Kirsten Whitley
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kirsten Whitley has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Eric Krokos
Department of Defense, Washington, DC, USA
10 shared publications - Chris North
Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA
7 shared publications - Amitabh Varshney
University of Maryland, College Park
4 shared publications - Sungwon In
Virginia Tech, Blacksburg, Virginia, USA
3 shared publications - Yalong Yang
School of Interactive Computing, Georgia Institute of Technology, Atlanta, Georgia, USA
3 shared publications - Alexander Rowden
Government of the United States of America
2 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
Space-to-Report: Transforming Spatial Layouts into Narrative Reports for Fluid Iterative Sensemaking
Textual sensemaking in spatial layouts allows users to externalize complex mental models, yet synthesizing these unstructured arrangements into linear narratives remains a severe cognitive burden. Current LLM-assisted tools largely ignore the rich structural and semantic context embedded within 2D space. To address this, we introduce the Space-to-Report framework, a novel paradigm leveraging Space-Augmented Generation (SAG) to translate 2D spatial layouts into steerable constraints for continuous narrative generation. We instantiate this framework in ReSPIRE, a prototype that maps interactive spatial layouts to narrative reports to stimulate human reflection-in-action for iterative sensemaking. An empirical evaluation confirms that SAG achieves predictable, linear controllability over space-report alignment under controlled spatial inputs. Furthermore, a user study ( N = 12) shows that ReSPIRE effectively bridges the gap between human spatial thinking and LLM linear generation, significantly reducing cognitive load while accelerating iteration. Crucially, validated by empirical behavioral logs, the framework drives a fundamental workflow shift toward fluid, iterative sensemaking, positioning the human as a strategic “architect” and the LLM as an aligned “executor” within a shared cognitive space.
- 14 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
Open AccessSpace-to-Report: Transforming Spatial Layouts into Narrative Reports for Fluid Iterative Sensemaking
Textual sensemaking in spatial layouts allows users to externalize complex mental models, yet synthesizing these unstructured arrangements into linear narratives remains a severe cognitive burden. Current LLM-assisted tools largely ignore the rich structural and semantic context embedded within 2D space. To address this, we introduce the Space-to-Report framework, a novel paradigm leveraging Space-Augmented Generation (SAG) to translate 2D spatial layouts into steerable constraints for continuous narrative generation. We instantiate this framework in ReSPIRE, a prototype that maps interactive spatial layouts to narrative reports to stimulate human reflection-in-action for iterative sensemaking. An empirical evaluation confirms that SAG achieves predictable, linear controllability over space-report alignment under controlled spatial inputs. Furthermore, a user study ( N = 12) shows that ReSPIRE effectively bridges the gap between human spatial thinking and LLM linear generation, significantly reducing cognitive load while accelerating iteration. Crucially, validated by empirical behavioral logs, the framework drives a fundamental workflow shift toward fluid, iterative sensemaking, positioning the human as a strategic “architect” and the LLM as an aligned “executor” within a shared cognitive space.
- Open Access
- 7 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction
Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can automate narrative generation from spatial layouts, current collage-based and re-generation methods struggle to support the incremental spatial refinements inherent to the sensemaking process. We identify three critical gaps in existing spatial-textual generation: interaction-revision misalignment, human-LLM intent misalignment, and lack of granular customization. To address these, we introduce Semantic Prompting, a framework for spatial refinement that perceives semantic interactions, reasons about refinement intent, and performs targeted positional revisions. We implemented S-prism to realize this framework. The empirical evaluation demonstrated that S-prism effectively enhanced the precision of interaction-revision refinement. A user study (N = 14) highlighted how participants leveraged S-prism for incremental formalization through interactive steering. Results showed that users valued its efficient, adaptable, and trustworthy support, which effectively strengthens human-LLM intent alignment.
- 7 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessSemantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction
Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can automate narrative generation from spatial layouts, current collage-based and re-generation methods struggle to support the incremental spatial refinements inherent to the sensemaking process. We identify three critical gaps in existing spatial-textual generation: interaction-revision misalignment, human-LLM intent misalignment, and lack of granular customization. To address these, we introduce Semantic Prompting, a framework for spatial refinement that perceives semantic interactions, reasons about refinement intent, and performs targeted positional revisions. We implemented S-prism to realize this framework. The empirical evaluation demonstrated that S-prism effectively enhanced the precision of interaction-revision refinement. A user study (N = 14) highlighted how participants leveraged S-prism for incremental formalization through interactive steering. Results showed that users valued its efficient, adaptable, and trustworthy support, which effectively strengthens human-LLM intent alignment.
- Open Access
- 7 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-9
LLM-Augmented Semantic Steering of Text Embedding Projection Spaces
- 7 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessLLM-Augmented Semantic Steering of Text Embedding Projection Spaces
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1687-1703
SIA: A Framework for Context-Aware Intent Clarification in Speech-Driven Immersive Analytics
The rise of generative AI has increased attention to voice interfaces. In immersive analytics, we conceptualize this trend as Speech-driven Immersive Analytics. While speech interfaces enable natural interactions, users, especially novices, still face a learning curve in articulating analytic intent and exploring data during the foraging phase. Prior work has primarily addressed these challenges through multimodal interaction or textual disambiguation. We introduce a context-aware Speech-driven Immersive Analytics framework (SIA) as a speech-oriented approach that leverages speech acts to convey actionable intent. This framework (SIA) was designed based on a formative study, a prototype development, three technical studies, and a user study. By extracting speech acts from utterances, SIA infers analytic tasks and embodiment tendencies, then integrates them with spatial, chart, and data context to generate feedforward: previews of potential actions and outcomes. The formative study identified user needs. The technical studies demonstrated that SIA improved the inference quality, enabling context-aware feedforward generation. The user study highlighted that the SIA-based prototype was responsive and intuitive, and feedforward helped users learn during the onboarding phase of data exploration. In particular, the user study identified which feedforward elements participants referenced and how they applied them when expressing intent in immersive analytics. Our key technical findings emphasize that the ensemble model, embedded in the Uncertainty Estimator, improves accuracy and stabilizes task inference. The Projector’s context summary was critical in generating context-aware feedforward. Based on these results, we discuss future research directions for intelligent Speech-driven Immersive Analytics.
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1687-1703
Open AccessSIA: A Framework for Context-Aware Intent Clarification in Speech-Driven Immersive Analytics
The rise of generative AI has increased attention to voice interfaces. In immersive analytics, we conceptualize this trend as Speech-driven Immersive Analytics. While speech interfaces enable natural interactions, users, especially novices, still face a learning curve in articulating analytic intent and exploring data during the foraging phase. Prior work has primarily addressed these challenges through multimodal interaction or textual disambiguation. We introduce a context-aware Speech-driven Immersive Analytics framework (SIA) as a speech-oriented approach that leverages speech acts to convey actionable intent. This framework (SIA) was designed based on a formative study, a prototype development, three technical studies, and a user study. By extracting speech acts from utterances, SIA infers analytic tasks and embodiment tendencies, then integrates them with spatial, chart, and data context to generate feedforward: previews of potential actions and outcomes. The formative study identified user needs. The technical studies demonstrated that SIA improved the inference quality, enabling context-aware feedforward generation. The user study highlighted that the SIA-based prototype was responsive and intuitive, and feedforward helped users learn during the onboarding phase of data exploration. In particular, the user study identified which feedforward elements participants referenced and how they applied them when expressing intent in immersive analytics. Our key technical findings emphasize that the ensemble model, embedded in the Uncertainty Estimator, improves accuracy and stabilizes task inference. The Projector’s context summary was critical in generating context-aware feedforward. Based on these results, we discuss future research directions for intelligent Speech-driven Immersive Analytics.
- Open Access
- 16 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 22 (5) , 1-17
Assessing the Scalability of Immersive WiFi Visualizations
Current commercial applications for visualizing WiFi data often provide limited capabilities. Few existing models effectively present multiple routers within an environmental context while simultaneously conveying signal strength and channel frequency information. However, recent academic studies have proposed visualizations that can. These novel visualizations are effective for analytical tasks in small data sets. However, their ability to help users with larger datasets has not yet been demonstrated. This work identifies Contour Lines, Wavelines, and Stacked Bars as three promising visualizations for immersive WiFi signal visualization. We tested their performance when representing networks with 10, 25, and 40 routers through an analytical user study.
- 16 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 22 (5) , 1-17
Open AccessAssessing the Scalability of Immersive WiFi Visualizations
Current commercial applications for visualizing WiFi data often provide limited capabilities. Few existing models effectively present multiple routers within an environmental context while simultaneously conveying signal strength and channel frequency information. However, recent academic studies have proposed visualizations that can. These novel visualizations are effective for analytical tasks in small data sets. However, their ability to help users with larger datasets has not yet been demonstrated. This work identifies Contour Lines, Wavelines, and Stacked Bars as three promising visualizations for immersive WiFi signal visualization. We tested their performance when representing networks with 10, 25, and 40 routers through an analytical user study.
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (1) , 1098-1108
Embodied Natural Language Interaction (NLI): Speech Input Patterns in Immersive Analytics
Embodiment shapes how users verbally express intent when interacting with data through speech interfaces in immersive analytics. Despite growing interest in Natural Language Interactions (NLIs) for visual analytics in immersive environments, users' speech patterns and their use of embodiment cues in speech remain underexplored. Understanding their interplay is crucial to bridging the gap between users' intent and an immersive analytic system. To address this, we report the results from 15 participants in a user study conducted using the Wizard of Oz method. We performed axial coding on 1,280 speech acts derived from 734 utterances, examining how analysis tasks are carried out with embodiment and linguistic features. Next, we measured Speech Input Uncertainty for each analysis task using the semantic entropy of utterances, estimating how uncertain users' speech inputs appear to an analytic system. Through these analyses, we identified five speech input patterns, showing that users dynamically blend embodied and non-embodied speech acts depending on data analysis tasks, phases, and Embodiment Reliance driven by the counts and types of embodiment cues in each utterance. We then examined how these patterns align with user reflections on factors that challenge speech interaction during the study. Finally, we propose design implications aligned with the five patterns.
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (1) , 1098-1108
Embodied Natural Language Interaction (NLI): Speech Input Patterns in Immersive Analytics
Embodiment shapes how users verbally express intent when interacting with data through speech interfaces in immersive analytics. Despite growing interest in Natural Language Interactions (NLIs) for visual analytics in immersive environments, users' speech patterns and their use of embodiment cues in speech remain underexplored. Understanding their interplay is crucial to bridging the gap between users' intent and an immersive analytic system. To address this, we report the results from 15 participants in a user study conducted using the Wizard of Oz method. We performed axial coding on 1,280 speech acts derived from 734 utterances, examining how analysis tasks are carried out with embodiment and linguistic features. Next, we measured Speech Input Uncertainty for each analysis task using the semantic entropy of utterances, estimating how uncertain users' speech inputs appear to an analytic system. Through these analyses, we identified five speech input patterns, showing that users dynamically blend embodied and non-embodied speech acts depending on data analysis tasks, phases, and Embodiment Reliance driven by the counts and types of embodiment cues in each utterance. We then examined how these patterns align with user reflections on factors that challenge speech interaction during the study. Finally, we propose design implications aligned with the five patterns.
- Open Access
- 12 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Investigating Seamless Transitions Between Immersive Computational Notebooks and Embodied Data Interactions
- 12 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessInvestigating Seamless Transitions Between Immersive Computational Notebooks and Embodied Data Interactions
- Open Access
- 12 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Towards an Embodied Composition Framework for Organizing Immersive Computational Notebooks
- 12 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessTowards an Embodied Composition Framework for Organizing Immersive Computational Notebooks
- Open Access
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 641-659
Enhancing Immersive Sensemaking with Gaze-Driven Recommendation Cues
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 641-659
Open AccessEnhancing Immersive Sensemaking with Gaze-Driven Recommendation Cues
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Evaluating Navigation and Comparison Performance of Computational Notebooks on Desktop and in Virtual Reality
The computational notebook serves as a versatile tool for data analysis. However, its conventional user interface falls short of keeping pace with the ever-growing data-related tasks, signaling the need for novel approaches. With the rapid development of interaction techniques and computing environments, there is a growing interest in integrating emerging technologies in data-driven workflows. Virtual reality, in particular, has demonstrated its potential in interactive data visualizations. In this work, we aimed to experiment with adapting computational notebooks into VR and verify the potential benefits VR can bring. We focus on the navigation and comparison aspects as they are primitive components in analysts’ workflow. To further improve comparison, we have designed and implemented a Branching&Merging functionality. We tested computational notebooks on the desktop and in VR, both with and without the added Branching&Merging capability. We found VR significantly facilitated navigation compared to desktop, and the ability to create branches enhanced comparison.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessEvaluating Navigation and Comparison Performance of Computational Notebooks on Desktop and in Virtual Reality
The computational notebook serves as a versatile tool for data analysis. However, its conventional user interface falls short of keeping pace with the ever-growing data-related tasks, signaling the need for novel approaches. With the rapid development of interaction techniques and computing environments, there is a growing interest in integrating emerging technologies in data-driven workflows. Virtual reality, in particular, has demonstrated its potential in interactive data visualizations. In this work, we aimed to experiment with adapting computational notebooks into VR and verify the potential benefits VR can bring. We focus on the navigation and comparison aspects as they are primitive components in analysts’ workflow. To further improve comparison, we have designed and implemented a Branching&Merging functionality. We tested computational notebooks on the desktop and in VR, both with and without the added Branching&Merging capability. We found VR significantly facilitated navigation compared to desktop, and the ability to create branches enhanced comparison.