI) in visual analytics (VA) tools raises vital questions about the behavior of users, their trust, and the potential of induced biases when provided with guidance during data exploration. We present an experiment where participants engaged in a visual data exploration task while receiving intelligent suggestions supplemented with four different transparency levels. We also modulated the difficulty of the task (easy or hard) to simulate a more tedious scenario for the analyst. Our results indicate that participants were more inclined to accept suggestions when completing a more difficult task despite the ai's lower suggestion accuracy. Moreover, the levels of transparency tested in this study did not significantly affect suggestion usage or subjective trust ratings of the participants. Additionally, we observed that participants who utilized suggestions throughout the task explored a greater quantity and diversity of data points. We discuss these findings and the implications of this research for improving the design and effectiveness of ai‐guided va tools.

show abstract

Guided Data Discovery in Interactive Visualizations via Active Search

Cited by 6 publications

References 27 publications

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

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

Confides: A Visual Analytics Solution for Automated Speech Recognition Analysis and Exploration

Guided By AI: Navigating Trust, Bias, and Data Exploration in AI‐Guided Visual Analytics

Contact Info

Product

Resources

About